Coding the presence of visual objects in a recurrent neural network of visual cortex.

PubMed

Zwickel, Timm; Wachtler, Thomas; Eckhorn, Reinhard

2007-01-01

Before we can recognize a visual object, our visual system has to segregate it from its background. This requires a fast mechanism for establishing the presence and location of objects independently of their identity. Recently, border-ownership neurons were recorded in monkey visual cortex which might be involved in this task [Zhou, H., Friedmann, H., von der Heydt, R., 2000. Coding of border ownership in monkey visual cortex. J. Neurosci. 20 (17), 6594-6611]. In order to explain the basic mechanisms required for fast coding of object presence, we have developed a neural network model of visual cortex consisting of three stages. Feed-forward and lateral connections support coding of Gestalt properties, including similarity, good continuation, and convexity. Neurons of the highest area respond to the presence of an object and encode its position, invariant of its form. Feedback connections to the lowest area facilitate orientation detectors activated by contours belonging to potential objects, and thus generate the experimentally observed border-ownership property. This feedback control acts fast and significantly improves the figure-ground segregation required for the consecutive task of object recognition.

Automatic labeling and characterization of objects using artificial neural networks

NASA Technical Reports Server (NTRS)

Campbell, William J.; Hill, Scott E.; Cromp, Robert F.

1989-01-01

Existing NASA supported scientific data bases are usually developed, managed and populated in a tedious, error prone and self-limiting way in terms of what can be described in a relational Data Base Management System (DBMS). The next generation Earth remote sensing platforms, i.e., Earth Observation System, (EOS), will be capable of generating data at a rate of over 300 Mbs per second from a suite of instruments designed for different applications. What is needed is an innovative approach that creates object-oriented databases that segment, characterize, catalog and are manageable in a domain-specific context and whose contents are available interactively and in near-real-time to the user community. Described here is work in progress that utilizes an artificial neural net approach to characterize satellite imagery of undefined objects into high-level data objects. The characterized data is then dynamically allocated to an object-oriented data base where it can be reviewed and assessed by a user. The definition, development, and evolution of the overall data system model are steps in the creation of an application-driven knowledge-based scientific information system.

Two-stage neural-network-based technique for Urdu character two-dimensional shape representation, classification, and recognition

NASA Astrophysics Data System (ADS)

Megherbi, Dalila B.; Lodhi, S. M.; Boulenouar, A. J.

2001-03-01

This work is in the field of automated document processing. This work addresses the problem of representation and recognition of Urdu characters using Fourier representation and a Neural Network architecture. In particular, we show that a two-stage Neural Network scheme is used here to make classification of 36 Urdu characters into seven sub-classes namely subclasses characterized by seven proposed and defined fuzzy features specifically related to Urdu characters. We show that here Fourier Descriptors and Neural Network provide a remarkably simple way to draw definite conclusions from vague, ambiguous, noisy or imprecise information. In particular, we illustrate the concept of interest regions and describe a framing method that provides a way to make the proposed technique for Urdu characters recognition robust and invariant to scaling and translation. We also show that a given character rotation is dealt with by using the Hotelling transform. This transform is based upon the eigenvalue decomposition of the covariance matrix of an image, providing a method of determining the orientation of the major axis of an object within an image. Finally experimental results are presented to show the power and robustness of the proposed two-stage Neural Network based technique for Urdu character recognition, its fault tolerance, and high recognition accuracy.

A recurrent neural network for nonlinear optimization with a continuously differentiable objective function and bound constraints.

PubMed

Liang, X B; Wang, J

2000-01-01

This paper presents a continuous-time recurrent neural-network model for nonlinear optimization with any continuously differentiable objective function and bound constraints. Quadratic optimization with bound constraints is a special problem which can be solved by the recurrent neural network. The proposed recurrent neural network has the following characteristics. 1) It is regular in the sense that any optimum of the objective function with bound constraints is also an equilibrium point of the neural network. If the objective function to be minimized is convex, then the recurrent neural network is complete in the sense that the set of optima of the function with bound constraints coincides with the set of equilibria of the neural network. 2) The recurrent neural network is primal and quasiconvergent in the sense that its trajectory cannot escape from the feasible region and will converge to the set of equilibria of the neural network for any initial point in the feasible bound region. 3) The recurrent neural network has an attractivity property in the sense that its trajectory will eventually converge to the feasible region for any initial states even at outside of the bounded feasible region. 4) For minimizing any strictly convex quadratic objective function subject to bound constraints, the recurrent neural network is globally exponentially stable for almost any positive network parameters. Simulation results are given to demonstrate the convergence and performance of the proposed recurrent neural network for nonlinear optimization with bound constraints.

Crack orientation and depth estimation in a low-pressure turbine disc using a phased array ultrasonic transducer and an artificial neural network.

PubMed

Yang, Xiaoxia; Chen, Shili; Jin, Shijiu; Chang, Wenshuang

2013-09-13

Stress corrosion cracks (SCC) in low-pressure steam turbine discs are serious hidden dangers to production safety in the power plants, and knowing the orientation and depth of the initial cracks is essential for the evaluation of the crack growth rate, propagation direction and working life of the turbine disc. In this paper, a method based on phased array ultrasonic transducer and artificial neural network (ANN), is proposed to estimate both the depth and orientation of initial cracks in the turbine discs. Echo signals from cracks with different depths and orientations were collected by a phased array ultrasonic transducer, and the feature vectors were extracted by wavelet packet, fractal technology and peak amplitude methods. The radial basis function (RBF) neural network was investigated and used in this application. The final results demonstrated that the method presented was efficient in crack estimation tasks.

Crack Orientation and Depth Estimation in a Low-Pressure Turbine Disc Using a Phased Array Ultrasonic Transducer and an Artificial Neural Network

PubMed Central

Yang, Xiaoxia; Chen, Shili; Jin, Shijiu; Chang, Wenshuang

2013-01-01

Stress corrosion cracks (SCC) in low-pressure steam turbine discs are serious hidden dangers to production safety in the power plants, and knowing the orientation and depth of the initial cracks is essential for the evaluation of the crack growth rate, propagation direction and working life of the turbine disc. In this paper, a method based on phased array ultrasonic transducer and artificial neural network (ANN), is proposed to estimate both the depth and orientation of initial cracks in the turbine discs. Echo signals from cracks with different depths and orientations were collected by a phased array ultrasonic transducer, and the feature vectors were extracted by wavelet packet, fractal technology and peak amplitude methods. The radial basis function (RBF) neural network was investigated and used in this application. The final results demonstrated that the method presented was efficient in crack estimation tasks. PMID:24064602

Time-oriented hierarchical method for computation of principal components using subspace learning algorithm.

PubMed

Jankovic, Marko; Ogawa, Hidemitsu

2004-10-01

Principal Component Analysis (PCA) and Principal Subspace Analysis (PSA) are classic techniques in statistical data analysis, feature extraction and data compression. Given a set of multivariate measurements, PCA and PSA provide a smaller set of "basis vectors" with less redundancy, and a subspace spanned by them, respectively. Artificial neurons and neural networks have been shown to perform PSA and PCA when gradient ascent (descent) learning rules are used, which is related to the constrained maximization (minimization) of statistical objective functions. Due to their low complexity, such algorithms and their implementation in neural networks are potentially useful in cases of tracking slow changes of correlations in the input data or in updating eigenvectors with new samples. In this paper we propose PCA learning algorithm that is fully homogeneous with respect to neurons. The algorithm is obtained by modification of one of the most famous PSA learning algorithms--Subspace Learning Algorithm (SLA). Modification of the algorithm is based on Time-Oriented Hierarchical Method (TOHM). The method uses two distinct time scales. On a faster time scale PSA algorithm is responsible for the "behavior" of all output neurons. On a slower scale, output neurons will compete for fulfillment of their "own interests". On this scale, basis vectors in the principal subspace are rotated toward the principal eigenvectors. At the end of the paper it will be briefly analyzed how (or why) time-oriented hierarchical method can be used for transformation of any of the existing neural network PSA method, into PCA method.

Hebbian based learning with winner-take-all for spiking neural networks

NASA Astrophysics Data System (ADS)

Gupta, Ankur; Long, Lyle

2009-03-01

Learning methods for spiking neural networks are not as well developed as the traditional neural networks that widely use back-propagation training. We propose and implement a Hebbian based learning method with winner-take-all competition for spiking neural networks. This approach is spike time dependent which makes it naturally well suited for a network of spiking neurons. Homeostasis with Hebbian learning is implemented which ensures stability and quicker learning. Homeostasis implies that the net sum of incoming weights associated with a neuron remains the same. Winner-take-all is also implemented for competitive learning between output neurons. We implemented this learning rule on a biologically based vision processing system that we are developing, and use layers of leaky integrate and fire neurons. The network when presented with 4 bars (or Gabor filters) of different orientation learns to recognize the bar orientations (or Gabor filters). After training, each output neuron learns to recognize a bar at specific orientation and responds by firing more vigorously to that bar and less vigorously to others. These neurons are found to have bell shaped tuning curves and are similar to the simple cells experimentally observed by Hubel and Wiesel in the striate cortex of cat and monkey.

A system of IAC neural networks as the basis for self-organization in a sociological dynamical system simulation.

PubMed

Duong, D V; Reilly, K D

1995-10-01

This sociological simulation uses the ideas of semiotics and symbolic interactionism to demonstrate how an appropriately developed associative memory in the minds of individuals on the microlevel can self-organize into macrolevel dissipative structures of societies such as racial cultural/economic classes, status symbols and fads. The associative memory used is based on an extension of the IAC neural network (the Interactive Activation and Competition network). Several IAC networks act together to form a society by virtue of their human-like properties of intuition and creativity. These properties give them the ability to create and understand signs, which lead to the macrolevel structures of society. This system is implemented in hierarchical object oriented container classes which facilitate change in deep structure. Graphs of general trends and an historical account of a simulation run of this dynamical system are presented.

Keypoint Density-Based Region Proposal for Fine-Grained Object Detection and Classification Using Regions with Convolutional Neural Network Features

DTIC Science & Technology

2015-12-15

Keypoint Density-based Region Proposal for Fine-Grained Object Detection and Classification using Regions with Convolutional Neural Network ... Convolutional Neural Networks (CNNs) enable them to outperform conventional techniques on standard object detection and classification tasks, their...detection accuracy and speed on the fine-grained Caltech UCSD bird dataset (Wah et al., 2011). Recently, Convolutional Neural Networks (CNNs), a deep

Artificial intelligence, neural network, and Internet tool integration in a pathology workstation to improve information access

NASA Astrophysics Data System (ADS)

Sargis, J. C.; Gray, W. A.

1999-03-01

The APWS allows user friendly access to several legacy systems which would normally each demand domain expertise for proper utilization. The generalized model, including objects, classes, strategies and patterns is presented. The core components of the APWS are the Microsoft Windows 95 Operating System, Oracle, Oracle Power Objects, Artificial Intelligence tools, a medical hyperlibrary and a web site. The paper includes a discussion of how could be automated by taking advantage of the expert system, object oriented programming and intelligent relational database tools within the APWS.

Toward a self-organizing pre-symbolic neural model representing sensorimotor primitives.

PubMed

Zhong, Junpei; Cangelosi, Angelo; Wermter, Stefan

2014-01-01

The acquisition of symbolic and linguistic representations of sensorimotor behavior is a cognitive process performed by an agent when it is executing and/or observing own and others' actions. According to Piaget's theory of cognitive development, these representations develop during the sensorimotor stage and the pre-operational stage. We propose a model that relates the conceptualization of the higher-level information from visual stimuli to the development of ventral/dorsal visual streams. This model employs neural network architecture incorporating a predictive sensory module based on an RNNPB (Recurrent Neural Network with Parametric Biases) and a horizontal product model. We exemplify this model through a robot passively observing an object to learn its features and movements. During the learning process of observing sensorimotor primitives, i.e., observing a set of trajectories of arm movements and its oriented object features, the pre-symbolic representation is self-organized in the parametric units. These representational units act as bifurcation parameters, guiding the robot to recognize and predict various learned sensorimotor primitives. The pre-symbolic representation also accounts for the learning of sensorimotor primitives in a latent learning context.

Toward a self-organizing pre-symbolic neural model representing sensorimotor primitives

PubMed Central

Zhong, Junpei; Cangelosi, Angelo; Wermter, Stefan

2014-01-01

The acquisition of symbolic and linguistic representations of sensorimotor behavior is a cognitive process performed by an agent when it is executing and/or observing own and others' actions. According to Piaget's theory of cognitive development, these representations develop during the sensorimotor stage and the pre-operational stage. We propose a model that relates the conceptualization of the higher-level information from visual stimuli to the development of ventral/dorsal visual streams. This model employs neural network architecture incorporating a predictive sensory module based on an RNNPB (Recurrent Neural Network with Parametric Biases) and a horizontal product model. We exemplify this model through a robot passively observing an object to learn its features and movements. During the learning process of observing sensorimotor primitives, i.e., observing a set of trajectories of arm movements and its oriented object features, the pre-symbolic representation is self-organized in the parametric units. These representational units act as bifurcation parameters, guiding the robot to recognize and predict various learned sensorimotor primitives. The pre-symbolic representation also accounts for the learning of sensorimotor primitives in a latent learning context. PMID:24550798

Modified-hybrid optical neural network filter for multiple object recognition within cluttered scenes

NASA Astrophysics Data System (ADS)

Kypraios, Ioannis; Young, Rupert C. D.; Chatwin, Chris R.

2009-08-01

Motivated by the non-linear interpolation and generalization abilities of the hybrid optical neural network filter between the reference and non-reference images of the true-class object we designed the modifiedhybrid optical neural network filter. We applied an optical mask to the hybrid optical neural network's filter input. The mask was built with the constant weight connections of a randomly chosen image included in the training set. The resulted design of the modified-hybrid optical neural network filter is optimized for performing best in cluttered scenes of the true-class object. Due to the shift invariance properties inherited by its correlator unit the filter can accommodate multiple objects of the same class to be detected within an input cluttered image. Additionally, the architecture of the neural network unit of the general hybrid optical neural network filter allows the recognition of multiple objects of different classes within the input cluttered image by modifying the output layer of the unit. We test the modified-hybrid optical neural network filter for multiple objects of the same and of different classes' recognition within cluttered input images and video sequences of cluttered scenes. The filter is shown to exhibit with a single pass over the input data simultaneously out-of-plane rotation, shift invariance and good clutter tolerance. It is able to successfully detect and classify correctly the true-class objects within background clutter for which there has been no previous training.

Multi-Frame Convolutional Neural Networks for Object Detection in Temporal Data

DTIC Science & Technology

2017-03-01

maximum 200 words) Given the problem of detecting objects in video , existing neural-network solutions rely on a post-processing step to combine...information across frames and strengthen conclusions. This technique has been successful for videos with simple, dominant objects but it cannot detect objects...Computer Science iii THIS PAGE INTENTIONALLY LEFT BLANK iv ABSTRACT Given the problem of detecting objects in video , existing neural-network solutions rely

Patterns recognition of electric brain activity using artificial neural networks

NASA Astrophysics Data System (ADS)

Musatov, V. Yu.; Pchelintseva, S. V.; Runnova, A. E.; Hramov, A. E.

2017-04-01

An approach for the recognition of various cognitive processes in the brain activity in the perception of ambiguous images. On the basis of developed theoretical background and the experimental data, we propose a new classification of oscillating patterns in the human EEG by using an artificial neural network approach. After learning of the artificial neural network reliably identified cube recognition processes, for example, left-handed or right-oriented Necker cube with different intensity of their edges, construct an artificial neural network based on Perceptron architecture and demonstrate its effectiveness in the pattern recognition of the EEG in the experimental.

Calculation of Crystallographic Texture of BCC Steels During Cold Rolling

NASA Astrophysics Data System (ADS)

Das, Arpan

2017-05-01

BCC alloys commonly tend to develop strong fibre textures and often represent as isointensity diagrams in φ 1 sections or by fibre diagrams. Alpha fibre in bcc steels is generally characterised by <110> crystallographic axis parallel to the rolling direction. The objective of present research is to correlate carbon content, carbide dispersion, rolling reduction, Euler angles (ϕ) (when φ 1 = 0° and φ 2 = 45° along alpha fibre) and the resulting alpha fibre texture orientation intensity. In the present research, Bayesian neural computation has been employed to correlate these and compare with the existing feed-forward neural network model comprehensively. Excellent match to the measured texture data within the bounding box of texture training data set has been already predicted through the feed-forward neural network model by other researchers. Feed-forward neural network prediction outside the bounds of training texture data showed deviations from the expected values. Currently, Bayesian computation has been similarly applied to confirm that the predictions are reasonable in the context of basic metallurgical principles, and matched better outside the bounds of training texture data set than the reported feed-forward neural network. Bayesian computation puts error bars on predicted values and allows significance of each individual parameters to be estimated. Additionally, it is also possible by Bayesian computation to estimate the isolated influence of particular variable such as carbon concentration, which exactly cannot in practice be varied independently. This shows the ability of the Bayesian neural network to examine the new phenomenon in situations where the data cannot be accessed through experiments.

A New Artificial Neural Network Approach in Solving Inverse Kinematics of Robotic Arm (Denso VP6242)

PubMed Central

Dülger, L. Canan; Kapucu, Sadettin

2016-01-01

This paper presents a novel inverse kinematics solution for robotic arm based on artificial neural network (ANN) architecture. The motion of robotic arm is controlled by the kinematics of ANN. A new artificial neural network approach for inverse kinematics is proposed. The novelty of the proposed ANN is the inclusion of the feedback of current joint angles configuration of robotic arm as well as the desired position and orientation in the input pattern of neural network, while the traditional ANN has only the desired position and orientation of the end effector in the input pattern of neural network. In this paper, a six DOF Denso robotic arm with a gripper is controlled by ANN. The comprehensive experimental results proved the applicability and the efficiency of the proposed approach in robotic motion control. The inclusion of current configuration of joint angles in ANN significantly increased the accuracy of ANN estimation of the joint angles output. The new controller design has advantages over the existing techniques for minimizing the position error in unconventional tasks and increasing the accuracy of ANN in estimation of robot's joint angles. PMID:27610129

A New Artificial Neural Network Approach in Solving Inverse Kinematics of Robotic Arm (Denso VP6242).

PubMed

Almusawi, Ahmed R J; Dülger, L Canan; Kapucu, Sadettin

2016-01-01

This paper presents a novel inverse kinematics solution for robotic arm based on artificial neural network (ANN) architecture. The motion of robotic arm is controlled by the kinematics of ANN. A new artificial neural network approach for inverse kinematics is proposed. The novelty of the proposed ANN is the inclusion of the feedback of current joint angles configuration of robotic arm as well as the desired position and orientation in the input pattern of neural network, while the traditional ANN has only the desired position and orientation of the end effector in the input pattern of neural network. In this paper, a six DOF Denso robotic arm with a gripper is controlled by ANN. The comprehensive experimental results proved the applicability and the efficiency of the proposed approach in robotic motion control. The inclusion of current configuration of joint angles in ANN significantly increased the accuracy of ANN estimation of the joint angles output. The new controller design has advantages over the existing techniques for minimizing the position error in unconventional tasks and increasing the accuracy of ANN in estimation of robot's joint angles.

Signal processing and neural network toolbox and its application to failure diagnosis and prognosis

NASA Astrophysics Data System (ADS)

Tu, Fang; Wen, Fang; Willett, Peter K.; Pattipati, Krishna R.; Jordan, Eric H.

2001-07-01

Many systems are comprised of components equipped with self-testing capability; however, if the system is complex involving feedback and the self-testing itself may occasionally be faulty, tracing faults to a single or multiple causes is difficult. Moreover, many sensors are incapable of reliable decision-making on their own. In such cases, a signal processing front-end that can match inference needs will be very helpful. The work is concerned with providing an object-oriented simulation environment for signal processing and neural network-based fault diagnosis and prognosis. In the toolbox, we implemented a wide range of spectral and statistical manipulation methods such as filters, harmonic analyzers, transient detectors, and multi-resolution decomposition to extract features for failure events from data collected by data sensors. Then we evaluated multiple learning paradigms for general classification, diagnosis and prognosis. The network models evaluated include Restricted Coulomb Energy (RCE) Neural Network, Learning Vector Quantization (LVQ), Decision Trees (C4.5), Fuzzy Adaptive Resonance Theory (FuzzyArtmap), Linear Discriminant Rule (LDR), Quadratic Discriminant Rule (QDR), Radial Basis Functions (RBF), Multiple Layer Perceptrons (MLP) and Single Layer Perceptrons (SLP). Validation techniques, such as N-fold cross-validation and bootstrap techniques, are employed for evaluating the robustness of network models. The trained networks are evaluated for their performance using test data on the basis of percent error rates obtained via cross-validation, time efficiency, generalization ability to unseen faults. Finally, the usage of neural networks for the prediction of residual life of turbine blades with thermal barrier coatings is described and the results are shown. The neural network toolbox has also been applied to fault diagnosis in mixed-signal circuits.

Perception of Upright: Multisensory Convergence and the Role of Temporo-Parietal Cortex

PubMed Central

Kheradmand, Amir; Winnick, Ariel

2017-01-01

We inherently maintain a stable perception of the world despite frequent changes in the head, eye, and body positions. Such “orientation constancy” is a prerequisite for coherent spatial perception and sensorimotor planning. As a multimodal sensory reference, perception of upright represents neural processes that subserve orientation constancy through integration of sensory information encoding the eye, head, and body positions. Although perception of upright is distinct from perception of body orientation, they share similar neural substrates within the cerebral cortical networks involved in perception of spatial orientation. These cortical networks, mainly within the temporo-parietal junction, are crucial for multisensory processing and integration that generate sensory reference frames for coherent perception of self-position and extrapersonal space transformations. In this review, we focus on these neural mechanisms and discuss (i) neurobehavioral aspects of orientation constancy, (ii) sensory models that address the neurophysiology underlying perception of upright, and (iii) the current evidence for the role of cerebral cortex in perception of upright and orientation constancy, including findings from the neurological disorders that affect cortical function. PMID:29118736

Autonomous Navigation Apparatus With Neural Network for a Mobile Vehicle

NASA Technical Reports Server (NTRS)

Quraishi, Naveed (Inventor)

1996-01-01

An autonomous navigation system for a mobile vehicle arranged to move within an environment includes a plurality of sensors arranged on the vehicle and at least one neural network including an input layer coupled to the sensors, a hidden layer coupled to the input layer, and an output layer coupled to the hidden layer. The neural network produces output signals representing respective positions of the vehicle, such as the X coordinate, the Y coordinate, and the angular orientation of the vehicle. A plurality of patch locations within the environment are used to train the neural networks to produce the correct outputs in response to the distances sensed.

Logarithmic r-θ mapping for hybrid optical neural network filter for multiple objects recognition within cluttered scenes

NASA Astrophysics Data System (ADS)

Kypraios, Ioannis; Young, Rupert C. D.; Chatwin, Chris R.; Birch, Phil M.

2009-04-01

θThe window unit in the design of the complex logarithmic r-θ mapping for hybrid optical neural network filter can allow multiple objects of the same class to be detected within the input image. Additionally, the architecture of the neural network unit of the complex logarithmic r-θ mapping for hybrid optical neural network filter becomes attractive for accommodating the recognition of multiple objects of different classes within the input image by modifying the output layer of the unit. We test the overall filter for multiple objects of the same and of different classes' recognition within cluttered input images and video sequences of cluttered scenes. Logarithmic r-θ mapping for hybrid optical neural network filter is shown to exhibit with a single pass over the input data simultaneously in-plane rotation, out-of-plane rotation, scale, log r-θ map translation and shift invariance, and good clutter tolerance by recognizing correctly the different objects within the cluttered scenes. We record in our results additional extracted information from the cluttered scenes about the objects' relative position, scale and in-plane rotation.

Classification of 2-dimensional array patterns: assembling many small neural networks is better than using a large one.

PubMed

Chen, Liang; Xue, Wei; Tokuda, Naoyuki

2010-08-01

In many pattern classification/recognition applications of artificial neural networks, an object to be classified is represented by a fixed sized 2-dimensional array of uniform type, which corresponds to the cells of a 2-dimensional grid of the same size. A general neural network structure, called an undistricted neural network, which takes all the elements in the array as inputs could be used for problems such as these. However, a districted neural network can be used to reduce the training complexity. A districted neural network usually consists of two levels of sub-neural networks. Each of the lower level neural networks, called a regional sub-neural network, takes the elements in a region of the array as its inputs and is expected to output a temporary class label, called an individual opinion, based on the partial information of the entire array. The higher level neural network, called an assembling sub-neural network, uses the outputs (opinions) of regional sub-neural networks as inputs, and by consensus derives the label decision for the object. Each of the sub-neural networks can be trained separately and thus the training is less expensive. The regional sub-neural networks can be trained and performed in parallel and independently, therefore a high speed can be achieved. We prove theoretically in this paper, using a simple model, that a districted neural network is actually more stable than an undistricted neural network in noisy environments. We conjecture that the result is valid for all neural networks. This theory is verified by experiments involving gender classification and human face recognition. We conclude that a districted neural network is highly recommended for neural network applications in recognition or classification of 2-dimensional array patterns in highly noisy environments. Copyright (c) 2010 Elsevier Ltd. All rights reserved.

Systematic construction and control of stereo nerve vision network in intelligent manufacturing

NASA Astrophysics Data System (ADS)

Liu, Hua; Wang, Helong; Guo, Chunjie; Ding, Quanxin; Zhou, Liwei

2017-10-01

A system method of constructing stereo vision by using neural network is proposed, and the operation and control mechanism in actual operation are proposed. This method makes effective use of the neural network in learning and memory function, by after training with samples. Moreover, the neural network can learn the nonlinear relationship in the stereoscopic vision system and the internal and external orientation elements. These considerations are Worthy of attention, which includes limited constraints, the scientific of critical group, the operating speed and the operability in technical aspects. The results support our theoretical forecast.

Neural-Network Object-Recognition Program

NASA Technical Reports Server (NTRS)

Spirkovska, L.; Reid, M. B.

1993-01-01

HONTIOR computer program implements third-order neural network exhibiting invariance under translation, change of scale, and in-plane rotation. Invariance incorporated directly into architecture of network. Only one view of each object needed to train network for two-dimensional-translation-invariant recognition of object. Also used for three-dimensional-transformation-invariant recognition by training network on only set of out-of-plane rotated views. Written in C language.

[Not Available].

PubMed

Pecevski, Dejan; Natschläger, Thomas; Schuch, Klaus

2009-01-01

The Parallel Circuit SIMulator (PCSIM) is a software package for simulation of neural circuits. It is primarily designed for distributed simulation of large scale networks of spiking point neurons. Although its computational core is written in C++, PCSIM's primary interface is implemented in the Python programming language, which is a powerful programming environment and allows the user to easily integrate the neural circuit simulator with data analysis and visualization tools to manage the full neural modeling life cycle. The main focus of this paper is to describe PCSIM's full integration into Python and the benefits thereof. In particular we will investigate how the automatically generated bidirectional interface and PCSIM's object-oriented modular framework enable the user to adopt a hybrid modeling approach: using and extending PCSIM's functionality either employing pure Python or C++ and thus combining the advantages of both worlds. Furthermore, we describe several supplementary PCSIM packages written in pure Python and tailored towards setting up and analyzing neural simulations.

Neural-net-based image matching

NASA Astrophysics Data System (ADS)

Jerebko, Anna K.; Barabanov, Nikita E.; Luciv, Vadim R.; Allinson, Nigel M.

2000-04-01

The paper describes a neural-based method for matching spatially distorted image sets. The matching of partially overlapping images is important in many applications-- integrating information from images formed from different spectral ranges, detecting changes in a scene and identifying objects of differing orientations and sizes. Our approach consists of extracting contour features from both images, describing the contour curves as sets of line segments, comparing these sets, determining the corresponding curves and their common reference points, calculating the image-to-image co-ordinate transformation parameters on the basis of the most successful variant of the derived curve relationships. The main steps are performed by custom neural networks. The algorithms describe in this paper have been successfully tested on a large set of images of the same terrain taken in different spectral ranges, at different seasons and rotated by various angles. In general, this experimental verification indicates that the proposed method for image fusion allows the robust detection of similar objects in noisy, distorted scenes where traditional approaches often fail.

About turn: how object orientation affects categorisation and mental rotation.

PubMed

Milivojevic, Branka; Hamm, Jeff P; Corballis, Michael C

2011-11-01

High-density ERPs evoked by rotated alphanumeric characters were examined to determine how neural processing is affected by stimulus orientation during letter/digit classifications and during mirror/normal discriminations. The former task typically produces response times that are unaffected by stimulus orientation while the latter is thought to require mental rotation. Sensitivity to orientation was first observed around 100-140 ms and this effect was attributed to differences in low-level features between vertical and oblique orientations. Subsequently, character misorientation amplified the N170, a neural marker of object classification, between 160 and 220 ms. Top-down processing is reflected in the ERPs beginning at 280-320 ms and this time range may reflect binding of ventral and dorsal stream information. In the case of mirror-normal discrimination these top-down processes can lead to mental rotation between 340 and 700 ms. Therefore, although neural processing reflects object orientation, these effects do not translate into increases in reaction-times or impaired accuracy for categorisation, and precede those that do in the mental-rotation task. Copyright © 2011 Elsevier Ltd. All rights reserved.

Artificial neural networks applied to forecasting time series.

PubMed

Montaño Moreno, Juan J; Palmer Pol, Alfonso; Muñoz Gracia, Pilar

2011-04-01

This study offers a description and comparison of the main models of Artificial Neural Networks (ANN) which have proved to be useful in time series forecasting, and also a standard procedure for the practical application of ANN in this type of task. The Multilayer Perceptron (MLP), Radial Base Function (RBF), Generalized Regression Neural Network (GRNN), and Recurrent Neural Network (RNN) models are analyzed. With this aim in mind, we use a time series made up of 244 time points. A comparative study establishes that the error made by the four neural network models analyzed is less than 10%. In accordance with the interpretation criteria of this performance, it can be concluded that the neural network models show a close fit regarding their forecasting capacity. The model with the best performance is the RBF, followed by the RNN and MLP. The GRNN model is the one with the worst performance. Finally, we analyze the advantages and limitations of ANN, the possible solutions to these limitations, and provide an orientation towards future research.

Neural networks: Alternatives to conventional techniques for automatic docking

NASA Technical Reports Server (NTRS)

Vinz, Bradley L.

1994-01-01

Automatic docking of orbiting spacecraft is a crucial operation involving the identification of vehicle orientation as well as complex approach dynamics. The chaser spacecraft must be able to recognize the target spacecraft within a scene and achieve accurate closing maneuvers. In a video-based system, a target scene must be captured and transformed into a pattern of pixels. Successful recognition lies in the interpretation of this pattern. Due to their powerful pattern recognition capabilities, artificial neural networks offer a potential role in interpretation and automatic docking processes. Neural networks can reduce the computational time required by existing image processing and control software. In addition, neural networks are capable of recognizing and adapting to changes in their dynamic environment, enabling enhanced performance, redundancy, and fault tolerance. Most neural networks are robust to failure, capable of continued operation with a slight degradation in performance after minor failures. This paper discusses the particular automatic docking tasks neural networks can perform as viable alternatives to conventional techniques.

Analysis of haptic information in the cerebral cortex

PubMed Central

2016-01-01

Haptic sensing of objects acquires information about a number of properties. This review summarizes current understanding about how these properties are processed in the cerebral cortex of macaques and humans. Nonnoxious somatosensory inputs, after initial processing in primary somatosensory cortex, are partially segregated into different pathways. A ventrally directed pathway carries information about surface texture into parietal opercular cortex and thence to medial occipital cortex. A dorsally directed pathway transmits information regarding the location of features on objects to the intraparietal sulcus and frontal eye fields. Shape processing occurs mainly in the intraparietal sulcus and lateral occipital complex, while orientation processing is distributed across primary somatosensory cortex, the parietal operculum, the anterior intraparietal sulcus, and a parieto-occipital region. For each of these properties, the respective areas outside primary somatosensory cortex also process corresponding visual information and are thus multisensory. Consistent with the distributed neural processing of haptic object properties, tactile spatial acuity depends on interaction between bottom-up tactile inputs and top-down attentional signals in a distributed neural network. Future work should clarify the roles of the various brain regions and how they interact at the network level. PMID:27440247

Learning Oriented Region-based Convolutional Neural Networks for Building Detection in Satellite Remote Sensing Images

NASA Astrophysics Data System (ADS)

Chen, C.; Gong, W.; Hu, Y.; Chen, Y.; Ding, Y.

2017-05-01

The automated building detection in aerial images is a fundamental problem encountered in aerial and satellite images analysis. Recently, thanks to the advances in feature descriptions, Region-based CNN model (R-CNN) for object detection is receiving an increasing attention. Despite the excellent performance in object detection, it is problematic to directly leverage the features of R-CNN model for building detection in single aerial image. As we know, the single aerial image is in vertical view and the buildings possess significant directional feature. However, in R-CNN model, direction of the building is ignored and the detection results are represented by horizontal rectangles. For this reason, the detection results with horizontal rectangle cannot describe the building precisely. To address this problem, in this paper, we proposed a novel model with a key feature related to orientation, namely, Oriented R-CNN (OR-CNN). Our contributions are mainly in the following two aspects: 1) Introducing a new oriented layer network for detecting the rotation angle of building on the basis of the successful VGG-net R-CNN model; 2) the oriented rectangle is proposed to leverage the powerful R-CNN for remote-sensing building detection. In experiments, we establish a complete and bran-new data set for training our oriented R-CNN model and comprehensively evaluate the proposed method on a publicly available building detection data set. We demonstrate State-of-the-art results compared with the previous baseline methods.

Finite-time convergent recurrent neural network with a hard-limiting activation function for constrained optimization with piecewise-linear objective functions.

PubMed

Liu, Qingshan; Wang, Jun

2011-04-01

This paper presents a one-layer recurrent neural network for solving a class of constrained nonsmooth optimization problems with piecewise-linear objective functions. The proposed neural network is guaranteed to be globally convergent in finite time to the optimal solutions under a mild condition on a derived lower bound of a single gain parameter in the model. The number of neurons in the neural network is the same as the number of decision variables of the optimization problem. Compared with existing neural networks for optimization, the proposed neural network has a couple of salient features such as finite-time convergence and a low model complexity. Specific models for two important special cases, namely, linear programming and nonsmooth optimization, are also presented. In addition, applications to the shortest path problem and constrained least absolute deviation problem are discussed with simulation results to demonstrate the effectiveness and characteristics of the proposed neural network.

A Neural Dynamic Model Generates Descriptions of Object-Oriented Actions.

PubMed

Richter, Mathis; Lins, Jonas; Schöner, Gregor

2017-01-01

Describing actions entails that relations between objects are discovered. A pervasively neural account of this process requires that fundamental problems are solved: the neural pointer problem, the binding problem, and the problem of generating discrete processing steps from time-continuous neural processes. We present a prototypical solution to these problems in a neural dynamic model that comprises dynamic neural fields holding representations close to sensorimotor surfaces as well as dynamic neural nodes holding discrete, language-like representations. Making the connection between these two types of representations enables the model to describe actions as well as to perceptually ground movement phrases-all based on real visual input. We demonstrate how the dynamic neural processes autonomously generate the processing steps required to describe or ground object-oriented actions. By solving the fundamental problems of neural pointing, binding, and emergent discrete processing, the model may be a first but critical step toward a systematic neural processing account of higher cognition. Copyright © 2017 The Authors. Topics in Cognitive Science published by Wiley Periodicals, Inc. on behalf of Cognitive Science Society.

Real-time object-to-features vectorisation via Siamese neural networks

NASA Astrophysics Data System (ADS)

Fedorenko, Fedor; Usilin, Sergey

2017-03-01

Object-to-features vectorisation is a hard problem to solve for objects that can be hard to distinguish. Siamese and Triplet neural networks are one of the more recent tools used for such task. However, most networks used are very deep networks that prove to be hard to compute in the Internet of Things setting. In this paper, a computationally efficient neural network is proposed for real-time object-to-features vectorisation into a Euclidean metric space. We use L2 distance to reflect feature vector similarity during both training and testing. In this way, feature vectors we develop can be easily classified using K-Nearest Neighbours classifier. Such approach can be used to train networks to vectorise such "problematic" objects like images of human faces, keypoint image patches, like keypoints on Arctic maps and surrounding marine areas.

Object-Oriented Control System Design Using On-Line Training of Artificial Neural Networks

NASA Technical Reports Server (NTRS)

Rubaai, Ahmed

1997-01-01

This report deals with the object-oriented model development of a neuro-controller design for permanent magnet (PM) dc motor drives. The system under study is described as a collection of interacting objects. Each object module describes the object behaviors, called methods. The characteristics of the object are included in its variables. The knowledge of the object exists within its variables, and the performance is determined by its methods. This structure maps well to the real world objects that comprise the system being modeled. A dynamic learning architecture that possesses the capabilities of simultaneous on-line identification and control is incorporated to enforce constraints on connections and control the dynamics of the motor. The control action is implemented "on-line", in "real time" in such a way that the predicted trajectory follows a specified reference model. A design example of controlling a PM dc motor drive on-line shows the effectiveness of the design tool. This will therefore be very useful in aerospace applications. It is expected to provide an innovative and noval software model for the rocket engine numerical simulator executive.

PCSIM: A Parallel Simulation Environment for Neural Circuits Fully Integrated with Python

PubMed Central

Pecevski, Dejan; Natschläger, Thomas; Schuch, Klaus

2008-01-01

The Parallel Circuit SIMulator (PCSIM) is a software package for simulation of neural circuits. It is primarily designed for distributed simulation of large scale networks of spiking point neurons. Although its computational core is written in C++, PCSIM's primary interface is implemented in the Python programming language, which is a powerful programming environment and allows the user to easily integrate the neural circuit simulator with data analysis and visualization tools to manage the full neural modeling life cycle. The main focus of this paper is to describe PCSIM's full integration into Python and the benefits thereof. In particular we will investigate how the automatically generated bidirectional interface and PCSIM's object-oriented modular framework enable the user to adopt a hybrid modeling approach: using and extending PCSIM's functionality either employing pure Python or C++ and thus combining the advantages of both worlds. Furthermore, we describe several supplementary PCSIM packages written in pure Python and tailored towards setting up and analyzing neural simulations. PMID:19543450

The neural basis of precise visual short-term memory for complex recognisable objects.

PubMed

Veldsman, Michele; Mitchell, Daniel J; Cusack, Rhodri

2017-10-01

Recent evidence suggests that visual short-term memory (VSTM) capacity estimated using simple objects, such as colours and oriented bars, may not generalise well to more naturalistic stimuli. More visual detail can be stored in VSTM when complex, recognisable objects are maintained compared to simple objects. It is not yet known if it is recognisability that enhances memory precision, nor whether maintenance of recognisable objects is achieved with the same network of brain regions supporting maintenance of simple objects. We used a novel stimulus generation method to parametrically warp photographic images along a continuum, allowing separate estimation of the precision of memory representations and the number of items retained. The stimulus generation method was also designed to create unrecognisable, though perceptually matched, stimuli, to investigate the impact of recognisability on VSTM. We adapted the widely-used change detection and continuous report paradigms for use with complex, photographic images. Across three functional magnetic resonance imaging (fMRI) experiments, we demonstrated greater precision for recognisable objects in VSTM compared to unrecognisable objects. This clear behavioural advantage was not the result of recruitment of additional brain regions, or of stronger mean activity within the core network. Representational similarity analysis revealed greater variability across item repetitions in the representations of recognisable, compared to unrecognisable complex objects. We therefore propose that a richer range of neural representations support VSTM for complex recognisable objects. Copyright © 2017 Elsevier Inc. All rights reserved.

Unsupervised learning of contextual constraints in neural networks for simultaneous visual processing of multiple objects

NASA Astrophysics Data System (ADS)

Marshall, Jonathan A.

1992-12-01

A simple self-organizing neural network model, called an EXIN network, that learns to process sensory information in a context-sensitive manner, is described. EXIN networks develop efficient representation structures for higher-level visual tasks such as segmentation, grouping, transparency, depth perception, and size perception. Exposure to a perceptual environment during a developmental period serves to configure the network to perform appropriate organization of sensory data. A new anti-Hebbian inhibitory learning rule permits superposition of multiple simultaneous neural activations (multiple winners), while maintaining contextual consistency constraints, instead of forcing winner-take-all pattern classifications. The activations can represent multiple patterns simultaneously and can represent uncertainty. The network performs parallel parsing, credit attribution, and simultaneous constraint satisfaction. EXIN networks can learn to represent multiple oriented edges even where they intersect and can learn to represent multiple transparently overlaid surfaces defined by stereo or motion cues. In the case of stereo transparency, the inhibitory learning implements both a uniqueness constraint and permits coactivation of cells representing multiple disparities at the same image location. Thus two or more disparities can be active simultaneously without interference. This behavior is analogous to that of Prazdny's stereo vision algorithm, with the bonus that each binocular point is assigned a unique disparity. In a large implementation, such a NN would also be able to represent effectively the disparities of a cloud of points at random depths, like human observers, and unlike Prazdny's method

A One-Layer Recurrent Neural Network for Real-Time Portfolio Optimization With Probability Criterion.

PubMed

Liu, Qingshan; Dang, Chuangyin; Huang, Tingwen

2013-02-01

This paper presents a decision-making model described by a recurrent neural network for dynamic portfolio optimization. The portfolio-optimization problem is first converted into a constrained fractional programming problem. Since the objective function in the programming problem is not convex, the traditional optimization techniques are no longer applicable for solving this problem. Fortunately, the objective function in the fractional programming is pseudoconvex on the feasible region. It leads to a one-layer recurrent neural network modeled by means of a discontinuous dynamic system. To ensure the optimal solutions for portfolio optimization, the convergence of the proposed neural network is analyzed and proved. In fact, the neural network guarantees to get the optimal solutions for portfolio-investment advice if some mild conditions are satisfied. A numerical example with simulation results substantiates the effectiveness and illustrates the characteristics of the proposed neural network.

Feature-based and object-based attention orientation during short-term memory maintenance.

PubMed

Ku, Yixuan

2015-12-01

Top-down attention biases the short-term memory (STM) processing at multiple stages. Orienting attention during the maintenance period of STM by a retrospective cue (retro-cue) strengthens the representation of the cued item and improves the subsequent STM performance. In a recent article, Backer et al. (Backer KC, Binns MA, Alain C. J Neurosci 35: 1307-1318, 2015) extended these findings from the visual to the auditory domain and combined electroencephalography to dissociate neural mechanisms underlying feature-based and object-based attention orientation. Both event-related potentials and neural oscillations explained the behavioral benefits of retro-cues and favored the theory that feature-based and object-based attention orientation were independent. Copyright © 2015 the American Physiological Society.

Learning Data Set Influence on Identification Accuracy of Gas Turbine Neural Network Model

NASA Astrophysics Data System (ADS)

Kuznetsov, A. V.; Makaryants, G. M.

2018-01-01

There are many gas turbine engine identification researches via dynamic neural network models. It should minimize errors between model and real object during identification process. Questions about training data set processing of neural networks are usually missed. This article presents a study about influence of data set type on gas turbine neural network model accuracy. The identification object is thermodynamic model of micro gas turbine engine. The thermodynamic model input signal is the fuel consumption and output signal is the engine rotor rotation frequency. Four types input signals was used for creating training and testing data sets of dynamic neural network models - step, fast, slow and mixed. Four dynamic neural networks were created based on these types of training data sets. Each neural network was tested via four types test data sets. In the result 16 transition processes from four neural networks and four test data sets from analogous solving results of thermodynamic model were compared. The errors comparison was made between all neural network errors in each test data set. In the comparison result it was shown error value ranges of each test data set. It is shown that error values ranges is small therefore the influence of data set types on identification accuracy is low.

Enhanced online convolutional neural networks for object tracking

NASA Astrophysics Data System (ADS)

Zhang, Dengzhuo; Gao, Yun; Zhou, Hao; Li, Tianwen

2018-04-01

In recent several years, object tracking based on convolution neural network has gained more and more attention. The initialization and update of convolution filters can directly affect the precision of object tracking effective. In this paper, a novel object tracking via an enhanced online convolution neural network without offline training is proposed, which initializes the convolution filters by a k-means++ algorithm and updates the filters by an error back-propagation. The comparative experiments of 7 trackers on 15 challenging sequences showed that our tracker can perform better than other trackers in terms of AUC and precision.

Calibration of a Hall effect displacement measurement system for complex motion analysis using a neural network.

PubMed

Northey, G W; Oliver, M L; Rittenhouse, D M

2006-01-01

Biomechanics studies often require the analysis of position and orientation. Although a variety of transducer and camera systems can be utilized, a common inexpensive alternative is the Hall effect sensor. Hall effect sensors have been used extensively for one-dimensional position analysis but their non-linear behavior and cross-talk effects make them difficult to calibrate for effective and accurate two- and three-dimensional position and orientation analysis. The aim of this study was to develop and calibrate a displacement measurement system for a hydraulic-actuation joystick used for repetitive motion analysis of heavy equipment operators. The system utilizes an array of four Hall effect sensors that are all active during any joystick movement. This built-in redundancy allows the calibration to utilize fully connected feed forward neural networks in conjunction with a Microscribe 3D digitizer. A fully connected feed forward neural network with one hidden layer containing five neurons was developed. Results indicate that the ability of the neural network to accurately predict the x, y and z coordinates of the joystick handle was good with r(2) values of 0.98 and higher. The calibration technique was found to be equally as accurate when used on data collected 5 days after the initial calibration, indicating the system is robust and stable enough to not require calibration every time the joystick is used. This calibration system allowed an infinite number of joystick orientations and positions to be found within the range of joystick motion.

NEVESIM: event-driven neural simulation framework with a Python interface.

PubMed

Pecevski, Dejan; Kappel, David; Jonke, Zeno

2014-01-01

NEVESIM is a software package for event-driven simulation of networks of spiking neurons with a fast simulation core in C++, and a scripting user interface in the Python programming language. It supports simulation of heterogeneous networks with different types of neurons and synapses, and can be easily extended by the user with new neuron and synapse types. To enable heterogeneous networks and extensibility, NEVESIM is designed to decouple the simulation logic of communicating events (spikes) between the neurons at a network level from the implementation of the internal dynamics of individual neurons. In this paper we will present the simulation framework of NEVESIM, its concepts and features, as well as some aspects of the object-oriented design approaches and simulation strategies that were utilized to efficiently implement the concepts and functionalities of the framework. We will also give an overview of the Python user interface, its basic commands and constructs, and also discuss the benefits of integrating NEVESIM with Python. One of the valuable capabilities of the simulator is to simulate exactly and efficiently networks of stochastic spiking neurons from the recently developed theoretical framework of neural sampling. This functionality was implemented as an extension on top of the basic NEVESIM framework. Altogether, the intended purpose of the NEVESIM framework is to provide a basis for further extensions that support simulation of various neural network models incorporating different neuron and synapse types that can potentially also use different simulation strategies.

NEVESIM: event-driven neural simulation framework with a Python interface

PubMed Central

Pecevski, Dejan; Kappel, David; Jonke, Zeno

2014-01-01

NEVESIM is a software package for event-driven simulation of networks of spiking neurons with a fast simulation core in C++, and a scripting user interface in the Python programming language. It supports simulation of heterogeneous networks with different types of neurons and synapses, and can be easily extended by the user with new neuron and synapse types. To enable heterogeneous networks and extensibility, NEVESIM is designed to decouple the simulation logic of communicating events (spikes) between the neurons at a network level from the implementation of the internal dynamics of individual neurons. In this paper we will present the simulation framework of NEVESIM, its concepts and features, as well as some aspects of the object-oriented design approaches and simulation strategies that were utilized to efficiently implement the concepts and functionalities of the framework. We will also give an overview of the Python user interface, its basic commands and constructs, and also discuss the benefits of integrating NEVESIM with Python. One of the valuable capabilities of the simulator is to simulate exactly and efficiently networks of stochastic spiking neurons from the recently developed theoretical framework of neural sampling. This functionality was implemented as an extension on top of the basic NEVESIM framework. Altogether, the intended purpose of the NEVESIM framework is to provide a basis for further extensions that support simulation of various neural network models incorporating different neuron and synapse types that can potentially also use different simulation strategies. PMID:25177291

Neural network post-processing of grayscale optical correlator

NASA Technical Reports Server (NTRS)

Lu, Thomas T; Hughlett, Casey L.; Zhoua, Hanying; Chao, Tien-Hsin; Hanan, Jay C.

2005-01-01

In this paper we present the use of a radial basis function neural network (RBFNN) as a post-processor to assist the optical correlator to identify the objects and to reject false alarms. Image plane features near the correlation peaks are extracted and fed to the neural network for analysis. The approach is capable of handling large number of object variations and filter sets. Preliminary experimental results are presented and the performance is analyzed.

Image object recognition based on the Zernike moment and neural networks

NASA Astrophysics Data System (ADS)

Wan, Jianwei; Wang, Ling; Huang, Fukan; Zhou, Liangzhu

1998-03-01

This paper first give a comprehensive discussion about the concept of artificial neural network its research methods and the relations with information processing. On the basis of such a discussion, we expound the mathematical similarity of artificial neural network and information processing. Then, the paper presents a new method of image recognition based on invariant features and neural network by using image Zernike transform. The method not only has the invariant properties for rotation, shift and scale of image object, but also has good fault tolerance and robustness. Meanwhile, it is also compared with statistical classifier and invariant moments recognition method.

The Visual Representation of 3D Object Orientation in Parietal Cortex

PubMed Central

Cowan, Noah J.; Angelaki, Dora E.

2013-01-01

An accurate representation of three-dimensional (3D) object orientation is essential for interacting with the environment. Where and how the brain visually encodes 3D object orientation remains unknown, but prior studies suggest the caudal intraparietal area (CIP) may be involved. Here, we develop rigorous analytical methods for quantifying 3D orientation tuning curves, and use these tools to the study the neural coding of surface orientation. Specifically, we show that single neurons in area CIP of the rhesus macaque jointly encode the slant and tilt of a planar surface, and that across the population, the distribution of preferred slant-tilts is not statistically different from uniform. This suggests that all slant-tilt combinations are equally represented in area CIP. Furthermore, some CIP neurons are found to also represent the third rotational degree of freedom that determines the orientation of the image pattern on the planar surface. Together, the present results suggest that CIP is a critical neural locus for the encoding of all three rotational degrees of freedom specifying an object's 3D spatial orientation. PMID:24305830

Using Neural Networks in Decision Making for a Reconfigurable Electro Mechanical Actuator (EMA)

NASA Technical Reports Server (NTRS)

Latino, Carl D.

2001-01-01

The objectives of this project were to demonstrate applicability and advantages of a neural network approach for evaluating the performance of an electro-mechanical actuator (EMA). The EMA in question was intended for the X-37 Advanced Technology Vehicle. It will have redundant components for safety and reliability. The neural networks for this application are to monitor the operation of the redundant electronics that control the actuator in real time and decide on the operating configuration. The system we proposed consists of the actuator, sensors, control circuitry and dedicated (embedded) processors. The main purpose of the study was to develop suitable hardware and neural network capable of allowing real time reconfiguration decisions to be made. This approach was to be compared to other methods such as fuzzy logic and knowledge based systems considered for the same application. Over the course of the project a more general objective was the identification of the other neural network applications and the education of interested NASA personnel on the topic of Neural Networks.

ANNarchy: a code generation approach to neural simulations on parallel hardware

PubMed Central

Vitay, Julien; Dinkelbach, Helge Ü.; Hamker, Fred H.

2015-01-01

Many modern neural simulators focus on the simulation of networks of spiking neurons on parallel hardware. Another important framework in computational neuroscience, rate-coded neural networks, is mostly difficult or impossible to implement using these simulators. We present here the ANNarchy (Artificial Neural Networks architect) neural simulator, which allows to easily define and simulate rate-coded and spiking networks, as well as combinations of both. The interface in Python has been designed to be close to the PyNN interface, while the definition of neuron and synapse models can be specified using an equation-oriented mathematical description similar to the Brian neural simulator. This information is used to generate C++ code that will efficiently perform the simulation on the chosen parallel hardware (multi-core system or graphical processing unit). Several numerical methods are available to transform ordinary differential equations into an efficient C++code. We compare the parallel performance of the simulator to existing solutions. PMID:26283957

The effects of short-term and long-term learning on the responses of lateral intraparietal neurons to visually presented objects

PubMed Central

Sigurdardottir, Heida M.; Sheinberg, David L.

2015-01-01

The lateral intraparietal area (LIP) of the dorsal visual stream is thought to play an important role in visually directed orienting, or the guidance of where to look and pay attention. LIP can also respond selectively to differently shaped objects. We sought to understand how and to what extent short-term and long-term experience with visual orienting can determine the nature of responses of LIP neurons to objects of different shapes. We taught monkeys to arbitrarily associate centrally presented objects of various shapes with orienting either toward or away from a preferred peripheral spatial location of a neuron. For some objects the training lasted for less than a single day, while for other objects the training lasted for several months. We found that neural responses to visual objects are affected both by such short-term and long-term experience, but that the length of the learning period determines exactly how this neural plasticity manifests itself. Short-term learning over the course of a single training session affects neural responses to objects, but these effects are only seen relatively late after visual onset; at this time, the neural responses to newly learned objects start to resemble those of familiar over-learned objects that share their meaning or arbitrary association. Long-term learning, on the other hand, affects the earliest and apparently bottom-up responses to visual objects. These responses tend to be greater for objects that have repeatedly been associated with looking toward, rather than away from, LIP neurons’ preferred spatial locations. Responses to objects can nonetheless be distinct even though the objects have both been similarly acted on in the past and will lead to the same orienting behavior in the future. Our results therefore also indicate that a complete experience-driven override of LIP object responses is difficult or impossible. PMID:25633647

Higher-order neural network software for distortion invariant object recognition

NASA Technical Reports Server (NTRS)

Reid, Max B.; Spirkovska, Lilly

1991-01-01

The state-of-the-art in pattern recognition for such applications as automatic target recognition and industrial robotic vision relies on digital image processing. We present a higher-order neural network model and software which performs the complete feature extraction-pattern classification paradigm required for automatic pattern recognition. Using a third-order neural network, we demonstrate complete, 100 percent accurate invariance to distortions of scale, position, and in-plate rotation. In a higher-order neural network, feature extraction is built into the network, and does not have to be learned. Only the relatively simple classification step must be learned. This is key to achieving very rapid training. The training set is much smaller than with standard neural network software because the higher-order network only has to be shown one view of each object to be learned, not every possible view. The software and graphical user interface run on any Sun workstation. Results of the use of the neural software in autonomous robotic vision systems are presented. Such a system could have extensive application in robotic manufacturing.

Recurrent Convolutional Neural Networks: A Better Model of Biological Object Recognition.

PubMed

Spoerer, Courtney J; McClure, Patrick; Kriegeskorte, Nikolaus

2017-01-01

Feedforward neural networks provide the dominant model of how the brain performs visual object recognition. However, these networks lack the lateral and feedback connections, and the resulting recurrent neuronal dynamics, of the ventral visual pathway in the human and non-human primate brain. Here we investigate recurrent convolutional neural networks with bottom-up (B), lateral (L), and top-down (T) connections. Combining these types of connections yields four architectures (B, BT, BL, and BLT), which we systematically test and compare. We hypothesized that recurrent dynamics might improve recognition performance in the challenging scenario of partial occlusion. We introduce two novel occluded object recognition tasks to test the efficacy of the models, digit clutter (where multiple target digits occlude one another) and digit debris (where target digits are occluded by digit fragments). We find that recurrent neural networks outperform feedforward control models (approximately matched in parametric complexity) at recognizing objects, both in the absence of occlusion and in all occlusion conditions. Recurrent networks were also found to be more robust to the inclusion of additive Gaussian noise. Recurrent neural networks are better in two respects: (1) they are more neurobiologically realistic than their feedforward counterparts; (2) they are better in terms of their ability to recognize objects, especially under challenging conditions. This work shows that computer vision can benefit from using recurrent convolutional architectures and suggests that the ubiquitous recurrent connections in biological brains are essential for task performance.

Improved Adjoint-Operator Learning For A Neural Network

NASA Technical Reports Server (NTRS)

Toomarian, Nikzad; Barhen, Jacob

1995-01-01

Improved method of adjoint-operator learning reduces amount of computation and associated computational memory needed to make electronic neural network learn temporally varying pattern (e.g., to recognize moving object in image) in real time. Method extension of method described in "Adjoint-Operator Learning for a Neural Network" (NPO-18352).

Simbrain 3.0: A flexible, visually-oriented neural network simulator.

PubMed

Tosi, Zachary; Yoshimi, Jeffrey

2016-11-01

Simbrain 3.0 is a software package for neural network design and analysis, which emphasizes flexibility (arbitrarily complex networks can be built using a suite of basic components) and a visually rich, intuitive interface. These features support both students and professionals. Students can study all of the major classes of neural networks in a familiar graphical setting, and can easily modify simulations, experimenting with networks and immediately seeing the results of their interventions. With the 3.0 release, Simbrain supports models on the order of thousands of neurons and a million synapses. This allows the same features that support education to support research professionals, who can now use the tool to quickly design, run, and analyze the behavior of large, highly customizable simulations. Copyright © 2016 Elsevier Ltd. All rights reserved.

Human cortical activity evoked by contextual processing in attentional orienting.

PubMed

Zhao, Shuo; Li, Chunlin; Uono, Shota; Yoshimura, Sayaka; Toichi, Motomi

2017-06-07

The ability to assess another person's direction of attention is paramount in social communication, many studies have reported a similar pattern between gaze and arrow cues in attention orienting. Neuroimaging research has also demonstrated no qualitative differences in attention to gaze and arrow cues. However, these studies were implemented under simple experiment conditions. Researchers have highlighted the importance of contextual processing (i.e., the semantic congruence between cue and target) in attentional orienting, showing that attentional orienting by social gaze or arrow cues could be modulated through contextual processing. Here, we examine the neural activity of attentional orienting by gaze and arrow cues in response to contextual processing using functional magnetic resonance imaging. The results demonstrated that the influence of neural activity through contextual processing to attentional orienting occurred under invalid conditions (when the cue and target were incongruent versus congruent) in the ventral frontoparietal network, although we did not identify any differences in the neural substrates of attentional orienting in contextual processing between gaze and arrow cues. These results support behavioural data of attentional orienting modulated by contextual processing based on the neurocognitive architecture.

Collision detection in complex dynamic scenes using an LGMD-based visual neural network with feature enhancement.

PubMed

Yue, Shigang; Rind, F Claire

2006-05-01

The lobula giant movement detector (LGMD) is an identified neuron in the locust brain that responds most strongly to the images of an approaching object such as a predator. Its computational model can cope with unpredictable environments without using specific object recognition algorithms. In this paper, an LGMD-based neural network is proposed with a new feature enhancement mechanism to enhance the expanded edges of colliding objects via grouped excitation for collision detection with complex backgrounds. The isolated excitation caused by background detail will be filtered out by the new mechanism. Offline tests demonstrated the advantages of the presented LGMD-based neural network in complex backgrounds. Real time robotics experiments using the LGMD-based neural network as the only sensory system showed that the system worked reliably in a wide range of conditions; in particular, the robot was able to navigate in arenas with structured surrounds and complex backgrounds.

A neural network ActiveX based integrated image processing environment.

PubMed

Ciuca, I; Jitaru, E; Alaicescu, M; Moisil, I

2000-01-01

The paper outlines an integrated image processing environment that uses neural networks ActiveX technology for object recognition and classification. The image processing environment which is Windows based, encapsulates a Multiple-Document Interface (MDI) and is menu driven. Object (shape) parameter extraction is focused on features that are invariant in terms of translation, rotation and scale transformations. The neural network models that can be incorporated as ActiveX components into the environment allow both clustering and classification of objects from the analysed image. Mapping neural networks perform an input sensitivity analysis on the extracted feature measurements and thus facilitate the removal of irrelevant features and improvements in the degree of generalisation. The program has been used to evaluate the dimensions of the hydrocephalus in a study for calculating the Evans index and the angle of the frontal horns of the ventricular system modifications.

Automatized smoking-related action schemata are reflected by reduced fMRI activity in sensorimotor brain regions of smokers.

PubMed

Isik, Ayse Ilkay; Naumer, Marcus J; Kaiser, Jochen; Buschenlange, Christian; Wiesmann, Sandro; Czoschke, Stefan; Yalachkov, Yavor

2017-01-01

In the later stages of addiction, automatized processes play a prominent role in guiding drug-seeking and drug-taking behavior. However, little is known about the neural correlates of automatized drug-taking skills and drug-related action knowledge in humans. We employed functional magnetic resonance imaging (fMRI) while smokers and non-smokers performed an orientation affordance task, where compatibility between the hand used for a behavioral response and the spatial orientation of a priming stimulus leads to shorter reaction times resulting from activation of the corresponding motor representations. While non-smokers exhibited this behavioral effect only for control objects, smokers showed the affordance effect for both control and smoking-related objects. Furthermore, smokers exhibited reduced fMRI activation for smoking-related as compared to control objects for compatible stimulus-response pairings in a sensorimotor brain network consisting of the right primary motor cortex, supplementary motor area, middle occipital gyrus, left fusiform gyrus and bilateral cingulate gyrus. In the incompatible condition, we found higher fMRI activation in smokers for smoking-related as compared to control objects in the right primary motor cortex, cingulate gyrus, and left fusiform gyrus. This suggests that the activation and performance of deeply embedded, automatized drug-taking schemata employ less brain resources. This might reduce the threshold for relapsing in individuals trying to abstain from smoking. In contrast, the interruption or modification of already triggered automatized action representations require increased neural resources.

Automatic detection of kidney in 3D pediatric ultrasound images using deep neural networks

NASA Astrophysics Data System (ADS)

Tabrizi, Pooneh R.; Mansoor, Awais; Biggs, Elijah; Jago, James; Linguraru, Marius George

2018-02-01

Ultrasound (US) imaging is the routine and safe diagnostic modality for detecting pediatric urology problems, such as hydronephrosis in the kidney. Hydronephrosis is the swelling of one or both kidneys because of the build-up of urine. Early detection of hydronephrosis can lead to a substantial improvement in kidney health outcomes. Generally, US imaging is a challenging modality for the evaluation of pediatric kidneys with different shape, size, and texture characteristics. The aim of this study is to present an automatic detection method to help kidney analysis in pediatric 3DUS images. The method localizes the kidney based on its minimum volume oriented bounding box) using deep neural networks. Separate deep neural networks are trained to estimate the kidney position, orientation, and scale, making the method computationally efficient by avoiding full parameter training. The performance of the method was evaluated using a dataset of 45 kidneys (18 normal and 27 diseased kidneys diagnosed with hydronephrosis) through the leave-one-out cross validation method. Quantitative results show the proposed detection method could extract the kidney position, orientation, and scale ratio with root mean square values of 1.3 +/- 0.9 mm, 6.34 +/- 4.32 degrees, and 1.73 +/- 0.04, respectively. This method could be helpful in automating kidney segmentation for routine clinical evaluation.

Revealing the neural networks associated with processing of natural social interaction and the related effects of actor-orientation and face-visibility.

PubMed

Saggar, Manish; Shelly, Elizabeth Walter; Lepage, Jean-Francois; Hoeft, Fumiko; Reiss, Allan L

2014-01-01

Understanding the intentions and desires of those around us is vital for adapting to a dynamic social environment. In this paper, a novel event-related functional Magnetic Resonance Imaging (fMRI) paradigm with dynamic and natural stimuli (2s video clips) was developed to directly examine the neural networks associated with processing of gestures with social intent as compared to nonsocial intent. When comparing social to nonsocial gestures, increased activation in both the mentalizing (or theory of mind) and amygdala networks was found. As a secondary aim, a factor of actor-orientation was included in the paradigm to examine how the neural mechanisms differ with respect to personal engagement during a social interaction versus passively observing an interaction. Activity in the lateral occipital cortex and precentral gyrus was found sensitive to actor-orientation during social interactions. Lastly, by manipulating face-visibility we tested whether facial information alone is the primary driver of neural activation differences observed between social and nonsocial gestures. We discovered that activity in the posterior superior temporal sulcus (pSTS) and fusiform gyrus (FFG) was partially driven by observing facial expressions during social gestures. Altogether, using multiple factors associated with processing of natural social interaction, we conceptually advance our understanding of how social stimuli is processed in the brain and discuss the application of this paradigm to clinical populations where atypical social cognition is manifested as a key symptom. © 2013.

Revealing the neural networks associated with processing of natural social interaction and the related effects of actor-orientation and face-visibility

PubMed Central

Saggar, Manish; Shelly, Elizabeth Walter; Lepage, Jean-Francois; Hoeft, Fumiko; Reiss, Allan L.

2013-01-01

Understanding the intentions and desires of those around us is vital for adapting to a dynamic social environment. In this paper, a novel event-related functional Magnetic Resonance Imaging (fMRI) paradigm with dynamic and natural stimuli (2s video clips) was developed to directly examine the neural networks associated with processing of gestures with social intent as compared to nonsocial intent. When comparing social to nonsocial gestures, increased activation in both the mentalizing (or theory of mind) and amygdala networks were found. As a secondary aim, a factor of actor-orientation was included in the paradigm to examine how the neural mechanisms differ with respect to personal engagement during a social interaction versus passively observing an interaction. Activity in the lateral occipital cortex and precentral gyrus were found sensitive to actor-orientation during social interactions. Lastly, by manipulating face-visibility we tested whether facial information alone is the primary driver of neural activation differences observed between social and nonsocial gestures. We discovered that activity in the posterior superior temporal sulcus (pSTS) and fusiform gyrus (FFG) were partially driven by observing facial expressions during social gestures. Altogether, using multiple factors associated with processing of natural social interaction, we conceptually advance our understanding of how social stimuli is processed in the brain and discuss the application of this paradigm to clinical populations where atypical social cognition is manifested as a key symptom. PMID:24084068

Development and application of deep convolutional neural network in target detection

NASA Astrophysics Data System (ADS)

Jiang, Xiaowei; Wang, Chunping; Fu, Qiang

2018-04-01

With the development of big data and algorithms, deep convolution neural networks with more hidden layers have more powerful feature learning and feature expression ability than traditional machine learning methods, making artificial intelligence surpass human level in many fields. This paper first reviews the development and application of deep convolutional neural networks in the field of object detection in recent years, then briefly summarizes and ponders some existing problems in the current research, and the future development of deep convolutional neural network is prospected.

An insect-inspired model for visual binding II: functional analysis and visual attention.

PubMed

Northcutt, Brandon D; Higgins, Charles M

2017-04-01

We have developed a neural network model capable of performing visual binding inspired by neuronal circuitry in the optic glomeruli of flies: a brain area that lies just downstream of the optic lobes where early visual processing is performed. This visual binding model is able to detect objects in dynamic image sequences and bind together their respective characteristic visual features-such as color, motion, and orientation-by taking advantage of their common temporal fluctuations. Visual binding is represented in the form of an inhibitory weight matrix which learns over time which features originate from a given visual object. In the present work, we show that information represented implicitly in this weight matrix can be used to explicitly count the number of objects present in the visual image, to enumerate their specific visual characteristics, and even to create an enhanced image in which one particular object is emphasized over others, thus implementing a simple form of visual attention. Further, we present a detailed analysis which reveals the function and theoretical limitations of the visual binding network and in this context describe a novel network learning rule which is optimized for visual binding.

Invariant 2D object recognition using the wavelet transform and structured neural networks

NASA Astrophysics Data System (ADS)

Khalil, Mahmoud I.; Bayoumi, Mohamed M.

1999-03-01

This paper applies the dyadic wavelet transform and the structured neural networks approach to recognize 2D objects under translation, rotation, and scale transformation. Experimental results are presented and compared with traditional methods. The experimental results showed that this refined technique successfully classified the objects and outperformed some traditional methods especially in the presence of noise.

Computational Models of Neuron-Astrocyte Interactions Lead to Improved Efficacy in the Performance of Neural Networks

PubMed Central

Alvarellos-González, Alberto; Pazos, Alejandro; Porto-Pazos, Ana B.

2012-01-01

The importance of astrocytes, one part of the glial system, for information processing in the brain has recently been demonstrated. Regarding information processing in multilayer connectionist systems, it has been shown that systems which include artificial neurons and astrocytes (Artificial Neuron-Glia Networks) have well-known advantages over identical systems including only artificial neurons. Since the actual impact of astrocytes in neural network function is unknown, we have investigated, using computational models, different astrocyte-neuron interactions for information processing; different neuron-glia algorithms have been implemented for training and validation of multilayer Artificial Neuron-Glia Networks oriented toward classification problem resolution. The results of the tests performed suggest that all the algorithms modelling astrocyte-induced synaptic potentiation improved artificial neural network performance, but their efficacy depended on the complexity of the problem. PMID:22649480

Computational models of neuron-astrocyte interactions lead to improved efficacy in the performance of neural networks.

PubMed

Alvarellos-González, Alberto; Pazos, Alejandro; Porto-Pazos, Ana B

2012-01-01

The importance of astrocytes, one part of the glial system, for information processing in the brain has recently been demonstrated. Regarding information processing in multilayer connectionist systems, it has been shown that systems which include artificial neurons and astrocytes (Artificial Neuron-Glia Networks) have well-known advantages over identical systems including only artificial neurons. Since the actual impact of astrocytes in neural network function is unknown, we have investigated, using computational models, different astrocyte-neuron interactions for information processing; different neuron-glia algorithms have been implemented for training and validation of multilayer Artificial Neuron-Glia Networks oriented toward classification problem resolution. The results of the tests performed suggest that all the algorithms modelling astrocyte-induced synaptic potentiation improved artificial neural network performance, but their efficacy depended on the complexity of the problem.

Real-time camera-based face detection using a modified LAMSTAR neural network system

NASA Astrophysics Data System (ADS)

Girado, Javier I.; Sandin, Daniel J.; DeFanti, Thomas A.; Wolf, Laura K.

2003-03-01

This paper describes a cost-effective, real-time (640x480 at 30Hz) upright frontal face detector as part of an ongoing project to develop a video-based, tetherless 3D head position and orientation tracking system. The work is specifically targeted for auto-stereoscopic displays and projection-based virtual reality systems. The proposed face detector is based on a modified LAMSTAR neural network system. At the input stage, after achieving image normalization and equalization, a sub-window analyzes facial features using a neural network. The sub-window is segmented, and each part is fed to a neural network layer consisting of a Kohonen Self-Organizing Map (SOM). The output of the SOM neural networks are interconnected and related by correlation-links, and can hence determine the presence of a face with enough redundancy to provide a high detection rate. To avoid tracking multiple faces simultaneously, the system is initially trained to track only the face centered in a box superimposed on the display. The system is also rotationally and size invariant to a certain degree.

Data systems and computer science: Neural networks base R/T program overview

NASA Technical Reports Server (NTRS)

Gulati, Sandeep

1991-01-01

The research base, in the U.S. and abroad, for the development of neural network technology is discussed. The technical objectives are to develop and demonstrate adaptive, neural information processing concepts. The leveraging of external funding is also discussed.

Neural-network classifiers for automatic real-world aerial image recognition

NASA Astrophysics Data System (ADS)

Greenberg, Shlomo; Guterman, Hugo

1996-08-01

We describe the application of the multilayer perceptron (MLP) network and a version of the adaptive resonance theory version 2-A (ART 2-A) network to the problem of automatic aerial image recognition (AAIR). The classification of aerial images, independent of their positions and orientations, is required for automatic tracking and target recognition. Invariance is achieved by the use of different invariant feature spaces in combination with supervised and unsupervised neural networks. The performance of neural-network-based classifiers in conjunction with several types of invariant AAIR global features, such as the Fourier-transform space, Zernike moments, central moments, and polar transforms, are examined. The advantages of this approach are discussed. The performance of the MLP network is compared with that of a classical correlator. The MLP neural-network correlator outperformed the binary phase-only filter (BPOF) correlator. It was found that the ART 2-A distinguished itself with its speed and its low number of required training vectors. However, only the MLP classifier was able to deal with a combination of shift and rotation geometric distortions.

Neural-network classifiers for automatic real-world aerial image recognition.

PubMed

Greenberg, S; Guterman, H

1996-08-10

We describe the application of the multilayer perceptron (MLP) network and a version of the adaptive resonance theory version 2-A (ART 2-A) network to the problem of automatic aerial image recognition (AAIR). The classification of aerial images, independent of their positions and orientations, is required for automatic tracking and target recognition. Invariance is achieved by the use of different invariant feature spaces in combination with supervised and unsupervised neural networks. The performance of neural-network-based classifiers in conjunction with several types of invariant AAIR global features, such as the Fourier-transform space, Zernike moments, central moments, and polar transforms, are examined. The advantages of this approach are discussed. The performance of the MLP network is compared with that of a classical correlator. The MLP neural-network correlator outperformed the binary phase-only filter (BPOF) correlator. It was found that the ART 2-A distinguished itself with its speed and its low number of required training vectors. However, only the MLP classifier was able to deal with a combination of shift and rotation geometric distortions.

Acquisition and Neural Network Prediction of 3D Deformable Object Shape Using a Kinect and a Force-Torque Sensor.

PubMed

Tawbe, Bilal; Cretu, Ana-Maria

2017-05-11

The realistic representation of deformations is still an active area of research, especially for deformable objects whose behavior cannot be simply described in terms of elasticity parameters. This paper proposes a data-driven neural-network-based approach for capturing implicitly and predicting the deformations of an object subject to external forces. Visual data, in the form of 3D point clouds gathered by a Kinect sensor, is collected over an object while forces are exerted by means of the probing tip of a force-torque sensor. A novel approach based on neural gas fitting is proposed to describe the particularities of a deformation over the selectively simplified 3D surface of the object, without requiring knowledge of the object material. An alignment procedure, a distance-based clustering, and inspiration from stratified sampling support this process. The resulting representation is denser in the region of the deformation (an average of 96.6% perceptual similarity with the collected data in the deformed area), while still preserving the object's overall shape (86% similarity over the entire surface) and only using on average of 40% of the number of vertices in the mesh. A series of feedforward neural networks is then trained to predict the mapping between the force parameters characterizing the interaction with the object and the change in the object shape, as captured by the fitted neural gas nodes. This series of networks allows for the prediction of the deformation of an object when subject to unknown interactions.

Selective attention modulates neural substrates of repetition priming and "implicit" visual memory: suppressions and enhancements revealed by FMRI.

PubMed

Vuilleumier, Patrik; Schwartz, Sophie; Duhoux, Stéphanie; Dolan, Raymond J; Driver, Jon

2005-08-01

Attention can enhance processing for relevant information and suppress this for ignored stimuli. However, some residual processing may still arise without attention. Here we presented overlapping outline objects at study, with subjects attending to those in one color but not the other. Attended objects were subsequently recognized on a surprise memory test, whereas there was complete amnesia for ignored items on such direct explicit testing; yet reliable behavioral priming effects were found on indirect testing. Event-related fMRI examined neural responses to previously attended or ignored objects, now shown alone in the same or mirror-reversed orientation as before, intermixed with new items. Repetition-related decreases in fMRI responses for objects previously attended and repeated in the same orientation were found in the right posterior fusiform, lateral occipital, and left inferior frontal cortex. More anterior fusiform regions also showed some repetition decreases for ignored objects, irrespective of orientation. View-specific repetition decreases were found in the striate cortex, particularly for previously attended items. In addition, previously ignored objects produced some fMRI response increases in the bilateral lingual gyri, relative to new objects. Selective attention at exposure can thus produce several distinct long-term effects on processing of stimuli repeated later, with neural response suppression stronger for previously attended objects, and some response enhancement for previously ignored objects, with these effects arising in different brain areas. Although repetition decreases may relate to positive priming phenomena, the repetition increases for ignored objects shown here for the first time might relate to processes that can produce "negative priming" in some behavioral studies. These results reveal quantitative and qualitative differences between neural substrates of long-term repetition effects for attended versus unattended objects.

Visuospatial Processing in Children with Neurofibromatosis Type 1

ERIC Educational Resources Information Center

Clements-Stephens, Amy M.; Rimrodt, Sheryl L.; Gaur, Pooja; Cutting, Laurie E.

2008-01-01

Neuroimaging studies investigating the neural network of visuospatial processing have revealed a right hemisphere network of activation including inferior parietal lobe, dorsolateral prefrontal cortex, and extrastriate regions. Impaired visuospatial processing, indicated by the Judgment of Line Orientation (JLO), is commonly seen in individuals…

Automatic anatomy recognition using neural network learning of object relationships via virtual landmarks

NASA Astrophysics Data System (ADS)

Yan, Fengxia; Udupa, Jayaram K.; Tong, Yubing; Xu, Guoping; Odhner, Dewey; Torigian, Drew A.

2018-03-01

The recently developed body-wide Automatic Anatomy Recognition (AAR) methodology depends on fuzzy modeling of individual objects, hierarchically arranging objects, constructing an anatomy ensemble of these models, and a dichotomous object recognition-delineation process. The parent-to-offspring spatial relationship in the object hierarchy is crucial in the AAR method. We have found this relationship to be quite complex, and as such any improvement in capturing this relationship information in the anatomy model will improve the process of recognition itself. Currently, the method encodes this relationship based on the layout of the geometric centers of the objects. Motivated by the concept of virtual landmarks (VLs), this paper presents a new one-shot AAR recognition method that utilizes the VLs to learn object relationships by training a neural network to predict the pose and the VLs of an offspring object given the VLs of the parent object in the hierarchy. We set up two neural networks for each parent-offspring object pair in a body region, one for predicting the VLs and another for predicting the pose parameters. The VL-based learning/prediction method is evaluated on two object hierarchies involving 14 objects. We utilize 54 computed tomography (CT) image data sets of head and neck cancer patients and the associated object contours drawn by dosimetrists for routine radiation therapy treatment planning. The VL neural network method is found to yield more accurate object localization than the currently used simple AAR method.

Neural network-based nonlinear model predictive control vs. linear quadratic gaussian control

USGS Publications Warehouse

Cho, C.; Vance, R.; Mardi, N.; Qian, Z.; Prisbrey, K.

1997-01-01

One problem with the application of neural networks to the multivariable control of mineral and extractive processes is determining whether and how to use them. The objective of this investigation was to compare neural network control to more conventional strategies and to determine if there are any advantages in using neural network control in terms of set-point tracking, rise time, settling time, disturbance rejection and other criteria. The procedure involved developing neural network controllers using both historical plant data and simulation models. Various control patterns were tried, including both inverse and direct neural network plant models. These were compared to state space controllers that are, by nature, linear. For grinding and leaching circuits, a nonlinear neural network-based model predictive control strategy was superior to a state space-based linear quadratic gaussian controller. The investigation pointed out the importance of incorporating state space into neural networks by making them recurrent, i.e., feeding certain output state variables into input nodes in the neural network. It was concluded that neural network controllers can have better disturbance rejection, set-point tracking, rise time, settling time and lower set-point overshoot, and it was also concluded that neural network controllers can be more reliable and easy to implement in complex, multivariable plants.

Neural activation toward erotic stimuli in homosexual and heterosexual males.

PubMed

Kagerer, Sabine; Klucken, Tim; Wehrum, Sina; Zimmermann, Mark; Schienle, Anne; Walter, Bertram; Vaitl, Dieter; Stark, Rudolf

2011-11-01

Studies investigating sexual arousal exist, yet there are diverging findings on the underlying neural mechanisms with regard to sexual orientation. Moreover, sexual arousal effects have often been confounded with general arousal effects. Hence, it is still unclear which structures underlie the sexual arousal response in homosexual and heterosexual men. Neural activity and subjective responses were investigated in order to disentangle sexual from general arousal. Considering sexual orientation, differential and conjoint neural activations were of interest. The functional magnetic resonance imaging (fMRI) study focused on the neural networks involved in the processing of sexual stimuli in 21 male participants (11 homosexual, 10 heterosexual). Both groups viewed pictures with erotic content as well as aversive and neutral stimuli. The erotic pictures were subdivided into three categories (most sexually arousing, least sexually arousing, and rest) based on the individual subjective ratings of each participant. Blood oxygen level-dependent responses measured by fMRI and subjective ratings. A conjunction analysis revealed conjoint neural activation related to sexual arousal in thalamus, hypothalamus, occipital cortex, and nucleus accumbens. Increased insula, amygdala, and anterior cingulate gyrus activation could be linked to general arousal. Group differences emerged neither when viewing the most sexually arousing pictures compared with highly arousing aversive pictures nor compared with neutral pictures. Results suggest that a widespread neural network is activated by highly sexually arousing visual stimuli. A partly distinct network of structures underlies sexual and general arousal effects. The processing of preferred, highly sexually arousing stimuli recruited similar structures in homosexual and heterosexual males. © 2011 International Society for Sexual Medicine.

Classification and pose estimation of objects using nonlinear features

NASA Astrophysics Data System (ADS)

Talukder, Ashit; Casasent, David P.

1998-03-01

A new nonlinear feature extraction method called the maximum representation and discrimination feature (MRDF) method is presented for extraction of features from input image data. It implements transformations similar to the Sigma-Pi neural network. However, the weights of the MRDF are obtained in closed form, and offer advantages compared to nonlinear neural network implementations. The features extracted are useful for both object discrimination (classification) and object representation (pose estimation). We show its use in estimating the class and pose of images of real objects and rendered solid CAD models of machine parts from single views using a feature-space trajectory (FST) neural network classifier. We show more accurate classification and pose estimation results than are achieved by standard principal component analysis (PCA) and Fukunaga-Koontz (FK) feature extraction methods.

Object-Oriented Analysis of Satellite Images Using Artificial Neural Networks for Post-Earthquake Buildings Change Detection

NASA Astrophysics Data System (ADS)

Khodaverdi zahraee, N.; Rastiveis, H.

2017-09-01

Earthquake is one of the most divesting natural events that threaten human life during history. After the earthquake, having information about the damaged area, the amount and type of damage can be a great help in the relief and reconstruction for disaster managers. It is very important that these measures should be taken immediately after the earthquake because any negligence could be more criminal losses. The purpose of this paper is to propose and implement an automatic approach for mapping destructed buildings after an earthquake using pre- and post-event high resolution satellite images. In the proposed method after preprocessing, segmentation of both images is performed using multi-resolution segmentation technique. Then, the segmentation results are intersected with ArcGIS to obtain equal image objects on both images. After that, appropriate textural features, which make a better difference between changed or unchanged areas, are calculated for all the image objects. Finally, subtracting the extracted textural features from pre- and post-event images, obtained values are applied as an input feature vector in an artificial neural network for classifying the area into two classes of changed and unchanged areas. The proposed method was evaluated using WorldView2 satellite images, acquired before and after the 2010 Haiti earthquake. The reported overall accuracy of 93% proved the ability of the proposed method for post-earthquake buildings change detection.

Neural networks and logical reasoning systems: a translation table.

PubMed

Martins, J; Mendes, R V

2001-04-01

A correspondence is established between the basic elements of logic reasoning systems (knowledge bases, rules, inference and queries) and the structure and dynamical evolution laws of neural networks. The correspondence is pictured as a translation dictionary which might allow to go back and forth between symbolic and network formulations, a desirable step in learning-oriented systems and multicomputer networks. In the framework of Horn clause logics, it is found that atomic propositions with n arguments correspond to nodes with nth order synapses, rules to synaptic intensity constraints, forward chaining to synaptic dynamics and queries either to simple node activation or to a query tensor dynamics.

Objective assessment of MPEG-2 video quality

NASA Astrophysics Data System (ADS)

Gastaldo, Paolo; Zunino, Rodolfo; Rovetta, Stefano

2002-07-01

The increasing use of video compression standards in broadcasting television systems has required, in recent years, the development of video quality measurements that take into account artifacts specifically caused by digital compression techniques. In this paper we present a methodology for the objective quality assessment of MPEG video streams by using circular back-propagation feedforward neural networks. Mapping neural networks can render nonlinear relationships between objective features and subjective judgments, thus avoiding any simplifying assumption on the complexity of the model. The neural network processes an instantaneous set of input values, and yields an associated estimate of perceived quality. Therefore, the neural-network approach turns objective quality assessment into adaptive modeling of subjective perception. The objective features used for the estimate are chosen according to the assessed relevance to perceived quality and are continuously extracted in real time from compressed video streams. The overall system mimics perception but does not require any analytical model of the underlying physical phenomenon. The capability to process compressed video streams represents an important advantage over existing approaches, like avoiding the stream-decoding process greatly enhances real-time performance. Experimental results confirm that the system provides satisfactory, continuous-time approximations for actual scoring curves concerning real test videos.

Target recognition based on convolutional neural network

NASA Astrophysics Data System (ADS)

Wang, Liqiang; Wang, Xin; Xi, Fubiao; Dong, Jian

2017-11-01

One of the important part of object target recognition is the feature extraction, which can be classified into feature extraction and automatic feature extraction. The traditional neural network is one of the automatic feature extraction methods, while it causes high possibility of over-fitting due to the global connection. The deep learning algorithm used in this paper is a hierarchical automatic feature extraction method, trained with the layer-by-layer convolutional neural network (CNN), which can extract the features from lower layers to higher layers. The features are more discriminative and it is beneficial to the object target recognition.

Object class segmentation of RGB-D video using recurrent convolutional neural networks.

PubMed

Pavel, Mircea Serban; Schulz, Hannes; Behnke, Sven

2017-04-01

Object class segmentation is a computer vision task which requires labeling each pixel of an image with the class of the object it belongs to. Deep convolutional neural networks (DNN) are able to learn and take advantage of local spatial correlations required for this task. They are, however, restricted by their small, fixed-sized filters, which limits their ability to learn long-range dependencies. Recurrent Neural Networks (RNN), on the other hand, do not suffer from this restriction. Their iterative interpretation allows them to model long-range dependencies by propagating activity. This property is especially useful when labeling video sequences, where both spatial and temporal long-range dependencies occur. In this work, a novel RNN architecture for object class segmentation is presented. We investigate several ways to train such a network. We evaluate our models on the challenging NYU Depth v2 dataset for object class segmentation and obtain competitive results. Copyright © 2017 Elsevier Ltd. All rights reserved.

Hierarchical Neural Network (HNN) for Closed Loop Decision Making: Designing the Architecture of a Hierarchical Neural Network to Model Attention, Learning and Goal Oriented Behavior

DTIC Science & Technology

1990-12-01

030(M aau fr e~ re u’. ~oil(eIOE, form a::o n lit Send c f"ent lt ar nq this Ourde" "tii tor ay otther a .e n Of p, amid". to W4Vsntinlln...etadnuaeters ief’ice. 0 i 0reor Iformat.a;tio n ax; d 1 21 ;eQo Q offait of IA4naqe-m.t and Sudget. P01osoer t m edltoru Prole (07044 ,l81.’Nairil m O C NMI. I...I Application of Neural Networks to Robotics I Ziaudin Ahmnad John Selizuky Allm Gun Dmeel University, Depwunent of Electrical miCapue Engineeing

ANNS An X Window Based Version of the AFIT Neural Network Simulator

DTIC Science & Technology

1993-06-01

programer or user can view the dy- namic behavior of an algorithm and its changes of learning state while the neural network paradigms or algorithms...an object as "something you can do things to. An object has state, behavior , and identity, the structure and behavior of similar objects are defined in...their common class. The terms instance and object are interchangeable" [5:516]. The behavior of an object is "characterized by the actions that it

A deep convolutional neural network to analyze position averaged convergent beam electron diffraction patterns.

PubMed

Xu, W; LeBeau, J M

2018-05-01

We establish a series of deep convolutional neural networks to automatically analyze position averaged convergent beam electron diffraction patterns. The networks first calibrate the zero-order disk size, center position, and rotation without the need for pretreating the data. With the aligned data, additional networks then measure the sample thickness and tilt. The performance of the network is explored as a function of a variety of variables including thickness, tilt, and dose. A methodology to explore the response of the neural network to various pattern features is also presented. Processing patterns at a rate of  ∼ 0.1 s/pattern, the network is shown to be orders of magnitude faster than a brute force method while maintaining accuracy. The approach is thus suitable for automatically processing big, 4D STEM data. We also discuss the generality of the method to other materials/orientations as well as a hybrid approach that combines the features of the neural network with least squares fitting for even more robust analysis. The source code is available at https://github.com/subangstrom/DeepDiffraction. Copyright © 2018 Elsevier B.V. All rights reserved.

Network-centric decision architecture for financial or 1/f data models

NASA Astrophysics Data System (ADS)

Jaenisch, Holger M.; Handley, James W.; Massey, Stoney; Case, Carl T.; Songy, Claude G.

2002-12-01

This paper presents a decision architecture algorithm for training neural equation based networks to make autonomous multi-goal oriented, multi-class decisions. These architectures make decisions based on their individual goals and draw from the same network centric feature set. Traditionally, these architectures are comprised of neural networks that offer marginal performance due to lack of convergence of the training set. We present an approach for autonomously extracting sample points as I/O exemplars for generation of multi-branch, multi-node decision architectures populated by adaptively derived neural equations. To test the robustness of this architecture, open source data sets in the form of financial time series were used, requiring a three-class decision space analogous to the lethal, non-lethal, and clutter discrimination problem. This algorithm and the results of its application are presented here.

Vibrational Analysis of Engine Components Using Neural-Net Processing and Electronic Holography

NASA Technical Reports Server (NTRS)

Decker, Arthur J.; Fite, E. Brian; Mehmed, Oral; Thorp, Scott A.

1997-01-01

The use of computational-model trained artificial neural networks to acquire damage specific information from electronic holograms is discussed. A neural network is trained to transform two time-average holograms into a pattern related to the bending-induced-strain distribution of the vibrating component. The bending distribution is very sensitive to component damage unlike the characteristic fringe pattern or the displacement amplitude distribution. The neural network processor is fast for real-time visualization of damage. The two-hologram limit makes the processor more robust to speckle pattern decorrelation. Undamaged and cracked cantilever plates serve as effective objects for testing the combination of electronic holography and neural-net processing. The requirements are discussed for using finite-element-model trained neural networks for field inspections of engine components. The paper specifically discusses neural-network fringe pattern analysis in the presence of the laser speckle effect and the performances of two limiting cases of the neural-net architecture.

Vibrational Analysis of Engine Components Using Neural-Net Processing and Electronic Holography

NASA Technical Reports Server (NTRS)

Decker, Arthur J.; Fite, E. Brian; Mehmed, Oral; Thorp, Scott A.

1998-01-01

The use of computational-model trained artificial neural networks to acquire damage specific information from electronic holograms is discussed. A neural network is trained to transform two time-average holograms into a pattern related to the bending-induced-strain distribution of the vibrating component. The bending distribution is very sensitive to component damage unlike the characteristic fringe pattern or the displacement amplitude distribution. The neural network processor is fast for real-time visualization of damage. The two-hologram limit makes the processor more robust to speckle pattern decorrelation. Undamaged and cracked cantilever plates serve as effective objects for testing the combination of electronic holography and neural-net processing. The requirements are discussed for using finite-element-model trained neural networks for field inspections of engine components. The paper specifically discusses neural-network fringe pattern analysis in the presence of the laser speckle effect and the performances of two limiting cases of the neural-net architecture.

The ART of representation: Memory reduction and noise tolerance in a neural network vision system

NASA Astrophysics Data System (ADS)

Langley, Christopher S.

The Feature Cerebellar Model Arithmetic Computer (FCMAC) is a multiple-input-single-output neural network that can provide three-degree-of-freedom (3-DOF) pose estimation for a robotic vision system. The FCMAC provides sufficient accuracy to enable a manipulator to grasp an object from an arbitrary pose within its workspace. The network learns an appearance-based representation of an object by storing coarsely quantized feature patterns. As all unique patterns are encoded, the network size grows uncontrollably. A new architecture is introduced herein, which combines the FCMAC with an Adaptive Resonance Theory (ART) network. The ART module categorizes patterns observed during training into a set of prototypes that are used to build the FCMAC. As a result, the network no longer grows without bound, but constrains itself to a user-specified size. Pose estimates remain accurate since the ART layer tends to discard the least relevant information first. The smaller network performs recall faster, and in some cases is better for generalization, resulting in a reduction of error at recall time. The ART-Under-Constraint (ART-C) algorithm is extended to include initial filling with randomly selected patterns (referred to as ART-F). In experiments using a real-world data set, the new network performed equally well using less than one tenth the number of coarse patterns as a regular FCMAC. The FCMAC is also extended to include real-valued input activations. As a result, the network can be tuned to reject a variety of types of noise in the image feature detection. A quantitative analysis of noise tolerance was performed using four synthetic noise algorithms, and a qualitative investigation was made using noisy real-world image data. In validation experiments, the FCMAC system outperformed Radial Basis Function (RBF) networks for the 3-DOF problem, and had accuracy comparable to that of Principal Component Analysis (PCA) and superior to that of Shape Context Matching (SCM), both of which estimate orientation only.

Comments on "The multisynapse neural network and its application to fuzzy clustering".

PubMed

Yu, Jian; Hao, Pengwei

2005-05-01

In the above-mentioned paper, Wei and Fahn proposed a neural architecture, the multisynapse neural network, to solve constrained optimization problems including high-order, logarithmic, and sinusoidal forms, etc. As one of its main applications, a fuzzy bidirectional associative clustering network (FBACN) was proposed for fuzzy-partition clustering according to the objective-functional method. The connection between the objective-functional-based fuzzy c-partition algorithms and FBACN is the Lagrange multiplier approach. Unfortunately, the Lagrange multiplier approach was incorrectly applied so that FBACN does not equivalently minimize its corresponding constrained objective-function. Additionally, Wei and Fahn adopted traditional definition of fuzzy c-partition, which is not satisfied by FBACN. Therefore, FBACN can not solve constrained optimization problems, either.

Thermalnet: a Deep Convolutional Network for Synthetic Thermal Image Generation

NASA Astrophysics Data System (ADS)

Kniaz, V. V.; Gorbatsevich, V. S.; Mizginov, V. A.

2017-05-01

Deep convolutional neural networks have dramatically changed the landscape of the modern computer vision. Nowadays methods based on deep neural networks show the best performance among image recognition and object detection algorithms. While polishing of network architectures received a lot of scholar attention, from the practical point of view the preparation of a large image dataset for a successful training of a neural network became one of major challenges. This challenge is particularly profound for image recognition in wavelengths lying outside the visible spectrum. For example no infrared or radar image datasets large enough for successful training of a deep neural network are available to date in public domain. Recent advances of deep neural networks prove that they are also capable to do arbitrary image transformations such as super-resolution image generation, grayscale image colorisation and imitation of style of a given artist. Thus a natural question arise: how could be deep neural networks used for augmentation of existing large image datasets? This paper is focused on the development of the Thermalnet deep convolutional neural network for augmentation of existing large visible image datasets with synthetic thermal images. The Thermalnet network architecture is inspired by colorisation deep neural networks.

Neural-network-directed alignment of optical systems using the laser-beam spatial filter as an example

NASA Technical Reports Server (NTRS)

Decker, Arthur J.; Krasowski, Michael J.; Weiland, Kenneth E.

1993-01-01

This report describes an effort at NASA Lewis Research Center to use artificial neural networks to automate the alignment and control of optical measurement systems. Specifically, it addresses the use of commercially available neural network software and hardware to direct alignments of the common laser-beam-smoothing spatial filter. The report presents a general approach for designing alignment records and combining these into training sets to teach optical alignment functions to neural networks and discusses the use of these training sets to train several types of neural networks. Neural network configurations used include the adaptive resonance network, the back-propagation-trained network, and the counter-propagation network. This work shows that neural networks can be used to produce robust sequencers. These sequencers can learn by example to execute the step-by-step procedures of optical alignment and also can learn adaptively to correct for environmentally induced misalignment. The long-range objective is to use neural networks to automate the alignment and operation of optical measurement systems in remote, harsh, or dangerous aerospace environments. This work also shows that when neural networks are trained by a human operator, training sets should be recorded, training should be executed, and testing should be done in a manner that does not depend on intellectual judgments of the human operator.

Application of two neural network paradigms to the study of voluntary employee turnover.

PubMed

Somers, M J

1999-04-01

Two neural network paradigms--multilayer perceptron and learning vector quantization--were used to study voluntary employee turnover with a sample of 577 hospital employees. The objectives of the study were twofold. The 1st was to assess whether neural computing techniques offered greater predictive accuracy than did conventional turnover methodologies. The 2nd was to explore whether computer models of turnover based on neural network technologies offered new insights into turnover processes. When compared with logistic regression analysis, both neural network paradigms provided considerably more accurate predictions of turnover behavior, particularly with respect to the correct classification of leavers. In addition, these neural network paradigms captured nonlinear relationships that are relevant for theory development. Results are discussed in terms of their implications for future research.

The neurodevelopment of human sexual orientation.

PubMed

Rahman, Qazi

2005-01-01

One of the most enduring and controversial questions in the neuroscience of sexual behaviour surrounds the mechanisms which produce sexual attraction to either males or females. Here, evidence is reviewed which supports the proposal that sexual orientation in humans may be laid down in neural circuitry during early foetal development. Behaviour genetic investigations provide strong evidence for a heritable component to male and female sexual orientation. Linkage studies are partly suggestive of X-linked loci although candidate gene studies have produced null findings. Further evidence demonstrates a role for prenatal sex hormones which may influence the development of a putative network of sexual-orientation-related neural substrates. However, hormonal effects are often inconsistent and investigations rely heavily on 'proxy markers'. A consistent fraternal birth order effect in male sexual orientation also provides support for a model of maternal immunization processes affecting prenatal sexual differentiation. The notion that non-heterosexual preferences may reflect generalized neurodevelopmental perturbations is not supported by available data. These current theories have left little room for learning models of sexual orientation. Future investigations, across the neurosciences, should focus to elucidate the fundamental neural architecture underlying the target-specific direction of human sexual orientation, and their antecedents in developmental neurobiology.

DANoC: An Efficient Algorithm and Hardware Codesign of Deep Neural Networks on Chip.

PubMed

Zhou, Xichuan; Li, Shengli; Tang, Fang; Hu, Shengdong; Lin, Zhi; Zhang, Lei

2017-07-18

Deep neural networks (NNs) are the state-of-the-art models for understanding the content of images and videos. However, implementing deep NNs in embedded systems is a challenging task, e.g., a typical deep belief network could exhaust gigabytes of memory and result in bandwidth and computational bottlenecks. To address this challenge, this paper presents an algorithm and hardware codesign for efficient deep neural computation. A hardware-oriented deep learning algorithm, named the deep adaptive network, is proposed to explore the sparsity of neural connections. By adaptively removing the majority of neural connections and robustly representing the reserved connections using binary integers, the proposed algorithm could save up to 99.9% memory utility and computational resources without undermining classification accuracy. An efficient sparse-mapping-memory-based hardware architecture is proposed to fully take advantage of the algorithmic optimization. Different from traditional Von Neumann architecture, the deep-adaptive network on chip (DANoC) brings communication and computation in close proximity to avoid power-hungry parameter transfers between on-board memory and on-chip computational units. Experiments over different image classification benchmarks show that the DANoC system achieves competitively high accuracy and efficiency comparing with the state-of-the-art approaches.

Flight Test of an Intelligent Flight-Control System

NASA Technical Reports Server (NTRS)

Davidson, Ron; Bosworth, John T.; Jacobson, Steven R.; Thomson, Michael Pl; Jorgensen, Charles C.

2003-01-01

The F-15 Advanced Controls Technology for Integrated Vehicles (ACTIVE) airplane (see figure) was the test bed for a flight test of an intelligent flight control system (IFCS). This IFCS utilizes a neural network to determine critical stability and control derivatives for a control law, the real-time gains of which are computed by an algorithm that solves the Riccati equation. These derivatives are also used to identify the parameters of a dynamic model of the airplane. The model is used in a model-following portion of the control law, in order to provide specific vehicle handling characteristics. The flight test of the IFCS marks the initiation of the Intelligent Flight Control System Advanced Concept Program (IFCS ACP), which is a collaboration between NASA and Boeing Phantom Works. The goals of the IFCS ACP are to (1) develop the concept of a flight-control system that uses neural-network technology to identify aircraft characteristics to provide optimal aircraft performance, (2) develop a self-training neural network to update estimates of aircraft properties in flight, and (3) demonstrate the aforementioned concepts on the F-15 ACTIVE airplane in flight. The activities of the initial IFCS ACP were divided into three Phases, each devoted to the attainment of a different objective. The objective of Phase I was to develop a pre-trained neural network to store and recall the wind-tunnel-based stability and control derivatives of the vehicle. The objective of Phase II was to develop a neural network that can learn how to adjust the stability and control derivatives to account for failures or modeling deficiencies. The objective of Phase III was to develop a flight control system that uses the neural network outputs as a basis for controlling the aircraft. The flight test of the IFCS was performed in stages. In the first stage, the Phase I version of the pre-trained neural network was flown in a passive mode. The neural network software was running using flight data inputs with the outputs provided to instrumentation only. The IFCS was not used to control the airplane. In another stage of the flight test, the Phase I pre-trained neural network was integrated into a Phase III version of the flight control system. The Phase I pretrained neural network provided realtime stability and control derivatives to a Phase III controller that was based on a stochastic optimal feedforward and feedback technique (SOFFT). This combined Phase I/III system was operated together with the research flight-control system (RFCS) of the F-15 ACTIVE during the flight test. The RFCS enables the pilot to switch quickly from the experimental- research flight mode back to the safe conventional mode. These initial IFCS ACP flight tests were completed in April 1999. The Phase I/III flight test milestone was to demonstrate, across a range of subsonic and supersonic flight conditions, that the pre-trained neural network could be used to supply real-time aerodynamic stability and control derivatives to the closed-loop optimal SOFFT flight controller. Additional objectives attained in the flight test included (1) flight qualification of a neural-network-based control system; (2) the use of a combined neural-network/closed-loop optimal flight-control system to obtain level-one handling qualities; and (3) demonstration, through variation of control gains, that different handling qualities can be achieved by setting new target parameters. In addition, data for the Phase-II (on-line-learning) neural network were collected, during the use of stacked-frequency- sweep excitation, for post-flight analysis. Initial analysis of these data showed the potential for future flight tests that will incorporate the real-time identification and on-line learning aspects of the IFCS.

Self-Orientation Modulates the Neural Correlates of Global and Local Processing

PubMed Central

Liddell, Belinda J.; Das, Pritha; Battaglini, Eva; Malhi, Gin S.; Felmingham, Kim L.; Whitford, Thomas J.; Bryant, Richard A.

2015-01-01

Differences in self-orientation (or “self-construal”) may affect how the visual environment is attended, but the neural and cultural mechanisms that drive this remain unclear. Behavioral studies have demonstrated that people from Western backgrounds with predominant individualistic values are perceptually biased towards local-level information; whereas people from non-Western backgrounds that support collectivist values are preferentially focused on contextual and global-level information. In this study, we compared two groups differing in predominant individualistic (N = 15) vs collectivistic (N = 15) self-orientation. Participants completed a global/local perceptual conflict task whilst undergoing functional Magnetic Resonance Imaging (fMRI) scanning. When participants high in individualistic values attended to the global level (ignoring the local level), greater activity was observed in the frontoparietal and cingulo-opercular networks that underpin attentional control, compared to the match (congruent) baseline. Participants high in collectivistic values activated similar attentional control networks o only when directly compared with global processing. This suggests that global interference was stronger than local interference in the conflict task in the collectivistic group. Both groups showed increased activity in dorsolateral prefrontal regions involved in resolving perceptual conflict during heightened distractor interference. The findings suggest that self-orientation may play an important role in driving attention networks to facilitate interaction with the visual environment. PMID:26270820

Self-Orientation Modulates the Neural Correlates of Global and Local Processing.

PubMed

Liddell, Belinda J; Das, Pritha; Battaglini, Eva; Malhi, Gin S; Felmingham, Kim L; Whitford, Thomas J; Bryant, Richard A

2015-01-01

Differences in self-orientation (or "self-construal") may affect how the visual environment is attended, but the neural and cultural mechanisms that drive this remain unclear. Behavioral studies have demonstrated that people from Western backgrounds with predominant individualistic values are perceptually biased towards local-level information; whereas people from non-Western backgrounds that support collectivist values are preferentially focused on contextual and global-level information. In this study, we compared two groups differing in predominant individualistic (N = 15) vs collectivistic (N = 15) self-orientation. Participants completed a global/local perceptual conflict task whilst undergoing functional Magnetic Resonance Imaging (fMRI) scanning. When participants high in individualistic values attended to the global level (ignoring the local level), greater activity was observed in the frontoparietal and cingulo-opercular networks that underpin attentional control, compared to the match (congruent) baseline. Participants high in collectivistic values activated similar attentional control networks o only when directly compared with global processing. This suggests that global interference was stronger than local interference in the conflict task in the collectivistic group. Both groups showed increased activity in dorsolateral prefrontal regions involved in resolving perceptual conflict during heightened distractor interference. The findings suggest that self-orientation may play an important role in driving attention networks to facilitate interaction with the visual environment.

The use of global image characteristics for neural network pattern recognitions

NASA Astrophysics Data System (ADS)

Kulyas, Maksim O.; Kulyas, Oleg L.; Loshkarev, Aleksey S.

2017-04-01

The recognition system is observed, where the information is transferred by images of symbols generated by a television camera. For descriptors of objects the coefficients of two-dimensional Fourier transformation generated in a special way. For solution of the task of classification the one-layer neural network trained on reference images is used. Fast learning of a neural network with a single neuron calculation of coefficients is applied.

Pattern Recognition Using Artificial Neural Network: A Review

NASA Astrophysics Data System (ADS)

Kim, Tai-Hoon

Among the various frameworks in which pattern recognition has been traditionally formulated, the statistical approach has been most intensively studied and used in practice. More recently, artificial neural network techniques theory have been receiving increasing attention. The design of a recognition system requires careful attention to the following issues: definition of pattern classes, sensing environment, pattern representation, feature extraction and selection, cluster analysis, classifier design and learning, selection of training and test samples, and performance evaluation. In spite of almost 50 years of research and development in this field, the general problem of recognizing complex patterns with arbitrary orientation, location, and scale remains unsolved. New and emerging applications, such as data mining, web searching, retrieval of multimedia data, face recognition, and cursive handwriting recognition, require robust and efficient pattern recognition techniques. The objective of this review paper is to summarize and compare some of the well-known methods used in various stages of a pattern recognition system using ANN and identify research topics and applications which are at the forefront of this exciting and challenging field.

A Neural Network Architecture For Rapid Model Indexing In Computer Vision Systems

NASA Astrophysics Data System (ADS)

Pawlicki, Ted

1988-03-01

Models of objects stored in memory have been shown to be useful for guiding the processing of computer vision systems. A major consideration in such systems, however, is how stored models are initially accessed and indexed by the system. As the number of stored models increases, the time required to search memory for the correct model becomes high. Parallel distributed, connectionist, neural networks' have been shown to have appealing content addressable memory properties. This paper discusses an architecture for efficient storage and reference of model memories stored as stable patterns of activity in a parallel, distributed, connectionist, neural network. The emergent properties of content addressability and resistance to noise are exploited to perform indexing of the appropriate object centered model from image centered primitives. The system consists of three network modules each of which represent information relative to a different frame of reference. The model memory network is a large state space vector where fields in the vector correspond to ordered component objects and relative, object based spatial relationships between the component objects. The component assertion network represents evidence about the existence of object primitives in the input image. It establishes local frames of reference for object primitives relative to the image based frame of reference. The spatial relationship constraint network is an intermediate representation which enables the association between the object based and the image based frames of reference. This intermediate level represents information about possible object orderings and establishes relative spatial relationships from the image based information in the component assertion network below. It is also constrained by the lawful object orderings in the model memory network above. The system design is consistent with current psychological theories of recognition by component. It also seems to support Marr's notions of hierarchical indexing. (i.e. the specificity, adjunct, and parent indices) It supports the notion that multiple canonical views of an object may have to be stored in memory to enable its efficient identification. The use of variable fields in the state space vectors appears to keep the number of required nodes in the network down to a tractable number while imposing a semantic value on different areas of the state space. This semantic imposition supports an interface between the analogical aspects of neural networks and the propositional paradigms of symbolic processing.

Digital implementation of a neural network for imaging

NASA Astrophysics Data System (ADS)

Wood, Richard; McGlashan, Alex; Yatulis, Jay; Mascher, Peter; Bruce, Ian

2012-10-01

This paper outlines the design and testing of a digital imaging system that utilizes an artificial neural network with unsupervised and supervised learning to convert streaming input (real time) image space into parameter space. The primary objective of this work is to investigate the effectiveness of using a neural network to significantly reduce the information density of streaming images so that objects can be readily identified by a limited set of primary parameters and act as an enhanced human machine interface (HMI). Many applications are envisioned including use in biomedical imaging, anomaly detection and as an assistive device for the visually impaired. A digital circuit was designed and tested using a Field Programmable Gate Array (FPGA) and an off the shelf digital camera. Our results indicate that the networks can be readily trained when subject to limited sets of objects such as the alphabet. We can also separate limited object sets with rotational and positional invariance. The results also show that limited visual fields form with only local connectivity.

Nondestructive pavement evaluation using ILLI-PAVE based artificial neural network models.

DOT National Transportation Integrated Search

2008-09-01

The overall objective in this research project is to develop advanced pavement structural analysis models for more accurate solutions with fast computation schemes. Soft computing and modeling approaches, specifically the Artificial Neural Network (A...

Path synthesis of four-bar mechanisms using synergy of polynomial neural network and Stackelberg game theory

NASA Astrophysics Data System (ADS)

Ahmadi, Bahman; Nariman-zadeh, Nader; Jamali, Ali

2017-06-01

In this article, a novel approach based on game theory is presented for multi-objective optimal synthesis of four-bar mechanisms. The multi-objective optimization problem is modelled as a Stackelberg game. The more important objective function, tracking error, is considered as the leader, and the other objective function, deviation of the transmission angle from 90° (TA), is considered as the follower. In a new approach, a group method of data handling (GMDH)-type neural network is also utilized to construct an approximate model for the rational reaction set (RRS) of the follower. Using the proposed game-theoretic approach, the multi-objective optimal synthesis of a four-bar mechanism is then cast into a single-objective optimal synthesis using the leader variables and the obtained RRS of the follower. The superiority of using the synergy game-theoretic method of Stackelberg with a GMDH-type neural network is demonstrated for two case studies on the synthesis of four-bar mechanisms.

The effects of short-term and long-term learning on the responses of lateral intraparietal neurons to visually presented objects.

PubMed

Sigurdardottir, Heida M; Sheinberg, David L

2015-07-01

The lateral intraparietal area (LIP) is thought to play an important role in the guidance of where to look and pay attention. LIP can also respond selectively to differently shaped objects. We sought to understand to what extent short-term and long-term experience with visual orienting determines the responses of LIP to objects of different shapes. We taught monkeys to arbitrarily associate centrally presented objects of various shapes with orienting either toward or away from a preferred spatial location of a neuron. The training could last for less than a single day or for several months. We found that neural responses to objects are affected by such experience, but that the length of the learning period determines how this neural plasticity manifests. Short-term learning affects neural responses to objects, but these effects are only seen relatively late after visual onset; at this time, the responses to newly learned objects resemble those of familiar objects that share their meaning or arbitrary association. Long-term learning affects the earliest bottom-up responses to visual objects. These responses tend to be greater for objects that have been associated with looking toward, rather than away from, LIP neurons' preferred spatial locations. Responses to objects can nonetheless be distinct, although they have been similarly acted on in the past and will lead to the same orienting behavior in the future. Our results therefore indicate that a complete experience-driven override of LIP object responses may be difficult or impossible. We relate these results to behavioral work on visual attention.

Convergence analysis of sliding mode trajectories in multi-objective neural networks learning.

PubMed

Costa, Marcelo Azevedo; Braga, Antonio Padua; de Menezes, Benjamin Rodrigues

2012-09-01

The Pareto-optimality concept is used in this paper in order to represent a constrained set of solutions that are able to trade-off the two main objective functions involved in neural networks supervised learning: data-set error and network complexity. The neural network is described as a dynamic system having error and complexity as its state variables and learning is presented as a process of controlling a learning trajectory in the resulting state space. In order to control the trajectories, sliding mode dynamics is imposed to the network. It is shown that arbitrary learning trajectories can be achieved by maintaining the sliding mode gains within their convergence intervals. Formal proofs of convergence conditions are therefore presented. The concept of trajectory learning presented in this paper goes further beyond the selection of a final state in the Pareto set, since it can be reached through different trajectories and states in the trajectory can be assessed individually against an additional objective function. Copyright © 2012 Elsevier Ltd. All rights reserved.

Processing of chromatic information in a deep convolutional neural network.

PubMed

Flachot, Alban; Gegenfurtner, Karl R

2018-04-01

Deep convolutional neural networks are a class of machine-learning algorithms capable of solving non-trivial tasks, such as object recognition, with human-like performance. Little is known about the exact computations that deep neural networks learn, and to what extent these computations are similar to the ones performed by the primate brain. Here, we investigate how color information is processed in the different layers of the AlexNet deep neural network, originally trained on object classification of over 1.2M images of objects in their natural contexts. We found that the color-responsive units in the first layer of AlexNet learned linear features and were broadly tuned to two directions in color space, analogously to what is known of color responsive cells in the primate thalamus. Moreover, these directions are decorrelated and lead to statistically efficient representations, similar to the cardinal directions of the second-stage color mechanisms in primates. We also found, in analogy to the early stages of the primate visual system, that chromatic and achromatic information were segregated in the early layers of the network. Units in the higher layers of AlexNet exhibit on average a lower responsivity for color than units at earlier stages.

About Turn: How Object Orientation Affects Categorisation and Mental Rotation

ERIC Educational Resources Information Center

Milivojevic, Branka; Hamm, Jeff P.; Corballis, Michael C.

2011-01-01

High-density ERPs evoked by rotated alphanumeric characters were examined to determine how neural processing is affected by stimulus orientation during letter/digit classifications and during mirror/normal discriminations. The former task typically produces response times that are unaffected by stimulus orientation while the latter is thought to…

Geometrical structure of Neural Networks: Geodesics, Jeffrey's Prior and Hyper-ribbons

NASA Astrophysics Data System (ADS)

Hayden, Lorien; Alemi, Alex; Sethna, James

2014-03-01

Neural networks are learning algorithms which are employed in a host of Machine Learning problems including speech recognition, object classification and data mining. In practice, neural networks learn a low dimensional representation of high dimensional data and define a model manifold which is an embedding of this low dimensional structure in the higher dimensional space. In this work, we explore the geometrical structure of a neural network model manifold. A Stacked Denoising Autoencoder and a Deep Belief Network are trained on handwritten digits from the MNIST database. Construction of geodesics along the surface and of slices taken from the high dimensional manifolds reveal a hierarchy of widths corresponding to a hyper-ribbon structure. This property indicates that neural networks fall into the class of sloppy models, in which certain parameter combinations dominate the behavior. Employing this information could prove valuable in designing both neural network architectures and training algorithms. This material is based upon work supported by the National Science Foundation Graduate Research Fellowship under Grant No . DGE-1144153.

Three-dimensional object recognitions from two-dimensional images using wavelet transforms and neural networks

NASA Astrophysics Data System (ADS)

Deschenes, Sylvain; Sheng, Yunlong; Chevrette, Paul C.

1998-03-01

3D object classification from 2D IR images is shown. The wavelet transform is used for edge detection. Edge tracking is used for removing noise effectively int he wavelet transform. The invariant Fourier descriptor is used to describe the contour curves. Invariance under out-of-plane rotation is achieved by the feature space trajectory neural network working as a classifier.

Deep learning in the small sample size setting: cascaded feed forward neural networks for medical image segmentation

NASA Astrophysics Data System (ADS)

Gaonkar, Bilwaj; Hovda, David; Martin, Neil; Macyszyn, Luke

2016-03-01

Deep Learning, refers to large set of neural network based algorithms, have emerged as promising machine- learning tools in the general imaging and computer vision domains. Convolutional neural networks (CNNs), a specific class of deep learning algorithms, have been extremely effective in object recognition and localization in natural images. A characteristic feature of CNNs, is the use of a locally connected multi layer topology that is inspired by the animal visual cortex (the most powerful vision system in existence). While CNNs, perform admirably in object identification and localization tasks, typically require training on extremely large datasets. Unfortunately, in medical image analysis, large datasets are either unavailable or are extremely expensive to obtain. Further, the primary tasks in medical imaging are organ identification and segmentation from 3D scans, which are different from the standard computer vision tasks of object recognition. Thus, in order to translate the advantages of deep learning to medical image analysis, there is a need to develop deep network topologies and training methodologies, that are geared towards medical imaging related tasks and can work in a setting where dataset sizes are relatively small. In this paper, we present a technique for stacked supervised training of deep feed forward neural networks for segmenting organs from medical scans. Each `neural network layer' in the stack is trained to identify a sub region of the original image, that contains the organ of interest. By layering several such stacks together a very deep neural network is constructed. Such a network can be used to identify extremely small regions of interest in extremely large images, inspite of a lack of clear contrast in the signal or easily identifiable shape characteristics. What is even more intriguing is that the network stack achieves accurate segmentation even when it is trained on a single image with manually labelled ground truth. We validate this approach,using a publicly available head and neck CT dataset. We also show that a deep neural network of similar depth, if trained directly using backpropagation, cannot acheive the tasks achieved using our layer wise training paradigm.

The optimization of force inputs for active structural acoustic control using a neural network

NASA Technical Reports Server (NTRS)

Cabell, R. H.; Lester, H. C.; Silcox, R. J.

1992-01-01

This paper investigates the use of a neural network to determine which force actuators, of a multi-actuator array, are best activated in order to achieve structural-acoustic control. The concept is demonstrated using a cylinder/cavity model on which the control forces, produced by piezoelectric actuators, are applied with the objective of reducing the interior noise. A two-layer neural network is employed and the back propagation solution is compared with the results calculated by a conventional, least-squares optimization analysis. The ability of the neural network to accurately and efficiently control actuator activation for interior noise reduction is demonstrated.

An Indoor Positioning Technique Based on a Feed-Forward Artificial Neural Network Using Levenberg-Marquardt Learning Method

NASA Astrophysics Data System (ADS)

Pahlavani, P.; Gholami, A.; Azimi, S.

2017-09-01

This paper presents an indoor positioning technique based on a multi-layer feed-forward (MLFF) artificial neural networks (ANN). Most of the indoor received signal strength (RSS)-based WLAN positioning systems use the fingerprinting technique that can be divided into two phases: the offline (calibration) phase and the online (estimation) phase. In this paper, RSSs were collected for all references points in four directions and two periods of time (Morning and Evening). Hence, RSS readings were sampled at a regular time interval and specific orientation at each reference point. The proposed ANN based model used Levenberg-Marquardt algorithm for learning and fitting the network to the training data. This RSS readings in all references points and the known position of these references points was prepared for training phase of the proposed MLFF neural network. Eventually, the average positioning error for this network using 30% check and validation data was computed approximately 2.20 meter.

The application of immune genetic algorithm in main steam temperature of PID control of BP network

NASA Astrophysics Data System (ADS)

Li, Han; Zhen-yu, Zhang

In order to overcome the uncertainties, large delay, large inertia and nonlinear property of the main steam temperature controlled object in the power plant, a neural network intelligent PID control system based on immune genetic algorithm and BP neural network is designed. Using the immune genetic algorithm global search optimization ability and good convergence, optimize the weights of the neural network, meanwhile adjusting PID parameters using BP network. The simulation result shows that the system is superior to conventional PID control system in the control of quality and robustness.

Deep Spatial-Temporal Joint Feature Representation for Video Object Detection.

PubMed

Zhao, Baojun; Zhao, Boya; Tang, Linbo; Han, Yuqi; Wang, Wenzheng

2018-03-04

With the development of deep neural networks, many object detection frameworks have shown great success in the fields of smart surveillance, self-driving cars, and facial recognition. However, the data sources are usually videos, and the object detection frameworks are mostly established on still images and only use the spatial information, which means that the feature consistency cannot be ensured because the training procedure loses temporal information. To address these problems, we propose a single, fully-convolutional neural network-based object detection framework that involves temporal information by using Siamese networks. In the training procedure, first, the prediction network combines the multiscale feature map to handle objects of various sizes. Second, we introduce a correlation loss by using the Siamese network, which provides neighboring frame features. This correlation loss represents object co-occurrences across time to aid the consistent feature generation. Since the correlation loss should use the information of the track ID and detection label, our video object detection network has been evaluated on the large-scale ImageNet VID dataset where it achieves a 69.5% mean average precision (mAP).

Object-oriented Bayesian networks for paternity cases with allelic dependencies

PubMed Central

Hepler, Amanda B.; Weir, Bruce S.

2008-01-01

This study extends the current use of Bayesian networks by incorporating the effects of allelic dependencies in paternity calculations. The use of object-oriented networks greatly simplify the process of building and interpreting forensic identification models, allowing researchers to solve new, more complex problems. We explore two paternity examples: the most common scenario where DNA evidence is available from the alleged father, the mother and the child; a more complex casewhere DNA is not available from the alleged father, but is available from the alleged father’s brother. Object-oriented networks are built, using HUGIN, for each example which incorporate the effects of allelic dependence caused by evolutionary relatedness. PMID:19079769

The utilization of neural nets in populating an object-oriented database

NASA Technical Reports Server (NTRS)

Campbell, William J.; Hill, Scott E.; Cromp, Robert F.

1989-01-01

Existing NASA supported scientific data bases are usually developed, managed and populated in a tedious, error prone and self-limiting way in terms of what can be described in a relational Data Base Management System (DBMS). The next generation Earth remote sensing platforms (i.e., Earth Observation System, (EOS), will be capable of generating data at a rate of over 300 Mbs per second from a suite of instruments designed for different applications. What is needed is an innovative approach that creates object-oriented databases that segment, characterize, catalog and are manageable in a domain-specific context and whose contents are available interactively and in near-real-time to the user community. Described here is work in progress that utilizes an artificial neural net approach to characterize satellite imagery of undefined objects into high-level data objects. The characterized data is then dynamically allocated to an object-oriented data base where it can be reviewed and assessed by a user. The definition, development, and evolution of the overall data system model are steps in the creation of an application-driven knowledge-based scientific information system.

Real time coarse orientation detection in MR scans using multi-planar deep convolutional neural networks

NASA Astrophysics Data System (ADS)

Bhatia, Parmeet S.; Reda, Fitsum; Harder, Martin; Zhan, Yiqiang; Zhou, Xiang Sean

2017-02-01

Automatically detecting anatomy orientation is an important task in medical image analysis. Specifically, the ability to automatically detect coarse orientation of structures is useful to minimize the effort of fine/accurate orientation detection algorithms, to initialize non-rigid deformable registration algorithms or to align models to target structures in model-based segmentation algorithms. In this work, we present a deep convolution neural network (DCNN)-based method for fast and robust detection of the coarse structure orientation, i.e., the hemi-sphere where the principal axis of a structure lies. That is, our algorithm predicts whether the principal orientation of a structure is in the northern hemisphere or southern hemisphere, which we will refer to as UP and DOWN, respectively, in the remainder of this manuscript. The only assumption of our method is that the entire structure is located within the scan's field-of-view (FOV). To efficiently solve the problem in 3D space, we formulated it as a multi-planar 2D deep learning problem. In the training stage, a large number coronal-sagittal slice pairs are constructed as 2-channel images to train a DCNN to classify whether a scan is UP or DOWN. During testing, we randomly sample a small number of coronal-sagittal 2-channel images and pass them through our trained network. Finally, coarse structure orientation is determined using majority voting. We tested our method on 114 Elbow MR Scans. Experimental results suggest that only five 2-channel images are sufficient to achieve a high success rate of 97.39%. Our method is also extremely fast and takes approximately 50 milliseconds per 3D MR scan. Our method is insensitive to the location of the structure in the FOV.

Neural Correlates of Visual–Spatial Attention in Electrocorticographic Signals in Humans

PubMed Central

Gunduz, Aysegul; Brunner, Peter; Daitch, Amy; Leuthardt, Eric C.; Ritaccio, Anthony L.; Pesaran, Bijan; Schalk, Gerwin

2011-01-01

Attention is a cognitive selection mechanism that allocates the limited processing resources of the brain to the sensory streams most relevant to our immediate goals, thereby enhancing responsiveness and behavioral performance. The underlying neural mechanisms of orienting attention are distributed across a widespread cortical network. While aspects of this network have been extensively studied, details about the electrophysiological dynamics of this network are scarce. In this study, we investigated attentional networks using electrocorticographic (ECoG) recordings from the surface of the brain, which combine broad spatial coverage with high temporal resolution, in five human subjects. ECoG was recorded when subjects covertly attended to a spatial location and responded to contrast changes in the presence of distractors in a modified Posner cueing task. ECoG amplitudes in the alpha, beta, and gamma bands identified neural changes associated with covert attention and motor preparation/execution in the different stages of the task. The results show that attentional engagement was primarily associated with ECoG activity in the visual, prefrontal, premotor, and parietal cortices. Motor preparation/execution was associated with ECoG activity in premotor/sensorimotor cortices. In summary, our results illustrate rich and distributed cortical dynamics that are associated with orienting attention and the subsequent motor preparation and execution. These findings are largely consistent with and expand on primate studies using intracortical recordings and human functional neuroimaging studies. PMID:22046153

Recognition of partially occluded threat objects using the annealed Hopefield network

NASA Technical Reports Server (NTRS)

Kim, Jung H.; Yoon, Sung H.; Park, Eui H.; Ntuen, Celestine A.

1992-01-01

Recognition of partially occluded objects has been an important issue to airport security because occlusion causes significant problems in identifying and locating objects during baggage inspection. The neural network approach is suitable for the problems in the sense that the inherent parallelism of neural networks pursues many hypotheses in parallel resulting in high computation rates. Moreover, they provide a greater degree of robustness or fault tolerance than conventional computers. The annealed Hopfield network which is derived from the mean field annealing (MFA) has been developed to find global solutions of a nonlinear system. In the study, it has been proven that the system temperature of MFA is equivalent to the gain of the sigmoid function of a Hopfield network. In our early work, we developed the hybrid Hopfield network (HHN) for fast and reliable matching. However, HHN doesn't guarantee global solutions and yields false matching under heavily occluded conditions because HHN is dependent on initial states by its nature. In this paper, we present the annealed Hopfield network (AHN) for occluded object matching problems. In AHN, the mean field theory is applied to the hybird Hopfield network in order to improve computational complexity of the annealed Hopfield network and provide reliable matching under heavily occluded conditions. AHN is slower than HHN. However, AHN provides near global solutions without initial restrictions and provides less false matching than HHN. In conclusion, a new algorithm based upon a neural network approach was developed to demonstrate the feasibility of the automated inspection of threat objects from x-ray images. The robustness of the algorithm is proved by identifying occluded target objects with large tolerance of their features.

Neural Architecture for Feature Binding in Visual Working Memory.

PubMed

Schneegans, Sebastian; Bays, Paul M

2017-04-05

Binding refers to the operation that groups different features together into objects. We propose a neural architecture for feature binding in visual working memory that employs populations of neurons with conjunction responses. We tested this model using cued recall tasks, in which subjects had to memorize object arrays composed of simple visual features (color, orientation, and location). After a brief delay, one feature of one item was given as a cue, and the observer had to report, on a continuous scale, one or two other features of the cued item. Binding failure in this task is associated with swap errors, in which observers report an item other than the one indicated by the cue. We observed that the probability of swapping two items strongly correlated with the items' similarity in the cue feature dimension, and found a strong correlation between swap errors occurring in spatial and nonspatial report. The neural model explains both swap errors and response variability as results of decoding noisy neural activity, and can account for the behavioral results in quantitative detail. We then used the model to compare alternative mechanisms for binding nonspatial features. We found the behavioral results fully consistent with a model in which nonspatial features are bound exclusively via their shared location, with no indication of direct binding between color and orientation. These results provide evidence for a special role of location in feature binding, and the model explains how this special role could be realized in the neural system. SIGNIFICANCE STATEMENT The problem of feature binding is of central importance in understanding the mechanisms of working memory. How do we remember not only that we saw a red and a round object, but that these features belong together to a single object rather than to different objects in our environment? Here we present evidence for a neural mechanism for feature binding in working memory, based on encoding of visual information by neurons that respond to the conjunction of features. We find clear evidence that nonspatial features are bound via space: we memorize directly where a color or an orientation appeared, but we memorize which color belonged with which orientation only indirectly by virtue of their shared location. Copyright © 2017 Schneegans and Bays.

Optimizing a neural network for detection of moving vehicles in video

NASA Astrophysics Data System (ADS)

Fischer, Noëlle M.; Kruithof, Maarten C.; Bouma, Henri

2017-10-01

In the field of security and defense, it is extremely important to reliably detect moving objects, such as cars, ships, drones and missiles. Detection and analysis of moving objects in cameras near borders could be helpful to reduce illicit trading, drug trafficking, irregular border crossing, trafficking in human beings and smuggling. Many recent benchmarks have shown that convolutional neural networks are performing well in the detection of objects in images. Most deep-learning research effort focuses on classification or detection on single images. However, the detection of dynamic changes (e.g., moving objects, actions and events) in streaming video is extremely relevant for surveillance and forensic applications. In this paper, we combine an end-to-end feedforward neural network for static detection with a recurrent Long Short-Term Memory (LSTM) network for multi-frame analysis. We present a practical guide with special attention to the selection of the optimizer and batch size. The end-to-end network is able to localize and recognize the vehicles in video from traffic cameras. We show an efficient way to collect relevant in-domain data for training with minimal manual labor. Our results show that the combination with LSTM improves performance for the detection of moving vehicles.

Neural network based satellite tracking for deep space applications

NASA Technical Reports Server (NTRS)

Amoozegar, F.; Ruggier, C.

2003-01-01

The objective of this paper is to provide a survey of neural network trends as applied to the tracking of spacecrafts in deep space at Ka-band under various weather conditions and examine the trade-off between tracing accuracy and communication link performance.

Intelligent detectors modelled from the cat's eye

NASA Astrophysics Data System (ADS)

Lindblad, Th.; Becanovic, V.; Lindsey, C. S.; Szekely, G.

1997-02-01

Biologically inspired image/signal processing, in particular neural networks like the Pulse-Coupled Neural Network (PCNN), are revisited. Their use with high granularity high-energy physics detectors, as well as optical sensing devices, for filtering, de-noising, segmentation, object isolation and edge detection is discussed.

Remote sensing of nutrient deficiency in Lactuca sativa using neural networks for terrestrial and advanced life support applications

NASA Astrophysics Data System (ADS)

Sears, Edie Seldon

2000-12-01

A remote sensing study using reflectance and fluorescence spectra of hydroponically grown Lactuca sativa (lettuce) canopies was conducted. An optical receiver was designed and constructed to interface with a commercial fiber optic spectrometer for data acquisition. Optical parameters were varied to determine effects of field of view and distance to target on vegetation stress assessment over the test plant growth cycle. Feedforward backpropagation neural networks (NN) were implemented to predict the presence of canopy stress. Effects of spatial and spectral resolutions on stress predictions of the neural network were also examined. Visual inspection and fresh mass values failed to differentiate among controls, plants cultivated with 25% of the recommended concentration of phosphorous (P), and those cultivated with 25% nitrogen (N) based on fresh mass and visual inspection. The NN's were trained on input vectors created using reflectance and test day, fluorescence and test day, and reflectance, fluorescence, and test day. Four networks were created representing four levels of spectral resolution: 100-nm NN, 10-nm NN, 1-nm NN, and 0.1-nm NN. The 10-nm resolution was found to be sufficient for classifying extreme nitrogen deficiency in freestanding hydroponic lettuce. As a result of leaf angle and canopy structure broadband scattering intensity in the 700-nm to 1000-nm range was found to be the most useful portion of the spectrum in this study. More subtle effects of "greenness" and fluorescence emission were believed to be obscured by canopy structure and leaf orientation. As field of view was not as found to be as significant as originally believed, systems implementing higher repetitions over more uniformly oriented, i.e. smaller, flatter, target areas would provide for more discernible neural network input vectors. It is believed that this technique holds considerable promise for early detection of extreme nitrogen deficiency. Further research is recommended using stereoscopic digital cameras to quantify leaf area index, leaf shape, and leaf orientation as well as reflectance. Given this additional information fluorescence emission may also prove a more useful biological assay of freestanding vegetation.

Synthetic event-related potentials: a computational bridge between neurolinguistic models and experiments.

PubMed

Barrès, Victor; Simons, Arthur; Arbib, Michael

2013-01-01

Our previous work developed Synthetic Brain Imaging to link neural and schema network models of cognition and behavior to PET and fMRI studies of brain function. We here extend this approach to Synthetic Event-Related Potentials (Synthetic ERP). Although the method is of general applicability, we focus on ERP correlates of language processing in the human brain. The method has two components: Phase 1: To generate cortical electro-magnetic source activity from neural or schema network models; and Phase 2: To generate known neurolinguistic ERP data (ERP scalp voltage topographies and waveforms) from putative cortical source distributions and activities within a realistic anatomical model of the human brain and head. To illustrate the challenges of Phase 2 of the methodology, spatiotemporal information from Friederici's 2002 model of auditory language comprehension was used to define cortical regions and time courses of activation for implementation within a forward model of ERP data. The cortical regions from the 2002 model were modeled using atlas-based masks overlaid on the MNI high definition single subject cortical mesh. The electromagnetic contribution of each region was modeled using current dipoles whose position and orientation were constrained by the cortical geometry. In linking neural network computation via EEG forward modeling to empirical results in neurolinguistics, we emphasize the need for neural network models to link their architecture to geometrically sound models of the cortical surface, and the need for conceptual models to refine and adopt brain-atlas based approaches to allow precise brain anchoring of their modules. The detailed analysis of Phase 2 sets the stage for a brief introduction to Phase 1 of the program, including the case for a schema-theoretic approach to language production and perception presented in detail elsewhere. Unlike Dynamic Causal Modeling (DCM) and Bojak's mean field model, Synthetic ERP builds on models of networks that mediate the relation between the brain's inputs, outputs, and internal states in executing a specific task. The neural networks used for Synthetic ERP must include neuroanatomically realistic placement and orientation of the cortical pyramidal neurons. These constraints pose exciting challenges for future work in neural network modeling that is applicable to systems and cognitive neuroscience. Copyright © 2012 Elsevier Ltd. All rights reserved.

Pattern classification and recognition of invertebrate functional groups using self-organizing neural networks.

PubMed

Zhang, WenJun

2007-07-01

Self-organizing neural networks can be used to mimic non-linear systems. The main objective of this study is to make pattern classification and recognition on sampling information using two self-organizing neural network models. Invertebrate functional groups sampled in the irrigated rice field were classified and recognized using one-dimensional self-organizing map and self-organizing competitive learning neural networks. Comparisons between neural network models, distance (similarity) measures, and number of neurons were conducted. The results showed that self-organizing map and self-organizing competitive learning neural network models were effective in pattern classification and recognition of sampling information. Overall the performance of one-dimensional self-organizing map neural network was better than self-organizing competitive learning neural network. The number of neurons could determine the number of classes in the classification. Different neural network models with various distance (similarity) measures yielded similar classifications. Some differences, dependent upon the specific network structure, would be found. The pattern of an unrecognized functional group was recognized with the self-organizing neural network. A relative consistent classification indicated that the following invertebrate functional groups, terrestrial blood sucker; terrestrial flyer; tourist (nonpredatory species with no known functional role other than as prey in ecosystem); gall former; collector (gather, deposit feeder); predator and parasitoid; leaf miner; idiobiont (acarine ectoparasitoid), were classified into the same group, and the following invertebrate functional groups, external plant feeder; terrestrial crawler, walker, jumper or hunter; neustonic (water surface) swimmer (semi-aquatic), were classified into another group. It was concluded that reliable conclusions could be drawn from comparisons of different neural network models that use different distance (similarity) measures. Results with the larger consistency will be more reliable.

Neural dynamics underlying attentional orienting to auditory representations in short-term memory.

PubMed

Backer, Kristina C; Binns, Malcolm A; Alain, Claude

2015-01-21

Sounds are ephemeral. Thus, coherent auditory perception depends on "hearing" back in time: retrospectively attending that which was lost externally but preserved in short-term memory (STM). Current theories of auditory attention assume that sound features are integrated into a perceptual object, that multiple objects can coexist in STM, and that attention can be deployed to an object in STM. Recording electroencephalography from humans, we tested these assumptions, elucidating feature-general and feature-specific neural correlates of auditory attention to STM. Alpha/beta oscillations and frontal and posterior event-related potentials indexed feature-general top-down attentional control to one of several coexisting auditory representations in STM. Particularly, task performance during attentional orienting was correlated with alpha/low-beta desynchronization (i.e., power suppression). However, attention to one feature could occur without simultaneous processing of the second feature of the representation. Therefore, auditory attention to memory relies on both feature-specific and feature-general neural dynamics. Copyright © 2015 the authors 0270-6474/15/351307-12$15.00/0.

Intelligent multi-spectral IR image segmentation

NASA Astrophysics Data System (ADS)

Lu, Thomas; Luong, Andrew; Heim, Stephen; Patel, Maharshi; Chen, Kang; Chao, Tien-Hsin; Chow, Edward; Torres, Gilbert

2017-05-01

This article presents a neural network based multi-spectral image segmentation method. A neural network is trained on the selected features of both the objects and background in the longwave (LW) Infrared (IR) images. Multiple iterations of training are performed until the accuracy of the segmentation reaches satisfactory level. The segmentation boundary of the LW image is used to segment the midwave (MW) and shortwave (SW) IR images. A second neural network detects the local discontinuities and refines the accuracy of the local boundaries. This article compares the neural network based segmentation method to the Wavelet-threshold and Grab-Cut methods. Test results have shown increased accuracy and robustness of this segmentation scheme for multi-spectral IR images.

Prediction of adverse outcomes of acute coronary syndrome using intelligent fusion of triage information with HUMINT

NASA Astrophysics Data System (ADS)

McCullough, Claire L.; Novobilski, Andrew J.; Fesmire, Francis M.

2006-04-01

Faculty from the University of Tennessee at Chattanooga and the University of Tennessee College of Medicine, Chattanooga Unit, have used data mining techniques and neural networks to examine a set of fourteen features, data items, and HUMINT assessments for 2,148 emergency room patients with symptoms possibly indicative of Acute Coronary Syndrome. Specifically, the authors have generated Bayesian networks describing linkages and causality in the data, and have compared them with neural networks. The data includes objective information routinely collected during triage and the physician's initial case assessment, a HUMINT appraisal. Both the neural network and the Bayesian network were used to fuse the disparate types of information with the goal of forecasting thirty-day adverse patient outcome. This paper presents details of the methods of data fusion including both the data mining techniques and the neural network. Results are compared using Receiver Operating Characteristic curves describing the outcomes of both methods, both using only objective features and including the subjective physician's assessment. While preliminary, the results of this continuing study are significant both from the perspective of potential use of the intelligent fusion of biomedical informatics to aid the physician in prescribing treatment necessary to prevent serious adverse outcome from ACS and as a model of fusion of objective data with subjective HUMINT assessment. Possible future work includes extension of successfully demonstrated intelligent fusion methods to other medical applications, and use of decision level fusion to combine results from data mining and neural net approaches for even more accurate outcome prediction.

High Performance Implementation of 3D Convolutional Neural Networks on a GPU.

PubMed

Lan, Qiang; Wang, Zelong; Wen, Mei; Zhang, Chunyuan; Wang, Yijie

2017-01-01

Convolutional neural networks have proven to be highly successful in applications such as image classification, object tracking, and many other tasks based on 2D inputs. Recently, researchers have started to apply convolutional neural networks to video classification, which constitutes a 3D input and requires far larger amounts of memory and much more computation. FFT based methods can reduce the amount of computation, but this generally comes at the cost of an increased memory requirement. On the other hand, the Winograd Minimal Filtering Algorithm (WMFA) can reduce the number of operations required and thus can speed up the computation, without increasing the required memory. This strategy was shown to be successful for 2D neural networks. We implement the algorithm for 3D convolutional neural networks and apply it to a popular 3D convolutional neural network which is used to classify videos and compare it to cuDNN. For our highly optimized implementation of the algorithm, we observe a twofold speedup for most of the 3D convolution layers of our test network compared to the cuDNN version.

High Performance Implementation of 3D Convolutional Neural Networks on a GPU

PubMed Central

Wang, Zelong; Wen, Mei; Zhang, Chunyuan; Wang, Yijie

2017-01-01

Convolutional neural networks have proven to be highly successful in applications such as image classification, object tracking, and many other tasks based on 2D inputs. Recently, researchers have started to apply convolutional neural networks to video classification, which constitutes a 3D input and requires far larger amounts of memory and much more computation. FFT based methods can reduce the amount of computation, but this generally comes at the cost of an increased memory requirement. On the other hand, the Winograd Minimal Filtering Algorithm (WMFA) can reduce the number of operations required and thus can speed up the computation, without increasing the required memory. This strategy was shown to be successful for 2D neural networks. We implement the algorithm for 3D convolutional neural networks and apply it to a popular 3D convolutional neural network which is used to classify videos and compare it to cuDNN. For our highly optimized implementation of the algorithm, we observe a twofold speedup for most of the 3D convolution layers of our test network compared to the cuDNN version. PMID:29250109

Method and apparatus for detecting concealed weapons

DOEpatents

Kotter, Dale K.; Fluck, Frederick D.

2006-03-14

Apparatus for classifying a ferromagnetic object within a sensing area may include a magnetic field sensor that produces magnetic field data. A signal processing system operatively associated with the magnetic field sensor includes a neural network. The neural network compares the magnetic field data with magnetic field data produced by known ferromagnetic objects to make a probabilistic determination as to the classification of the ferromagnetic object within the sensing area. A user interface operatively associated with the signal processing system produces a user-discernable output indicative of the probabilistic determination of the classification of the ferromagnetic object within a sensing area.

Antagonistic neural networks underlying differentiated leadership roles.

PubMed

Boyatzis, Richard E; Rochford, Kylie; Jack, Anthony I

2014-01-01

The emergence of two distinct leadership roles, the task leader and the socio-emotional leader, has been documented in the leadership literature since the 1950s. Recent research in neuroscience suggests that the division between task-oriented and socio-emotional-oriented roles derives from a fundamental feature of our neurobiology: an antagonistic relationship between two large-scale cortical networks - the task-positive network (TPN) and the default mode network (DMN). Neural activity in TPN tends to inhibit activity in the DMN, and vice versa. The TPN is important for problem solving, focusing of attention, making decisions, and control of action. The DMN plays a central role in emotional self-awareness, social cognition, and ethical decision making. It is also strongly linked to creativity and openness to new ideas. Because activation of the TPN tends to suppress activity in the DMN, an over-emphasis on task-oriented leadership may prove deleterious to social and emotional aspects of leadership. Similarly, an overemphasis on the DMN would result in difficulty focusing attention, making decisions, and solving known problems. In this paper, we will review major streams of theory and research on leadership roles in the context of recent findings from neuroscience and psychology. We conclude by suggesting that emerging research challenges the assumption that role differentiation is both natural and necessary, in particular when openness to new ideas, people, emotions, and ethical concerns are important to success.

Antagonistic neural networks underlying differentiated leadership roles

PubMed Central

Boyatzis, Richard E.; Rochford, Kylie; Jack, Anthony I.

2014-01-01

The emergence of two distinct leadership roles, the task leader and the socio-emotional leader, has been documented in the leadership literature since the 1950s. Recent research in neuroscience suggests that the division between task-oriented and socio-emotional-oriented roles derives from a fundamental feature of our neurobiology: an antagonistic relationship between two large-scale cortical networks – the task-positive network (TPN) and the default mode network (DMN). Neural activity in TPN tends to inhibit activity in the DMN, and vice versa. The TPN is important for problem solving, focusing of attention, making decisions, and control of action. The DMN plays a central role in emotional self-awareness, social cognition, and ethical decision making. It is also strongly linked to creativity and openness to new ideas. Because activation of the TPN tends to suppress activity in the DMN, an over-emphasis on task-oriented leadership may prove deleterious to social and emotional aspects of leadership. Similarly, an overemphasis on the DMN would result in difficulty focusing attention, making decisions, and solving known problems. In this paper, we will review major streams of theory and research on leadership roles in the context of recent findings from neuroscience and psychology. We conclude by suggesting that emerging research challenges the assumption that role differentiation is both natural and necessary, in particular when openness to new ideas, people, emotions, and ethical concerns are important to success. PMID:24624074

Multi-objective evolutionary optimization for constructing neural networks for virtual reality visual data mining: application to geophysical prospecting.

PubMed

Valdés, Julio J; Barton, Alan J

2007-05-01

A method for the construction of virtual reality spaces for visual data mining using multi-objective optimization with genetic algorithms on nonlinear discriminant (NDA) neural networks is presented. Two neural network layers (the output and the last hidden) are used for the construction of simultaneous solutions for: (i) a supervised classification of data patterns and (ii) an unsupervised similarity structure preservation between the original data matrix and its image in the new space. A set of spaces are constructed from selected solutions along the Pareto front. This strategy represents a conceptual improvement over spaces computed by single-objective optimization. In addition, genetic programming (in particular gene expression programming) is used for finding analytic representations of the complex mappings generating the spaces (a composition of NDA and orthogonal principal components). The presented approach is domain independent and is illustrated via application to the geophysical prospecting of caves.

HONTIOR - HIGHER-ORDER NEURAL NETWORK FOR TRANSFORMATION INVARIANT OBJECT RECOGNITION

NASA Technical Reports Server (NTRS)

Spirkovska, L.

1994-01-01

Neural networks have been applied in numerous fields, including transformation invariant object recognition, wherein an object is recognized despite changes in the object's position in the input field, size, or rotation. One of the more successful neural network methods used in invariant object recognition is the higher-order neural network (HONN) method. With a HONN, known relationships are exploited and the desired invariances are built directly into the architecture of the network, eliminating the need for the network to learn invariance to transformations. This results in a significant reduction in the training time required, since the network needs to be trained on only one view of each object, not on numerous transformed views. Moreover, one hundred percent accuracy is guaranteed for images characterized by the built-in distortions, providing noise is not introduced through pixelation. The program HONTIOR implements a third-order neural network having invariance to translation, scale, and in-plane rotation built directly into the architecture, Thus, for 2-D transformation invariance, the network needs only to be trained on just one view of each object. HONTIOR can also be used for 3-D transformation invariant object recognition by training the network only on a set of out-of-plane rotated views. Historically, the major drawback of HONNs has been that the size of the input field was limited to the memory required for the large number of interconnections in a fully connected network. HONTIOR solves this problem by coarse coding the input images (coding an image as a set of overlapping but offset coarser images). Using this scheme, large input fields (4096 x 4096 pixels) can easily be represented using very little virtual memory (30Mb). The HONTIOR distribution consists of three main programs. The first program contains the training and testing routines for a third-order neural network. The second program contains the same training and testing procedures as the first, but it also contains a number of functions to display and edit training and test images. Finally, the third program is an auxiliary program which calculates the included angles for a given input field size. HONTIOR is written in C language, and was originally developed for Sun3 and Sun4 series computers. Both graphic and command line versions of the program are provided. The command line version has been successfully compiled and executed both on computers running the UNIX operating system and on DEC VAX series computer running VMS. The graphic version requires the SunTools windowing environment, and therefore runs only on Sun series computers. The executable for the graphics version of HONTIOR requires 1Mb of RAM. The standard distribution medium for HONTIOR is a .25 inch streaming magnetic tape cartridge in UNIX tar format. It is also available on a 3.5 inch diskette in UNIX tar format. The package includes sample input and output data. HONTIOR was developed in 1991. Sun, Sun3 and Sun4 are trademarks of Sun Microsystems, Inc. UNIX is a registered trademark of AT&T Bell Laboratories. DEC, VAX, and VMS are trademarks of Digital Equipment Corporation.

Two-dimensional shape recognition using oriented-polar representation

NASA Astrophysics Data System (ADS)

Hu, Neng-Chung; Yu, Kuo-Kan; Hsu, Yung-Li

1997-10-01

To deal with such a problem as object recognition of position, scale, and rotation invariance (PSRI), we utilize some PSRI properties of images obtained from objects, for example, the centroid of the image. The corresponding position of the centroid to the boundary of the image is invariant in spite of rotation, scale, and translation of the image. To obtain the information of the image, we use the technique similar to Radon transform, called the oriented-polar representation of a 2D image. In this representation, two specific points, the centroid and the weighted mean point, are selected to form an initial ray, then the image is sampled with N angularly equispaced rays departing from the initial rays. Each ray contains a number of intersections and the distance information obtained from the centroid to the intersections. The shape recognition algorithm is based on the least total error of these two items of information. Together with a simple noise removal and a typical backpropagation neural network, this algorithm is simple, but the PSRI is achieved with a high recognition rate.

Third-dimension information retrieval from a single convergent-beam transmission electron diffraction pattern using an artificial neural network

NASA Astrophysics Data System (ADS)

Pennington, Robert S.; Van den Broek, Wouter; Koch, Christoph T.

2014-05-01

We have reconstructed third-dimension specimen information from convergent-beam electron diffraction (CBED) patterns simulated using the stacked-Bloch-wave method. By reformulating the stacked-Bloch-wave formalism as an artificial neural network and optimizing with resilient back propagation, we demonstrate specimen orientation reconstructions with depth resolutions down to 5 nm. To show our algorithm's ability to analyze realistic data, we also discuss and demonstrate our algorithm reconstructing from noisy data and using a limited number of CBED disks. Applicability of this reconstruction algorithm to other specimen parameters is discussed.

Neural basis for dynamic updating of object representation in visual working memory.

PubMed

Takahama, Sachiko; Miyauchi, Satoru; Saiki, Jun

2010-02-15

In real world, objects have multiple features and change dynamically. Thus, object representations must satisfy dynamic updating and feature binding. Previous studies have investigated the neural activity of dynamic updating or feature binding alone, but not both simultaneously. We investigated the neural basis of feature-bound object representation in a dynamically updating situation by conducting a multiple object permanence tracking task, which required observers to simultaneously process both the maintenance and dynamic updating of feature-bound objects. Using an event-related design, we separated activities during memory maintenance and change detection. In the search for regions showing selective activation in dynamic updating of feature-bound objects, we identified a network during memory maintenance that was comprised of the inferior precentral sulcus, superior parietal lobule, and middle frontal gyrus. In the change detection period, various prefrontal regions, including the anterior prefrontal cortex, were activated. In updating object representation of dynamically moving objects, the inferior precentral sulcus closely cooperates with a so-called "frontoparietal network", and subregions of the frontoparietal network can be decomposed into those sensitive to spatial updating and feature binding. The anterior prefrontal cortex identifies changes in object representation by comparing memory and perceptual representations rather than maintaining object representations per se, as previously suggested. Copyright 2009 Elsevier Inc. All rights reserved.

Disentangling the attention network test: behavioral, event related potentials, and neural source analyses

PubMed Central

Galvao-Carmona, Alejandro; González-Rosa, Javier J.; Hidalgo-Muñoz, Antonio R.; Páramo, Dolores; Benítez, María L.; Izquierdo, Guillermo; Vázquez-Marrufo, Manuel

2014-01-01

Background: The study of the attentional system remains a challenge for current neuroscience. The “Attention Network Test” (ANT) was designed to study simultaneously three different attentional networks (alerting, orienting, and executive) based in subtraction of different experimental conditions. However, some studies recommend caution with these calculations due to the interactions between the attentional networks. In particular, it is highly relevant that several interpretations about attentional impairment have arisen from these calculations in diverse pathologies. Event related potentials (ERPs) and neural source analysis can be applied to disentangle the relationships between these attentional networks not specifically shown by behavioral measures. Results: This study shows that there is a basic level of alerting (tonic alerting) in the no cue (NC) condition, represented by a slow negative trend in the ERP trace prior to the onset of the target stimuli. A progressive increase in the CNV amplitude related to the amount of information provided by the cue conditions is also shown. Neural source analysis reveals specific modulations of the CNV related to a task-related expectancy presented in the NC condition; a late modulation triggered by the central cue (CC) condition and probably representing a generic motor preparation; and an early and late modulation for spatial cue (SC) condition suggesting specific motor and sensory preactivation. Finally, the first component in the information processing of the target stimuli modulated by the interaction between orienting network and the executive system can be represented by N1. Conclusions: The ANT is useful as a paradigm to study specific attentional mechanisms and their interactions. However, calculation of network effects is based in subtractions with non-comparable experimental conditions, as evidenced by the present data, which can induce misinterpretations in the study of the attentional capacity in human subjects. PMID:25352800

Hybrid Neural-Network: Genetic Algorithm Technique for Aircraft Engine Performance Diagnostics Developed and Demonstrated

NASA Technical Reports Server (NTRS)

Kobayashi, Takahisa; Simon, Donald L.

2002-01-01

As part of the NASA Aviation Safety Program, a unique model-based diagnostics method that employs neural networks and genetic algorithms for aircraft engine performance diagnostics has been developed and demonstrated at the NASA Glenn Research Center against a nonlinear gas turbine engine model. Neural networks are applied to estimate the internal health condition of the engine, and genetic algorithms are used for sensor fault detection, isolation, and quantification. This hybrid architecture combines the excellent nonlinear estimation capabilities of neural networks with the capability to rank the likelihood of various faults given a specific sensor suite signature. The method requires a significantly smaller data training set than a neural network approach alone does, and it performs the combined engine health monitoring objectives of performance diagnostics and sensor fault detection and isolation in the presence of nominal and degraded engine health conditions.

Chaotic simulated annealing by a neural network with a variable delay: design and application.

PubMed

Chen, Shyan-Shiou

2011-10-01

In this paper, we have three goals: the first is to delineate the advantages of a variably delayed system, the second is to find a more intuitive Lyapunov function for a delayed neural network, and the third is to design a delayed neural network for a quadratic cost function. For delayed neural networks, most researchers construct a Lyapunov function based on the linear matrix inequality (LMI) approach. However, that approach is not intuitive. We provide a alternative candidate Lyapunov function for a delayed neural network. On the other hand, if we are first given a quadratic cost function, we can construct a delayed neural network by suitably dividing the second-order term into two parts: a self-feedback connection weight and a delayed connection weight. To demonstrate the advantage of a variably delayed neural network, we propose a transiently chaotic neural network with variable delay and show numerically that the model should possess a better searching ability than Chen-Aihara's model, Wang's model, and Zhao's model. We discuss both the chaotic and the convergent phases. During the chaotic phase, we simply present bifurcation diagrams for a single neuron with a constant delay and with a variable delay. We show that the variably delayed model possesses the stochastic property and chaotic wandering. During the convergent phase, we not only provide a novel Lyapunov function for neural networks with a delay (the Lyapunov function is independent of the LMI approach) but also establish a correlation between the Lyapunov function for a delayed neural network and an objective function for the traveling salesman problem. © 2011 IEEE

Analog neural network control method proposed for use in a backup satellite control mode

DOE Office of Scientific and Technical Information (OSTI.GOV)

Frigo, J.R.; Tilden, M.W.

1998-03-01

The authors propose to use an analog neural network controller implemented in hardware, independent of the active control system, for use in a satellite backup control mode. The controller uses coarse sun sensor inputs. The field of view of the sensors activate the neural controller, creating an analog dead band with respect to the direction of the sun on each axis. This network controls the orientation of the vehicle toward the sunlight to ensure adequate power for the system. The attitude of the spacecraft is stabilized with respect to the ambient magnetic field on orbit. This paper develops a modelmore » of the controller using real-time coarse sun sensor data and a dynamic model of a prototype system based on a satellite system. The simulation results and the feasibility of this control method for use in a satellite backup control mode are discussed.« less

Improving Odometric Accuracy for an Autonomous Electric Cart.

PubMed

Toledo, Jonay; Piñeiro, Jose D; Arnay, Rafael; Acosta, Daniel; Acosta, Leopoldo

2018-01-12

In this paper, a study of the odometric system for the autonomous cart Verdino, which is an electric vehicle based on a golf cart, is presented. A mathematical model of the odometric system is derived from cart movement equations, and is used to compute the vehicle position and orientation. The inputs of the system are the odometry encoders, and the model uses the wheels diameter and distance between wheels as parameters. With this model, a least square minimization is made in order to get the nominal best parameters. This model is updated, including a real time wheel diameter measurement improving the accuracy of the results. A neural network model is used in order to learn the odometric model from data. Tests are made using this neural network in several configurations and the results are compared to the mathematical model, showing that the neural network can outperform the first proposed model.

Recognition of abstract objects via neural oscillators: interaction among topological organization, associative memory and gamma band synchronization.

PubMed

Ursino, Mauro; Magosso, Elisa; Cuppini, Cristiano

2009-02-01

Synchronization of neural activity in the gamma band is assumed to play a significant role not only in perceptual processing, but also in higher cognitive functions. Here, we propose a neural network of Wilson-Cowan oscillators to simulate recognition of abstract objects, each represented as a collection of four features. Features are ordered in topological maps of oscillators connected via excitatory lateral synapses, to implement a similarity principle. Experience on previous objects is stored in long-range synapses connecting the different topological maps, and trained via timing dependent Hebbian learning (previous knowledge principle). Finally, a downstream decision network detects the presence of a reliable object representation, when all features are oscillating in synchrony. Simulations performed giving various simultaneous objects to the network (from 1 to 4), with some missing and/or modified properties suggest that the network can reconstruct objects, and segment them from the other simultaneously present objects, even in case of deteriorated information, noise, and moderate correlation among the inputs (one common feature). The balance between sensitivity and specificity depends on the strength of the Hebbian learning. Achieving a correct reconstruction in all cases, however, requires ad hoc selection of the oscillation frequency. The model represents an attempt to investigate the interactions among topological maps, autoassociative memory, and gamma-band synchronization, for recognition of abstract objects.

Reconstructing missing daily precipitation data using regression trees and artificial neural networks

USDA-ARS?s Scientific Manuscript database

Incomplete meteorological data has been a problem in environmental modeling studies. The objective of this work was to develop a technique to reconstruct missing daily precipitation data in the central part of Chesapeake Bay Watershed using regression trees (RT) and artificial neural networks (ANN)....

Coarse-coded higher-order neural networks for PSRI object recognition. [position, scale, and rotation invariant

NASA Technical Reports Server (NTRS)

Spirkovska, Lilly; Reid, Max B.

1993-01-01

A higher-order neural network (HONN) can be designed to be invariant to changes in scale, translation, and inplane rotation. Invariances are built directly into the architecture of a HONN and do not need to be learned. Consequently, fewer training passes and a smaller training set are required to learn to distinguish between objects. The size of the input field is limited, however, because of the memory required for the large number of interconnections in a fully connected HONN. By coarse coding the input image, the input field size can be increased to allow the larger input scenes required for practical object recognition problems. We describe a coarse coding technique and present simulation results illustrating its usefulness and its limitations. Our simulations show that a third-order neural network can be trained to distinguish between two objects in a 4096 x 4096 pixel input field independent of transformations in translation, in-plane rotation, and scale in less than ten passes through the training set. Furthermore, we empirically determine the limits of the coarse coding technique in the object recognition domain.

Optical implementation of a feature-based neural network with application to automatic target recognition

NASA Technical Reports Server (NTRS)

Chao, Tien-Hsin; Stoner, William W.

1993-01-01

An optical neural network based on the neocognitron paradigm is introduced. A novel aspect of the architecture design is shift-invariant multichannel Fourier optical correlation within each processing layer. Multilayer processing is achieved by feeding back the ouput of the feature correlator interatively to the input spatial light modulator and by updating the Fourier filters. By training the neural net with characteristic features extracted from the target images, successful pattern recognition with intraclass fault tolerance and interclass discrimination is achieved. A detailed system description is provided. Experimental demonstrations of a two-layer neural network for space-object discrimination is also presented.

Automatic target recognition using a feature-based optical neural network

NASA Technical Reports Server (NTRS)

Chao, Tien-Hsin

1992-01-01

An optical neural network based upon the Neocognitron paradigm (K. Fukushima et al. 1983) is introduced. A novel aspect of the architectural design is shift-invariant multichannel Fourier optical correlation within each processing layer. Multilayer processing is achieved by iteratively feeding back the output of the feature correlator to the input spatial light modulator and updating the Fourier filters. By training the neural net with characteristic features extracted from the target images, successful pattern recognition with intra-class fault tolerance and inter-class discrimination is achieved. A detailed system description is provided. Experimental demonstration of a two-layer neural network for space objects discrimination is also presented.

Low-complexity object detection with deep convolutional neural network for embedded systems

NASA Astrophysics Data System (ADS)

Tripathi, Subarna; Kang, Byeongkeun; Dane, Gokce; Nguyen, Truong

2017-09-01

We investigate low-complexity convolutional neural networks (CNNs) for object detection for embedded vision applications. It is well-known that consolidation of an embedded system for CNN-based object detection is more challenging due to computation and memory requirement comparing with problems like image classification. To achieve these requirements, we design and develop an end-to-end TensorFlow (TF)-based fully-convolutional deep neural network for generic object detection task inspired by one of the fastest framework, YOLO.1 The proposed network predicts the localization of every object by regressing the coordinates of the corresponding bounding box as in YOLO. Hence, the network is able to detect any objects without any limitations in the size of the objects. However, unlike YOLO, all the layers in the proposed network is fully-convolutional. Thus, it is able to take input images of any size. We pick face detection as an use case. We evaluate the proposed model for face detection on FDDB dataset and Widerface dataset. As another use case of generic object detection, we evaluate its performance on PASCAL VOC dataset. The experimental results demonstrate that the proposed network can predict object instances of different sizes and poses in a single frame. Moreover, the results show that the proposed method achieves comparative accuracy comparing with the state-of-the-art CNN-based object detection methods while reducing the model size by 3× and memory-BW by 3 - 4× comparing with one of the best real-time CNN-based object detectors, YOLO. Our 8-bit fixed-point TF-model provides additional 4× memory reduction while keeping the accuracy nearly as good as the floating-point model. Moreover, the fixed- point model is capable of achieving 20× faster inference speed comparing with the floating-point model. Thus, the proposed method is promising for embedded implementations.

A light and faster regional convolutional neural network for object detection in optical remote sensing images

NASA Astrophysics Data System (ADS)

Ding, Peng; Zhang, Ye; Deng, Wei-Jian; Jia, Ping; Kuijper, Arjan

2018-07-01

Detection of objects from satellite optical remote sensing images is very important for many commercial and governmental applications. With the development of deep convolutional neural networks (deep CNNs), the field of object detection has seen tremendous advances. Currently, objects in satellite remote sensing images can be detected using deep CNNs. In general, optical remote sensing images contain many dense and small objects, and the use of the original Faster Regional CNN framework does not yield a suitably high precision. Therefore, after careful analysis we adopt dense convoluted networks, a multi-scale representation and various combinations of improvement schemes to enhance the structure of the base VGG16-Net for improving the precision. We propose an approach to reduce the test-time (detection time) and memory requirements. To validate the effectiveness of our approach, we perform experiments using satellite remote sensing image datasets of aircraft and automobiles. The results show that the improved network structure can detect objects in satellite optical remote sensing images more accurately and efficiently.

Neural field model to reconcile structure with function in primary visual cortex.

PubMed

Rankin, James; Chavane, Frédéric

2017-10-01

Voltage-sensitive dye imaging experiments in primary visual cortex (V1) have shown that local, oriented visual stimuli elicit stable orientation-selective activation within the stimulus retinotopic footprint. The cortical activation dynamically extends far beyond the retinotopic footprint, but the peripheral spread stays non-selective-a surprising finding given a number of anatomo-functional studies showing the orientation specificity of long-range connections. Here we use a computational model to investigate this apparent discrepancy by studying the expected population response using known published anatomical constraints. The dynamics of input-driven localized states were simulated in a planar neural field model with multiple sub-populations encoding orientation. The realistic connectivity profile has parameters controlling the clustering of long-range connections and their orientation bias. We found substantial overlap between the anatomically relevant parameter range and a steep decay in orientation selective activation that is consistent with the imaging experiments. In this way our study reconciles the reported orientation bias of long-range connections with the functional expression of orientation selective neural activity. Our results demonstrate this sharp decay is contingent on three factors, that long-range connections are sufficiently diffuse, that the orientation bias of these connections is in an intermediate range (consistent with anatomy) and that excitation is sufficiently balanced by inhibition. Conversely, our modelling results predict that, for reduced inhibition strength, spurious orientation selective activation could be generated through long-range lateral connections. Furthermore, if the orientation bias of lateral connections is very strong, or if inhibition is particularly weak, the network operates close to an instability leading to unbounded cortical activation.

A System for Video Surveillance and Monitoring CMU VSAM Final Report

DTIC Science & Technology

1999-11-30

motion-based skeletonization, neural network , spatio-temporal salience Patterns inside image chips, spurious motion rejection, model -based... network of sensors with respect to the model coordinate system, computation of 3D geolocation estimates, and graphical display of object hypotheses...rithms have been developed. The first uses view dependent visual properties to train a neural network classifier to recognize four classes: single

A Neural Network Aero Design System for Advanced Turbo-Engines

NASA Technical Reports Server (NTRS)

Sanz, Jose M.

1999-01-01

An inverse design method calculates the blade shape that produces a prescribed input pressure distribution. By controlling this input pressure distribution the aerodynamic design objectives can easily be met. Because of the intrinsic relationship between pressure distribution and airfoil physical properties, a neural network can be trained to choose the optimal pressure distribution that would meet a set of physical requirements. The neural network technique works well not only as an interpolating device but also as an extrapolating device to achieve blade designs from a given database. Two validating test cases are discussed.

A biologically inspired neural network model to transformation invariant object recognition

NASA Astrophysics Data System (ADS)

Iftekharuddin, Khan M.; Li, Yaqin; Siddiqui, Faraz

2007-09-01

Transformation invariant image recognition has been an active research area due to its widespread applications in a variety of fields such as military operations, robotics, medical practices, geographic scene analysis, and many others. The primary goal for this research is detection of objects in the presence of image transformations such as changes in resolution, rotation, translation, scale and occlusion. We investigate a biologically-inspired neural network (NN) model for such transformation-invariant object recognition. In a classical training-testing setup for NN, the performance is largely dependent on the range of transformation or orientation involved in training. However, an even more serious dilemma is that there may not be enough training data available for successful learning or even no training data at all. To alleviate this problem, a biologically inspired reinforcement learning (RL) approach is proposed. In this paper, the RL approach is explored for object recognition with different types of transformations such as changes in scale, size, resolution and rotation. The RL is implemented in an adaptive critic design (ACD) framework, which approximates the neuro-dynamic programming of an action network and a critic network, respectively. Two ACD algorithms such as Heuristic Dynamic Programming (HDP) and Dual Heuristic dynamic Programming (DHP) are investigated to obtain transformation invariant object recognition. The two learning algorithms are evaluated statistically using simulated transformations in images as well as with a large-scale UMIST face database with pose variations. In the face database authentication case, the 90° out-of-plane rotation of faces from 20 different subjects in the UMIST database is used. Our simulations show promising results for both designs for transformation-invariant object recognition and authentication of faces. Comparing the two algorithms, DHP outperforms HDP in learning capability, as DHP takes fewer steps to perform a successful recognition task in general. Further, the residual critic error in DHP is generally smaller than that of HDP, and DHP achieves a 100% success rate more frequently than HDP for individual objects/subjects. On the other hand, HDP is more robust than the DHP as far as success rate across the database is concerned when applied in a stochastic and uncertain environment, and the computational time involved in DHP is more.

Statistical Hypothesis Testing using CNN Features for Synthesis of Adversarial Counterexamples to Human and Object Detection Vision Systems

DOE Office of Scientific and Technical Information (OSTI.GOV)

Raj, Sunny; Jha, Sumit Kumar; Pullum, Laura L.

Validating the correctness of human detection vision systems is crucial for safety applications such as pedestrian collision avoidance in autonomous vehicles. The enormous space of possible inputs to such an intelligent system makes it difficult to design test cases for such systems. In this report, we present our tool MAYA that uses an error model derived from a convolutional neural network (CNN) to explore the space of images similar to a given input image, and then tests the correctness of a given human or object detection system on such perturbed images. We demonstrate the capability of our tool on themore » pre-trained Histogram-of-Oriented-Gradients (HOG) human detection algorithm implemented in the popular OpenCV toolset and the Caffe object detection system pre-trained on the ImageNet benchmark. Our tool may serve as a testing resource for the designers of intelligent human and object detection systems.« less

Advanced miniature processing handware for ATR applications

NASA Technical Reports Server (NTRS)

Chao, Tien-Hsin (Inventor); Daud, Taher (Inventor); Thakoor, Anikumar (Inventor)

2003-01-01

A Hybrid Optoelectronic Neural Object Recognition System (HONORS), is disclosed, comprising two major building blocks: (1) an advanced grayscale optical correlator (OC) and (2) a massively parallel three-dimensional neural-processor. The optical correlator, with its inherent advantages in parallel processing and shift invariance, is used for target of interest (TOI) detection and segmentation. The three-dimensional neural-processor, with its robust neural learning capability, is used for target classification and identification. The hybrid optoelectronic neural object recognition system, with its powerful combination of optical processing and neural networks, enables real-time, large frame, automatic target recognition (ATR).

Sequential and parallel image restoration: neural network implementations.

PubMed

Figueiredo, M T; Leitao, J N

1994-01-01

Sequential and parallel image restoration algorithms and their implementations on neural networks are proposed. For images degraded by linear blur and contaminated by additive white Gaussian noise, maximum a posteriori (MAP) estimation and regularization theory lead to the same high dimension convex optimization problem. The commonly adopted strategy (in using neural networks for image restoration) is to map the objective function of the optimization problem into the energy of a predefined network, taking advantage of its energy minimization properties. Departing from this approach, we propose neural implementations of iterative minimization algorithms which are first proved to converge. The developed schemes are based on modified Hopfield (1985) networks of graded elements, with both sequential and parallel updating schedules. An algorithm supported on a fully standard Hopfield network (binary elements and zero autoconnections) is also considered. Robustness with respect to finite numerical precision is studied, and examples with real images are presented.

Object-Oriented Dynamic Bayesian Network-Templates for Modelling Mechatronic Systems

DTIC Science & Technology

2002-05-04

daimlerchrysler.com Abstract are widespread. For modelling mechanical systems The object-oriented paradigma is a new but proven technol- ADAMS [31 or...hardware (sub-)systems. On the Software side thermal flow or hydraulics, see Figure 1. It also contains a the object-oriented paradigma is by now (at

Computational model for perception of objects and motions.

PubMed

Yang, WenLu; Zhang, LiQing; Ma, LiBo

2008-06-01

Perception of objects and motions in the visual scene is one of the basic problems in the visual system. There exist 'What' and 'Where' pathways in the superior visual cortex, starting from the simple cells in the primary visual cortex. The former is able to perceive objects such as forms, color, and texture, and the latter perceives 'where', for example, velocity and direction of spatial movement of objects. This paper explores brain-like computational architectures of visual information processing. We propose a visual perceptual model and computational mechanism for training the perceptual model. The computational model is a three-layer network. The first layer is the input layer which is used to receive the stimuli from natural environments. The second layer is designed for representing the internal neural information. The connections between the first layer and the second layer, called the receptive fields of neurons, are self-adaptively learned based on principle of sparse neural representation. To this end, we introduce Kullback-Leibler divergence as the measure of independence between neural responses and derive the learning algorithm based on minimizing the cost function. The proposed algorithm is applied to train the basis functions, namely receptive fields, which are localized, oriented, and bandpassed. The resultant receptive fields of neurons in the second layer have the characteristics resembling that of simple cells in the primary visual cortex. Based on these basis functions, we further construct the third layer for perception of what and where in the superior visual cortex. The proposed model is able to perceive objects and their motions with a high accuracy and strong robustness against additive noise. Computer simulation results in the final section show the feasibility of the proposed perceptual model and high efficiency of the learning algorithm.

New technologies of mining stratal minerals and their computation

NASA Astrophysics Data System (ADS)

Beysembayev, K. M.; Reshetnikova, O. S.; Nokina, Z. N.; Teliman, I. V.; Asmagambet, D. K.

2018-03-01

The paper considers the systems of flat and volumetric modeling of controlling long-wall faces for schemes with rock collapse of the immediate and main roof and smooth lowering of the remaining layers, as well as in forming a vault over the face. Stress distributions are obtained for the reference pressure zone. They are needed for recognizing the active state of the long-wall face in the feedback mode. The project of the system “support - lateral rocks” is represented by a multidimensional network base. Its connections reflect the elements of the system or rocks, workings, supports with nodes and parts. The connections reflect the logic of the operation of machines, assemblies and parts, and the types of their mechanical connections. At the nodes of the base, there are built-in systems of object-oriented programming languages. This allows combining spatial elements of the system into a simple neural network.

Superior Generalization Capability of Hardware-Learing Algorithm Developed for Self-Learning Neuron-MOS Neural Networks

NASA Astrophysics Data System (ADS)

Kondo, Shuhei; Shibata, Tadashi; Ohmi, Tadahiro

1995-02-01

We have investigated the learning performance of the hardware backpropagation (HBP) algorithm, a hardware-oriented learning algorithm developed for the self-learning architecture of neural networks constructed using neuron MOS (metal-oxide-semiconductor) transistors. The solution to finding a mirror symmetry axis in a 4×4 binary pixel array was tested by computer simulation based on the HBP algorithm. Despite the inherent restrictions imposed on the hardware-learning algorithm, HBP exhibits equivalent learning performance to that of the original backpropagation (BP) algorithm when all the pertinent parameters are optimized. Very importantly, we have found that HBP has a superior generalization capability over BP; namely, HBP exhibits higher performance in solving problems that the network has not yet learnt.

Neural-like growing networks

NASA Astrophysics Data System (ADS)

Yashchenko, Vitaliy A.

2000-03-01

On the basis of the analysis of scientific ideas reflecting the law in the structure and functioning the biological structures of a brain, and analysis and synthesis of knowledge, developed by various directions in Computer Science, also there were developed the bases of the theory of a new class neural-like growing networks, not having the analogue in world practice. In a base of neural-like growing networks the synthesis of knowledge developed by classical theories - semantic and neural of networks is. The first of them enable to form sense, as objects and connections between them in accordance with construction of the network. With thus each sense gets a separate a component of a network as top, connected to other tops. In common it quite corresponds to structure reflected in a brain, where each obvious concept is presented by certain structure and has designating symbol. Secondly, this network gets increased semantic clearness at the expense owing to formation not only connections between neural by elements, but also themselves of elements as such, i.e. here has a place not simply construction of a network by accommodation sense structures in environment neural of elements, and purely creation of most this environment, as of an equivalent of environment of memory. Thus neural-like growing networks are represented by the convenient apparatus for modeling of mechanisms of teleological thinking, as a fulfillment of certain psychophysiological of functions.

A neural network prototyping package within IRAF

NASA Technical Reports Server (NTRS)

Bazell, D.; Bankman, I.

1992-01-01

We outline our plans for incorporating a Neural Network Prototyping Package into the IRAF environment. The package we are developing will allow the user to choose between different types of networks and to specify the details of the particular architecture chosen. Neural networks consist of a highly interconnected set of simple processing units. The strengths of the connections between units are determined by weights which are adaptively set as the network 'learns'. In some cases, learning can be a separate phase of the user cycle of the network while in other cases the network learns continuously. Neural networks have been found to be very useful in pattern recognition and image processing applications. They can form very general 'decision boundaries' to differentiate between objects in pattern space and they can be used for associative recall of patterns based on partial cures and for adaptive filtering. We discuss the different architectures we plan to use and give examples of what they can do.

Electrophysiological correlates of retrieval orientation in reality monitoring.

PubMed

Rosburg, Timm; Mecklinger, Axel; Johansson, Mikael

2011-02-14

Retrieval orientation describes the modulation in the processing of retrieval cues by the nature of the targeted material in memory. Retrieval orientation is usually investigated by analyzing the cortical responses to new (unstudied) material when different memory contents are targeted. This approach avoids confounding effects of retrieval success. We investigated the neural correlates of retrieval orientation in reality monitoring with event-related potentials (ERPs) and assessed the impact of retrieval accuracy on obtained ERP measures. Thirty-two subjects studied visually presented object names that were followed either by a picture of that object (perceived condition) or by the instruction to mentally generate such a picture (imagine condition). Subsequently, subjects had to identify object names of one study condition and reject object names of the second study condition together with newly presented object names. The data analysis showed that object names were more accurately identified when they had been presented in the perceived condition. Two topographically distinct ERP effects of retrieval orientation were revealed: From 600 to 1100 ms after stimulus representation, ERPs were more positive at frontal electrode sites when object names from the imagine condition were targeted. The analysis of response-locked ERP data revealed an additional effect at posterior electrode sites, with more negative ERPs shortly after response onset when items from the imagine condition were targeted. The ERP effect at frontal electrode sites, but not at posterior electrode sites was modulated by relative memory accuracy, with stronger effects in subjects who had lower memory accuracy for items of the imagine condition. The findings are suggestive for a contribution of frontal brain areas to retrieval orientation processes in reality monitoring and indicate that neural correlates of retrieval orientation can be modulated by retrieval effort, with stronger activation of these correlates with increasing task demands. Copyright © 2010 Elsevier Inc. All rights reserved.

Intellectual system for images restoration

NASA Astrophysics Data System (ADS)

Mardare, Igor

2005-02-01

Intelligence systems on basis of artificial neural networks and associative memory allow to solve effectively problems of recognition and restoration of images. However, within analytical technologies there are no dominating approaches of deciding of intellectual problems. Choice of the best technology depends on nature of problem, features of objects, volume of represented information about the object, number of classes of objects, etc. It is required to determine opportunities, preconditions and field of application of neural networks and associative memory for decision of problem of restoration of images and to use their supplementary benefits for further development of intelligence systems.

Combined expert system/neural networks method for process fault diagnosis

DOEpatents

Reifman, Jaques; Wei, Thomas Y. C.

1995-01-01

A two-level hierarchical approach for process fault diagnosis is an operating system employs a function-oriented approach at a first level and a component characteristic-oriented approach at a second level, where the decision-making procedure is structured in order of decreasing intelligence with increasing precision. At the first level, the diagnostic method is general and has knowledge of the overall process including a wide variety of plant transients and the functional behavior of the process components. An expert system classifies malfunctions by function to narrow the diagnostic focus to a particular set of possible faulty components that could be responsible for the detected functional misbehavior of the operating system. At the second level, the diagnostic method limits its scope to component malfunctions, using more detailed knowledge of component characteristics. Trained artificial neural networks are used to further narrow the diagnosis and to uniquely identify the faulty component by classifying the abnormal condition data as a failure of one of the hypothesized components through component characteristics. Once an anomaly is detected, the hierarchical structure is used to successively narrow the diagnostic focus from a function misbehavior, i.e., a function oriented approach, until the fault can be determined, i.e., a component characteristic-oriented approach.

Combined expert system/neural networks method for process fault diagnosis

DOEpatents

Reifman, J.; Wei, T.Y.C.

1995-08-15

A two-level hierarchical approach for process fault diagnosis of an operating system employs a function-oriented approach at a first level and a component characteristic-oriented approach at a second level, where the decision-making procedure is structured in order of decreasing intelligence with increasing precision. At the first level, the diagnostic method is general and has knowledge of the overall process including a wide variety of plant transients and the functional behavior of the process components. An expert system classifies malfunctions by function to narrow the diagnostic focus to a particular set of possible faulty components that could be responsible for the detected functional misbehavior of the operating system. At the second level, the diagnostic method limits its scope to component malfunctions, using more detailed knowledge of component characteristics. Trained artificial neural networks are used to further narrow the diagnosis and to uniquely identify the faulty component by classifying the abnormal condition data as a failure of one of the hypothesized components through component characteristics. Once an anomaly is detected, the hierarchical structure is used to successively narrow the diagnostic focus from a function misbehavior, i.e., a function oriented approach, until the fault can be determined, i.e., a component characteristic-oriented approach. 9 figs.

A Novel Experimental and Analytical Approach to the Multimodal Neural Decoding of Intent During Social Interaction in Freely-behaving Human Infants.

PubMed

Cruz-Garza, Jesus G; Hernandez, Zachery R; Tse, Teresa; Caducoy, Eunice; Abibullaev, Berdakh; Contreras-Vidal, Jose L

2015-10-04

Understanding typical and atypical development remains one of the fundamental questions in developmental human neuroscience. Traditionally, experimental paradigms and analysis tools have been limited to constrained laboratory tasks and contexts due to technical limitations imposed by the available set of measuring and analysis techniques and the age of the subjects. These limitations severely limit the study of developmental neural dynamics and associated neural networks engaged in cognition, perception and action in infants performing "in action and in context". This protocol presents a novel approach to study infants and young children as they freely organize their own behavior, and its consequences in a complex, partly unpredictable and highly dynamic environment. The proposed methodology integrates synchronized high-density active scalp electroencephalography (EEG), inertial measurement units (IMUs), video recording and behavioral analysis to capture brain activity and movement non-invasively in freely-behaving infants. This setup allows for the study of neural network dynamics in the developing brain, in action and context, as these networks are recruited during goal-oriented, exploration and social interaction tasks.

Naturalistic FMRI mapping reveals superior temporal sulcus as the hub for the distributed brain network for social perception.

PubMed

Lahnakoski, Juha M; Glerean, Enrico; Salmi, Juha; Jääskeläinen, Iiro P; Sams, Mikko; Hari, Riitta; Nummenmaa, Lauri

2012-01-01

Despite the abundant data on brain networks processing static social signals, such as pictures of faces, the neural systems supporting social perception in naturalistic conditions are still poorly understood. Here we delineated brain networks subserving social perception under naturalistic conditions in 19 healthy humans who watched, during 3-T functional magnetic resonance imaging (fMRI), a set of 137 short (approximately 16 s each, total 27 min) audiovisual movie clips depicting pre-selected social signals. Two independent raters estimated how well each clip represented eight social features (faces, human bodies, biological motion, goal-oriented actions, emotion, social interaction, pain, and speech) and six filler features (places, objects, rigid motion, people not in social interaction, non-goal-oriented action, and non-human sounds) lacking social content. These ratings were used as predictors in the fMRI analysis. The posterior superior temporal sulcus (STS) responded to all social features but not to any non-social features, and the anterior STS responded to all social features except bodies and biological motion. We also found four partially segregated, extended networks for processing of specific social signals: (1) a fronto-temporal network responding to multiple social categories, (2) a fronto-parietal network preferentially activated to bodies, motion, and pain, (3) a temporo-amygdalar network responding to faces, social interaction, and speech, and (4) a fronto-insular network responding to pain, emotions, social interactions, and speech. Our results highlight the role of the pSTS in processing multiple aspects of social information, as well as the feasibility and efficiency of fMRI mapping under conditions that resemble the complexity of real life.

A Novel Optical/digital Processing System for Pattern Recognition

NASA Technical Reports Server (NTRS)

Boone, Bradley G.; Shukla, Oodaye B.

1993-01-01

This paper describes two processing algorithms that can be implemented optically: the Radon transform and angular correlation. These two algorithms can be combined in one optical processor to extract all the basic geometric and amplitude features from objects embedded in video imagery. We show that the internal amplitude structure of objects is recovered by the Radon transform, which is a well-known result, but, in addition, we show simulation results that calculate angular correlation, a simple but unique algorithm that extracts object boundaries from suitably threshold images from which length, width, area, aspect ratio, and orientation can be derived. In addition to circumventing scale and rotation distortions, these simulations indicate that the features derived from the angular correlation algorithm are relatively insensitive to tracking shifts and image noise. Some optical architecture concepts, including one based on micro-optical lenslet arrays, have been developed to implement these algorithms. Simulation test and evaluation using simple synthetic object data will be described, including results of a study that uses object boundaries (derivable from angular correlation) to classify simple objects using a neural network.

[Formula: see text]A longitudinal analysis of the attention networks in 6- to 11-year-old children.

PubMed

Lewis, Frances C; Reeve, Robert A; Johnson, Katherine A

2018-02-01

Attention is critical for everyday functioning. Posner and Petersen's model of attention describes three neural networks involved in attention control-the alerting network for arousal, the orienting network for selecting sensory input and reorienting attention, and the executive network for the regulatory control of attention. No longitudinal research has examined relative change in these networks in children. A modified version of the attention network task (ANT) was used to examine changes in the three attention networks, three times over 12 months, in 114 6-, 8- and 10-year-olds. Findings showed that the alerting network continued to develop over this period, the orienting network had stabilized by 6 years, and the conflict network had largely stabilized by 7 years. The reorienting of attention was also assessed using invalid cues, which showed a similar developmental trajectory to the orienting attention network and had stabilized by 6 years. The results confirm that age 6 to 7 years is a critical period in the development of attention, in particular executive attention. The largest improvement over the evaluation period was between 6 and 7 years; however, subtle changes were found in attention beyond 8 years of age.

Orientation Encoding and Viewpoint Invariance in Face Recognition: Inferring Neural Properties from Large-Scale Signals.

PubMed

Ramírez, Fernando M

2018-05-01

Viewpoint-invariant face recognition is thought to be subserved by a distributed network of occipitotemporal face-selective areas that, except for the human anterior temporal lobe, have been shown to also contain face-orientation information. This review begins by highlighting the importance of bilateral symmetry for viewpoint-invariant recognition and face-orientation perception. Then, monkey electrophysiological evidence is surveyed describing key tuning properties of face-selective neurons-including neurons bimodally tuned to mirror-symmetric face-views-followed by studies combining functional magnetic resonance imaging (fMRI) and multivariate pattern analyses to probe the representation of face-orientation and identity information in humans. Altogether, neuroimaging studies suggest that face-identity is gradually disentangled from face-orientation information along the ventral visual processing stream. The evidence seems to diverge, however, regarding the prevalent form of tuning of neural populations in human face-selective areas. In this context, caveats possibly leading to erroneous inferences regarding mirror-symmetric coding are exposed, including the need to distinguish angular from Euclidean distances when interpreting multivariate pattern analyses. On this basis, this review argues that evidence from the fusiform face area is best explained by a view-sensitive code reflecting head angular disparity, consistent with a role of this area in face-orientation perception. Finally, the importance is stressed of explicit models relating neural properties to large-scale signals.

Early Visual Cortex Dynamics during Top-Down Modulated Shifts of Feature-Selective Attention.

PubMed

Müller, Matthias M; Trautmann, Mireille; Keitel, Christian

2016-04-01

Shifting attention from one color to another color or from color to another feature dimension such as shape or orientation is imperative when searching for a certain object in a cluttered scene. Most attention models that emphasize feature-based selection implicitly assume that all shifts in feature-selective attention underlie identical temporal dynamics. Here, we recorded time courses of behavioral data and steady-state visual evoked potentials (SSVEPs), an objective electrophysiological measure of neural dynamics in early visual cortex to investigate temporal dynamics when participants shifted attention from color or orientation toward color or orientation, respectively. SSVEPs were elicited by four random dot kinematograms that flickered at different frequencies. Each random dot kinematogram was composed of dashes that uniquely combined two features from the dimensions color (red or blue) and orientation (slash or backslash). Participants were cued to attend to one feature (such as color or orientation) and respond to coherent motion targets of the to-be-attended feature. We found that shifts toward color occurred earlier after the shifting cue compared with shifts toward orientation, regardless of the original feature (i.e., color or orientation). This was paralleled in SSVEP amplitude modulations as well as in the time course of behavioral data. Overall, our results suggest different neural dynamics during shifts of attention from color and orientation and the respective shifting destinations, namely, either toward color or toward orientation.

Deep neural networks for modeling visual perceptual learning.

PubMed

Wenliang, Li; Seitz, Aaron R

2018-05-23

Understanding visual perceptual learning (VPL) has become increasingly more challenging as new phenomena are discovered with novel stimuli and training paradigms. While existing models aid our knowledge of critical aspects of VPL, the connections shown by these models between behavioral learning and plasticity across different brain areas are typically superficial. Most models explain VPL as readout from simple perceptual representations to decision areas and are not easily adaptable to explain new findings. Here, we show that a well-known instance of deep neural network (DNN), while not designed specifically for VPL, provides a computational model of VPL with enough complexity to be studied at many levels of analyses. After learning a Gabor orientation discrimination task, the DNN model reproduced key behavioral results, including increasing specificity with higher task precision, and also suggested that learning precise discriminations could asymmetrically transfer to coarse discriminations when the stimulus conditions varied. In line with the behavioral findings, the distribution of plasticity moved towards lower layers when task precision increased, and this distribution was also modulated by tasks with different stimulus types. Furthermore, learning in the network units demonstrated close resemblance to extant electrophysiological recordings in monkey visual areas. Altogether, the DNN fulfilled predictions of existing theories regarding specificity and plasticity, and reproduced findings of tuning changes in neurons of the primate visual areas. Although the comparisons were mostly qualitative, the DNN provides a new method of studying VPL and can serve as a testbed for theories and assist in generating predictions for physiological investigations. SIGNIFICANCE STATEMENT Visual perceptual learning (VPL) has been found to cause changes at multiple stages of the visual hierarchy. We found that training a deep neural network (DNN) on an orientation discrimination task produced similar behavioral and physiological patterns found in human and monkey experiments. Unlike existing VPL models, the DNN was pre-trained on natural images to reach high performance in object recognition but was not designed specifically for VPL, and yet it fulfilled predictions of existing theories regarding specificity and plasticity, and reproduced findings of tuning changes in neurons of the primate visual areas. When used with care, this unbiased and deep-hierarchical model can provide new ways of studying VPL from behavior to physiology. Copyright © 2018 the authors.

Recurrent Artificial Neural Networks and Finite State Natural Language Processing.

ERIC Educational Resources Information Center

Moisl, Hermann

It is argued that pessimistic assessments of the adequacy of artificial neural networks (ANNs) for natural language processing (NLP) on the grounds that they have a finite state architecture are unjustified, and that their adequacy in this regard is an empirical issue. First, arguments that counter standard objections to finite state NLP on the…

Spin switches for compact implementation of neuron and synapse

NASA Astrophysics Data System (ADS)

Quang Diep, Vinh; Sutton, Brian; Behin-Aein, Behtash; Datta, Supriyo

2014-06-01

Nanomagnets driven by spin currents provide a natural implementation for a neuron and a synapse: currents allow convenient summation of multiple inputs, while the magnet provides the threshold function. The objective of this paper is to explore the possibility of a hardware neural network implementation using a spin switch (SS) as its basic building block. SS is a recently proposed device based on established technology with a transistor-like gain and input-output isolation. This allows neural networks to be constructed with purely passive interconnections without intervening clocks or amplifiers. The weights for the neural network are conveniently adjusted through analog voltages that can be stored in a non-volatile manner in an underlying CMOS layer using a floating gate low dropout voltage regulator. The operation of a multi-layer SS neural network designed for character recognition is demonstrated using a standard simulation model based on coupled Landau-Lifshitz-Gilbert equations, one for each magnet in the network.

Behavioral and neural correlates of disrupted orienting attention in posttraumatic stress disorder.

PubMed

Russman Block, Stefanie; King, Anthony P; Sripada, Rebecca K; Weissman, Daniel H; Welsh, Robert; Liberzon, Israel

2017-04-01

Prior work has revealed that posttraumatic stress disorder (PTSD) is associated with altered (a) attentional performance and (b) resting-state functional connectivity (rsFC) in brain networks linked to attention. Here, we sought to characterize and link these behavioral and brain-based alterations in the context of Posner and Peterson's tripartite model of attention. Male military veterans with PTSD (N = 49; all deployed to Iraq or Afghanistan) and healthy age-and-gender-matched community controls (N = 26) completed the Attention Network Task. A subset of these individuals (36 PTSD and 21 controls) also underwent functional magnetic resonance imaging (fMRI) to assess rsFC. The behavioral measures revealed that the PTSD group was impaired at disengaging spatial attention, relative to the control group. FMRI measures further revealed that, relative to the control group, the PTSD group exhibited greater rsFC between the salience network and (a) the default mode network, (b) the dorsal attention network, and (c) the ventral attention network. Moreover, problems with disengaging spatial attention increased the rsFC between the networks above in the control group, but not in the PTSD group. The present findings link PTSD to both altered orienting of spatial attention and altered relationships between spatial orienting and functional connectivity involving the salience network. Interventions that target orienting and disengaging spatial attention may be a new avenue for PTSD research.

Method for neural network control of motion using real-time environmental feedback

NASA Technical Reports Server (NTRS)

Buckley, Theresa M. (Inventor)

1997-01-01

A method of motion control for robotics and other automatically controlled machinery using a neural network controller with real-time environmental feedback. The method is illustrated with a two-finger robotic hand having proximity sensors and force sensors that provide environmental feedback signals. The neural network controller is taught to control the robotic hand through training sets using back- propagation methods. The training sets are created by recording the control signals and the feedback signal as the robotic hand or a simulation of the robotic hand is moved through a representative grasping motion. The data recorded is divided into discrete increments of time and the feedback data is shifted out of phase with the control signal data so that the feedback signal data lag one time increment behind the control signal data. The modified data is presented to the neural network controller as a training set. The time lag introduced into the data allows the neural network controller to account for the temporal component of the robotic motion. Thus trained, the neural network controlled robotic hand is able to grasp a wide variety of different objects by generalizing from the training sets.

Artificial neural network classification using a minimal training set - Comparison to conventional supervised classification

NASA Technical Reports Server (NTRS)

Hepner, George F.; Logan, Thomas; Ritter, Niles; Bryant, Nevin

1990-01-01

Recent research has shown an artificial neural network (ANN) to be capable of pattern recognition and the classification of image data. This paper examines the potential for the application of neural network computing to satellite image processing. A second objective is to provide a preliminary comparison and ANN classification. An artificial neural network can be trained to do land-cover classification of satellite imagery using selected sites representative of each class in a manner similar to conventional supervised classification. One of the major problems associated with recognition and classifications of pattern from remotely sensed data is the time and cost of developing a set of training sites. This reseach compares the use of an ANN back propagation classification procedure with a conventional supervised maximum likelihood classification procedure using a minimal training set. When using a minimal training set, the neural network is able to provide a land-cover classification superior to the classification derived from the conventional classification procedure. This research is the foundation for developing application parameters for further prototyping of software and hardware implementations for artificial neural networks in satellite image and geographic information processing.

View-tolerant face recognition and Hebbian learning imply mirror-symmetric neural tuning to head orientation

PubMed Central

Leibo, Joel Z.; Liao, Qianli; Freiwald, Winrich A.; Anselmi, Fabio; Poggio, Tomaso

2017-01-01

SUMMARY The primate brain contains a hierarchy of visual areas, dubbed the ventral stream, which rapidly computes object representations that are both specific for object identity and robust against identity-preserving transformations like depth-rotations [1, 2]. Current computational models of object recognition, including recent deep learning networks, generate these properties through a hierarchy of alternating selectivity-increasing filtering and tolerance-increasing pooling operations, similar to simple-complex cells operations [3, 4, 5, 6]. Here we prove that a class of hierarchical architectures and a broad set of biologically plausible learning rules generate approximate invariance to identity-preserving transformations at the top level of the processing hierarchy. However, all past models tested failed to reproduce the most salient property of an intermediate representation of a three-level face-processing hierarchy in the brain: mirror-symmetric tuning to head orientation [7]. Here we demonstrate that one specific biologically-plausible Hebb-type learning rule generates mirror-symmetric tuning to bilaterally symmetric stimuli like faces at intermediate levels of the architecture and show why it does so. Thus the tuning properties of individual cells inside the visual stream appear to result from group properties of the stimuli they encode and to reflect the learning rules that sculpted the information-processing system within which they reside. PMID:27916522

Position estimation and driving of an autonomous vehicle by monocular vision

NASA Astrophysics Data System (ADS)

Hanan, Jay C.; Kayathi, Pavan; Hughlett, Casey L.

2007-04-01

Automatic adaptive tracking in real-time for target recognition provided autonomous control of a scale model electric truck. The two-wheel drive truck was modified as an autonomous rover test-bed for vision based guidance and navigation. Methods were implemented to monitor tracking error and ensure a safe, accurate arrival at the intended science target. Some methods are situation independent relying only on the confidence error of the target recognition algorithm. Other methods take advantage of the scenario of combined motion and tracking to filter out anomalies. In either case, only a single calibrated camera was needed for position estimation. Results from real-time autonomous driving tests on the JPL simulated Mars yard are presented. Recognition error was often situation dependent. For the rover case, the background was in motion and may be characterized to provide visual cues on rover travel such as rate, pitch, roll, and distance to objects of interest or hazards. Objects in the scene may be used as landmarks, or waypoints, for such estimations. As objects are approached, their scale increases and their orientation may change. In addition, particularly on rough terrain, these orientation and scale changes may be unpredictable. Feature extraction combined with the neural network algorithm was successful in providing visual odometry in the simulated Mars environment.

Oscillatory network with self-organized dynamical connections for synchronization-based image segmentation.

PubMed

Kuzmina, Margarita; Manykin, Eduard; Surina, Irina

2004-01-01

An oscillatory network of columnar architecture located in 3D spatial lattice was recently designed by the authors as oscillatory model of the brain visual cortex. Single network oscillator is a relaxational neural oscillator with internal dynamics tunable by visual image characteristics - local brightness and elementary bar orientation. It is able to demonstrate either activity state (stable undamped oscillations) or "silence" (quickly damped oscillations). Self-organized nonlocal dynamical connections of oscillators depend on oscillator activity levels and orientations of cortical receptive fields. Network performance consists in transfer into a state of clusterized synchronization. At current stage grey-level image segmentation tasks are carried out by 2D oscillatory network, obtained as a limit version of the source model. Due to supplemented network coupling strength control the 2D reduced network provides synchronization-based image segmentation. New results on segmentation of brightness and texture images presented in the paper demonstrate accurate network performance and informative visualization of segmentation results, inherent in the model.

The neural network classification of false killer whale (Pseudorca crassidens) vocalizations.

PubMed

Murray, S O; Mercado, E; Roitblat, H L

1998-12-01

This study reports the use of unsupervised, self-organizing neural network to categorize the repertoire of false killer whale vocalizations. Self-organizing networks are capable of detecting patterns in their input and partitioning those patterns into categories without requiring that the number or types of categories be predefined. The inputs for the neural networks were two-dimensional characterization of false killer whale vocalization, where each vocalization was characterized by a sequence of short-time measurements of duty cycle and peak frequency. The first neural network used competitive learning, where units in a competitive layer distributed themselves to recognize frequently presented input vectors. This network resulted in classes representing typical patterns in the vocalizations. The second network was a Kohonen feature map which organized the outputs topologically, providing a graphical organization of pattern relationships. The networks performed well as measured by (1) the average correlation between the input vectors and the weight vectors for each category, and (2) the ability of the networks to classify novel vocalizations. The techniques used in this study could easily be applied to other species and facilitate the development of objective, comprehensive repertoire models.

The Predictive Brain State: Asynchrony in Disorders of Attention?

PubMed Central

Ghajar, Jamshid; Ivry, Richard B.

2015-01-01

It is postulated that a key function of attention in goal-oriented behavior is to reduce performance variability by generating anticipatory neural activity that can be synchronized with expected sensory information. A network encompassing the prefrontal cortex, parietal lobe, and cerebellum may be critical in the maintenance and timing of such predictive neural activity. Dysfunction of this temporal process may constitute a fundamental defect in attention, causing working memory problems, distractibility, and decreased awareness. PMID:19074688

Convolutional Neural Network-Based Robot Navigation Using Uncalibrated Spherical Images †

PubMed Central

Ran, Lingyan; Zhang, Yanning; Zhang, Qilin; Yang, Tao

2017-01-01

Vision-based mobile robot navigation is a vibrant area of research with numerous algorithms having been developed, the vast majority of which either belong to the scene-oriented simultaneous localization and mapping (SLAM) or fall into the category of robot-oriented lane-detection/trajectory tracking. These methods suffer from high computational cost and require stringent labelling and calibration efforts. To address these challenges, this paper proposes a lightweight robot navigation framework based purely on uncalibrated spherical images. To simplify the orientation estimation, path prediction and improve computational efficiency, the navigation problem is decomposed into a series of classification tasks. To mitigate the adverse effects of insufficient negative samples in the “navigation via classification” task, we introduce the spherical camera for scene capturing, which enables 360° fisheye panorama as training samples and generation of sufficient positive and negative heading directions. The classification is implemented as an end-to-end Convolutional Neural Network (CNN), trained on our proposed Spherical-Navi image dataset, whose category labels can be efficiently collected. This CNN is capable of predicting potential path directions with high confidence levels based on a single, uncalibrated spherical image. Experimental results demonstrate that the proposed framework outperforms competing ones in realistic applications. PMID:28604624

Convolutional Neural Network-Based Robot Navigation Using Uncalibrated Spherical Images.

PubMed

Ran, Lingyan; Zhang, Yanning; Zhang, Qilin; Yang, Tao

2017-06-12

Vision-based mobile robot navigation is a vibrant area of research with numerous algorithms having been developed, the vast majority of which either belong to the scene-oriented simultaneous localization and mapping (SLAM) or fall into the category of robot-oriented lane-detection/trajectory tracking. These methods suffer from high computational cost and require stringent labelling and calibration efforts. To address these challenges, this paper proposes a lightweight robot navigation framework based purely on uncalibrated spherical images. To simplify the orientation estimation, path prediction and improve computational efficiency, the navigation problem is decomposed into a series of classification tasks. To mitigate the adverse effects of insufficient negative samples in the "navigation via classification" task, we introduce the spherical camera for scene capturing, which enables 360° fisheye panorama as training samples and generation of sufficient positive and negative heading directions. The classification is implemented as an end-to-end Convolutional Neural Network (CNN), trained on our proposed Spherical-Navi image dataset, whose category labels can be efficiently collected. This CNN is capable of predicting potential path directions with high confidence levels based on a single, uncalibrated spherical image. Experimental results demonstrate that the proposed framework outperforms competing ones in realistic applications.

Neural control of magnetic suspension systems

NASA Technical Reports Server (NTRS)

Gray, W. Steven

1993-01-01

The purpose of this research program is to design, build and test (in cooperation with NASA personnel from the NASA Langley Research Center) neural controllers for two different small air-gap magnetic suspension systems. The general objective of the program is to study neural network architectures for the purpose of control in an experimental setting and to demonstrate the feasibility of the concept. The specific objectives of the research program are: (1) to demonstrate through simulation and experimentation the feasibility of using neural controllers to stabilize a nonlinear magnetic suspension system; (2) to investigate through simulation and experimentation the performance of neural controllers designs under various types of parametric and nonparametric uncertainty; (3) to investigate through simulation and experimentation various types of neural architectures for real-time control with respect to performance and complexity; and (4) to benchmark in an experimental setting the performance of neural controllers against other types of existing linear and nonlinear compensator designs. To date, the first one-dimensional, small air-gap magnetic suspension system has been built, tested and delivered to the NASA Langley Research Center. The device is currently being stabilized with a digital linear phase-lead controller. The neural controller hardware is under construction. Two different neural network paradigms are under consideration, one based on hidden layer feedforward networks trained via back propagation and one based on using Gaussian radial basis functions trained by analytical methods related to stability conditions. Some advanced nonlinear control algorithms using feedback linearization and sliding mode control are in simulation studies.

A Neural Network-Based Gait Phase Classification Method Using Sensors Equipped on Lower Limb Exoskeleton Robots

PubMed Central

Jung, Jun-Young; Heo, Wonho; Yang, Hyundae; Park, Hyunsub

2015-01-01

An exact classification of different gait phases is essential to enable the control of exoskeleton robots and detect the intentions of users. We propose a gait phase classification method based on neural networks using sensor signals from lower limb exoskeleton robots. In such robots, foot sensors with force sensing registers are commonly used to classify gait phases. We describe classifiers that use the orientation of each lower limb segment and the angular velocities of the joints to output the current gait phase. Experiments to obtain the input signals and desired outputs for the learning and validation process are conducted, and two neural network methods (a multilayer perceptron and nonlinear autoregressive with external inputs (NARX)) are used to develop an optimal classifier. Offline and online evaluations using four criteria are used to compare the performance of the classifiers. The proposed NARX-based method exhibits sufficiently good performance to replace foot sensors as a means of classifying gait phases. PMID:26528986

A Neural Network-Based Gait Phase Classification Method Using Sensors Equipped on Lower Limb Exoskeleton Robots.

PubMed

Jung, Jun-Young; Heo, Wonho; Yang, Hyundae; Park, Hyunsub

2015-10-30

An exact classification of different gait phases is essential to enable the control of exoskeleton robots and detect the intentions of users. We propose a gait phase classification method based on neural networks using sensor signals from lower limb exoskeleton robots. In such robots, foot sensors with force sensing registers are commonly used to classify gait phases. We describe classifiers that use the orientation of each lower limb segment and the angular velocities of the joints to output the current gait phase. Experiments to obtain the input signals and desired outputs for the learning and validation process are conducted, and two neural network methods (a multilayer perceptron and nonlinear autoregressive with external inputs (NARX)) are used to develop an optimal classifier. Offline and online evaluations using four criteria are used to compare the performance of the classifiers. The proposed NARX-based method exhibits sufficiently good performance to replace foot sensors as a means of classifying gait phases.

Self organizing map neural networks approach for lithologic interpretation of nuclear and electrical well logs in basaltic environment, Southern Syria.

PubMed

Asfahani, J; Ahmad, Z; Ghani, B Abdul

2018-07-01

An approach based on self organizing map (SOM) artificial neural networks is proposed herewith oriented towards interpreting nuclear and electrical well logging data. The well logging measurements of Kodana well in Southern Syria have been interpreted by applying the proposed approach. Lithological cross-section model of the basaltic environment has been derived and four different kinds of basalt have been consequently distinguished. The four basalts are hard massive basalt, hard basalt, pyroclastic basalt and the alteration basalt products- clay. The results obtained by SOM artificial neural networks are in a good agreement with the previous published results obtained by other different techniques. The SOM approach is practiced successfully in the case study of the Kodana well logging data, and can be therefore recommended as a suitable and effective approach for handling huge well logging data with higher number of variables required for lithological discrimination purposes. Copyright © 2018 Elsevier Ltd. All rights reserved.

Multi-modality image fusion based on enhanced fuzzy radial basis function neural networks.

PubMed

Chao, Zhen; Kim, Dohyeon; Kim, Hee-Joung

2018-04-01

In clinical applications, single modality images do not provide sufficient diagnostic information. Therefore, it is necessary to combine the advantages or complementarities of different modalities of images. Recently, neural network technique was applied to medical image fusion by many researchers, but there are still many deficiencies. In this study, we propose a novel fusion method to combine multi-modality medical images based on the enhanced fuzzy radial basis function neural network (Fuzzy-RBFNN), which includes five layers: input, fuzzy partition, front combination, inference, and output. Moreover, we propose a hybrid of the gravitational search algorithm (GSA) and error back propagation algorithm (EBPA) to train the network to update the parameters of the network. Two different patterns of images are used as inputs of the neural network, and the output is the fused image. A comparison with the conventional fusion methods and another neural network method through subjective observation and objective evaluation indexes reveals that the proposed method effectively synthesized the information of input images and achieved better results. Meanwhile, we also trained the network by using the EBPA and GSA, individually. The results reveal that the EBPGSA not only outperformed both EBPA and GSA, but also trained the neural network more accurately by analyzing the same evaluation indexes. Copyright © 2018 Associazione Italiana di Fisica Medica. Published by Elsevier Ltd. All rights reserved.

Cerebellar neurocontroller project, for aerospace applications, in a civilian neurocomputing initiative in the 'decade of the brain'

NASA Technical Reports Server (NTRS)

Pellionisz, Andras J.; Jorgensen, Charles C.; Werbos, Paul J.

1992-01-01

A key question is how to utilize civilian government agencies along with an industrial consortium to successfully complement the so far primarily defense-oriented neural network research. Civilian artificial neural system projects, such as artificial cerebellar neurocontrollers aimed at duplicating nature's existing neural network solutions for adaptive sensorimotor coordination, are proposed by such a synthesis. The cerebellum provides an intelligent interface between higher possibly symbolic levels of human intelligence and repetitious demands of real world conventional controllers. The generation of such intelligent interfaces could be crucial to the economic feasibility of the human settlement of space and an improvement in telerobotics techniques to permit the cost-effective exploitation of nonterrestrial materials and planetary exploration and monitoring. The authors propose a scientific framework within which such interagency activities could effectively cooperate.

The use of neural networks and texture analysis for rapid objective selection of regions of interest in cytoskeletal images.

PubMed

Derkacs, Amanda D Felder; Ward, Samuel R; Lieber, Richard L

2012-02-01

Understanding cytoskeletal dynamics in living tissue is prerequisite to understanding mechanisms of injury, mechanotransduction, and mechanical signaling. Real-time visualization is now possible using transfection with plasmids that encode fluorescent cytoskeletal proteins. Using this approach with the muscle-specific intermediate filament protein desmin, we found that a green fluorescent protein-desmin chimeric protein was unevenly distributed throughout the muscle fiber, resulting in some image areas that were saturated as well as others that lacked any signal. Our goal was to analyze the muscle fiber cytoskeletal network quantitatively in an unbiased fashion. To objectively select areas of the muscle fiber that are suitable for analysis, we devised a method that provides objective classification of regions of images of striated cytoskeletal structures into "usable" and "unusable" categories. This method consists of a combination of spatial analysis of the image using Fourier methods along with a boosted neural network that "decides" on the quality of the image based on previous training. We trained the neural network using the expert opinion of three scientists familiar with these types of images. We found that this method was over 300 times faster than manual classification and that it permitted objective and accurate classification of image regions.

Selective attention on representations in working memory: cognitive and neural mechanisms.

PubMed

Ku, Yixuan

2018-01-01

Selective attention and working memory are inter-dependent core cognitive functions. It is critical to allocate attention on selected targets during the capacity-limited working memory processes to fulfill the goal-directed behavior. The trends of research on both topics are increasing exponentially in recent years, and it is considered that selective attention and working memory share similar underlying neural mechanisms. Different types of attention orientation in working memory are introduced by distinctive cues, and the means using retrospective cues are strengthened currently as it is manipulating the representation in memory, instead of the perceptual representation. The cognitive and neural mechanisms of the retro-cue effects are further reviewed, as well as the potential molecular mechanism. The frontal-parietal network that is involved in both attention and working memory is also the neural candidate for attention orientation during working memory. Neural oscillations in the gamma and alpha/beta oscillations may respectively be employed for the feedforward and feedback information transfer between the sensory cortices and the association cortices. Dopamine and serotonin systems might interact with each other subserving the communication between memory and attention. In conclusion, representations which attention shifts towards are strengthened, while representations which attention moves away from are degraded. Studies on attention orientation during working memory indicates the flexibility of the processes of working memory, and the beneficial way that overcome the limited capacity of working memory.

Selective attention on representations in working memory: cognitive and neural mechanisms

PubMed Central

2018-01-01

Selective attention and working memory are inter-dependent core cognitive functions. It is critical to allocate attention on selected targets during the capacity-limited working memory processes to fulfill the goal-directed behavior. The trends of research on both topics are increasing exponentially in recent years, and it is considered that selective attention and working memory share similar underlying neural mechanisms. Different types of attention orientation in working memory are introduced by distinctive cues, and the means using retrospective cues are strengthened currently as it is manipulating the representation in memory, instead of the perceptual representation. The cognitive and neural mechanisms of the retro-cue effects are further reviewed, as well as the potential molecular mechanism. The frontal-parietal network that is involved in both attention and working memory is also the neural candidate for attention orientation during working memory. Neural oscillations in the gamma and alpha/beta oscillations may respectively be employed for the feedforward and feedback information transfer between the sensory cortices and the association cortices. Dopamine and serotonin systems might interact with each other subserving the communication between memory and attention. In conclusion, representations which attention shifts towards are strengthened, while representations which attention moves away from are degraded. Studies on attention orientation during working memory indicates the flexibility of the processes of working memory, and the beneficial way that overcome the limited capacity of working memory. PMID:29629245

Deep Neural Networks as a Computational Model for Human Shape Sensitivity

PubMed Central

Op de Beeck, Hans P.

2016-01-01

Theories of object recognition agree that shape is of primordial importance, but there is no consensus about how shape might be represented, and so far attempts to implement a model of shape perception that would work with realistic stimuli have largely failed. Recent studies suggest that state-of-the-art convolutional ‘deep’ neural networks (DNNs) capture important aspects of human object perception. We hypothesized that these successes might be partially related to a human-like representation of object shape. Here we demonstrate that sensitivity for shape features, characteristic to human and primate vision, emerges in DNNs when trained for generic object recognition from natural photographs. We show that these models explain human shape judgments for several benchmark behavioral and neural stimulus sets on which earlier models mostly failed. In particular, although never explicitly trained for such stimuli, DNNs develop acute sensitivity to minute variations in shape and to non-accidental properties that have long been implicated to form the basis for object recognition. Even more strikingly, when tested with a challenging stimulus set in which shape and category membership are dissociated, the most complex model architectures capture human shape sensitivity as well as some aspects of the category structure that emerges from human judgments. As a whole, these results indicate that convolutional neural networks not only learn physically correct representations of object categories but also develop perceptually accurate representational spaces of shapes. An even more complete model of human object representations might be in sight by training deep architectures for multiple tasks, which is so characteristic in human development. PMID:27124699

Research on Environmental Adjustment of Cloud Ranch Based on BP Neural Network PID Control

NASA Astrophysics Data System (ADS)

Ren, Jinzhi; Xiang, Wei; Zhao, Lin; Wu, Jianbo; Huang, Lianzhen; Tu, Qinggang; Zhao, Heming

2018-01-01

In order to make the intelligent ranch management mode replace the traditional artificial one gradually, this paper proposes a pasture environment control system based on cloud server, and puts forward the PID control algorithm based on BP neural network to control temperature and humidity better in the pasture environment. First, to model the temperature and humidity (controlled object) of the pasture, we can get the transfer function. Then the traditional PID control algorithm and the PID one based on BP neural network are applied to the transfer function. The obtained step tracking curves can be seen that the PID controller based on BP neural network has obvious superiority in adjusting time and error, etc. This algorithm, calculating reasonable control parameters of the temperature and humidity to control environment, can be better used in the cloud service platform.

Architecture for networked electronic patient record systems.

PubMed

Takeda, H; Matsumura, Y; Kuwata, S; Nakano, H; Sakamoto, N; Yamamoto, R

2000-11-01

There have been two major approaches to the development of networked electronic patient record (EPR) architecture. One uses object-oriented methodologies for constructing the model, which include the GEHR project, Synapses, HL7 RIM and so on. The second approach uses document-oriented methodologies, as applied in examples of HL7 PRA. It is practically beneficial to take the advantages of both approaches and to add solution technologies for network security such as PKI. In recognition of the similarity with electronic commerce, a certificate authority as a trusted third party will be organised for establishing networked EPR system. This paper describes a Japanese functional model that has been developed, and proposes a document-object-oriented architecture, which is-compared with other existing models.

The Effect of Happiness and Sadness on Alerting, Orienting, and Executive Attention

ERIC Educational Resources Information Center

Finucane, Anne M.; Whiteman, Martha C.; Power, Mick J.

2010-01-01

Objective: According to the attention network approach, attention is best understood in terms of three functionally and neuroanatomically distinct networks--alerting, orienting, and executive attention. An important question is whether the experience of emotion differentially influences the efficiency of these networks. Method: This study examines…

Proceedings of the Seventh International Symposium on Methodologies for Intelligent Systems (Poster Session)

DOE Office of Scientific and Technical Information (OSTI.GOV)

Harber, K.S.

1993-05-01

This report contains the following papers: Implications in vivid logic; a self-learning bayesian expert system; a natural language generation system for a heterogeneous distributed database system; competence-switching'' managed by intelligent systems; strategy acquisition by an artificial neural network: Experiments in learning to play a stochastic game; viewpoints and selective inheritance in object-oriented modeling; multivariate discretization of continuous attributes for machine learning; utilization of the case-based reasoning method to resolve dynamic problems; formalization of an ontology of ceramic science in CLASSIC; linguistic tools for intelligent systems; an application of rough sets in knowledge synthesis; and a relational model for imprecise queries.more » These papers have been indexed separately.« less

Proceedings of the Seventh International Symposium on Methodologies for Intelligent Systems (Poster Session)

DOE Office of Scientific and Technical Information (OSTI.GOV)

Harber, K.S.

1993-05-01

This report contains the following papers: Implications in vivid logic; a self-learning Bayesian Expert System; a natural language generation system for a heterogeneous distributed database system; ``competence-switching`` managed by intelligent systems; strategy acquisition by an artificial neural network: Experiments in learning to play a stochastic game; viewpoints and selective inheritance in object-oriented modeling; multivariate discretization of continuous attributes for machine learning; utilization of the case-based reasoning method to resolve dynamic problems; formalization of an ontology of ceramic science in CLASSIC; linguistic tools for intelligent systems; an application of rough sets in knowledge synthesis; and a relational model for imprecise queries.more » These papers have been indexed separately.« less

Neuro-fuzzy controller to navigate an unmanned vehicle.

PubMed

Selma, Boumediene; Chouraqui, Samira

2013-12-01

A Neuro-fuzzy control method for an Unmanned Vehicle (UV) simulation is described. The objective is guiding an autonomous vehicle to a desired destination along a desired path in an environment characterized by a terrain and a set of distinct objects, such as obstacles like donkey traffic lights and cars circulating in the trajectory. The autonomous navigate ability and road following precision are mainly influenced by its control strategy and real-time control performance. Fuzzy Logic Controller can very well describe the desired system behavior with simple "if-then" relations owing the designer to derive "if-then" rules manually by trial and error. On the other hand, Neural Networks perform function approximation of a system but cannot interpret the solution obtained neither check if its solution is plausible. The two approaches are complementary. Combining them, Neural Networks will allow learning capability while Fuzzy-Logic will bring knowledge representation (Neuro-Fuzzy). In this paper, an artificial neural network fuzzy inference system (ANFIS) controller is described and implemented to navigate the autonomous vehicle. Results show several improvements in the control system adjusted by neuro-fuzzy techniques in comparison to the previous methods like Artificial Neural Network (ANN).

Review on Neural Correlates of Emotion Regulation and Music: Implications for Emotion Dysregulation

PubMed Central

Hou, Jiancheng; Song, Bei; Chen, Andrew C. N.; Sun, Changan; Zhou, Jiaxian; Zhu, Haidong; Beauchaine, Theodore P.

2017-01-01

Previous studies have examined the neural correlates of emotion regulation and the neural changes that are evoked by music exposure. However, the link between music and emotion regulation is poorly understood. The objectives of this review are to (1) synthesize what is known about the neural correlates of emotion regulation and music-evoked emotions, and (2) consider the possibility of therapeutic effects of music on emotion dysregulation. Music-evoked emotions can modulate activities in both cortical and subcortical systems, and across cortical-subcortical networks. Functions within these networks are integral to generation and regulation of emotions. Since dysfunction in these networks are observed in numerous psychiatric disorders, a better understanding of neural correlates of music exposure may lead to more systematic and effective use of music therapy in emotion dysregulation. PMID:28421017

Magnocellular pathway for rotation invariant Neocognitron.

PubMed

Ting, C H

1993-03-01

In the mammalian visual system, magnocellular pathway and parvocellular pathway cooperatively process visual information in parallel. The magnocellular pathway is more global and less particular about the details while the parvocellular pathway recognizes objects based on the local features. In many aspects, Neocognitron may be regarded as the artificial analogue of the parvocellular pathway. It is interesting then to model the magnocellular pathway. In order to achieve "rotation invariance" for Neocognitron, we propose a neural network model after the magnocellular pathway and expand its roles to include surmising the orientation of the input pattern prior to recognition. With the incorporation of the magnocellular pathway, a basic shift in the original paradigm has taken place. A pattern is now said to be recognized when and only when one of the winners of the magnocellular pathway is validified by the parvocellular pathway. We have implemented the magnocellular pathway coupled with Neocognitron parallel on transputers; our simulation programme is now able to recognize numerals in arbitrary orientation.

Inversion of quasi-3D DC resistivity imaging data using artificial neural networks

NASA Astrophysics Data System (ADS)

Neyamadpour, Ahmad; Wan Abdullah, W. A. T.; Taib, Samsudin

2010-02-01

The objective of this paper is to investigate the applicability of artificial neural networks in inverting quasi-3D DC resistivity imaging data. An electrical resistivity imaging survey was carried out along seven parallel lines using a dipole-dipole array to confirm the validation of the results of an inversion using an artificial neural network technique. The model used to produce synthetic data to train the artificial neural network was a homogeneous medium of 100Ωm resistivity with an embedded anomalous body of 1000Ωm resistivity. The network was trained using 21 datasets (comprising 12159 data points) and tested on another 11 synthetic datasets (comprising 6369 data points) and on real field data. Another 24 test datasets (comprising 13896 data points) consisting of different resistivities for the background and the anomalous bodies were used in order to test the interpolation and extrapolation of network properties. Different learning paradigms were tried in the training process of the neural network, with the resilient propagation paradigm being the most efficient. The number of nodes, hidden layers, and efficient values for learning rate and momentum coefficient have been studied. Although a significant correlation between results of the neural network and the conventional robust inversion technique was found, the ANN results show more details of the subsurface structure, and the RMS misfits for the results of the neural network are less than seen with conventional methods. The interpreted results show that the trained network was able to invert quasi-3D electrical resistivity imaging data obtained by dipole-dipole configuration both rapidly and accurately.

Genetic learning in rule-based and neural systems

NASA Technical Reports Server (NTRS)

Smith, Robert E.

1993-01-01

The design of neural networks and fuzzy systems can involve complex, nonlinear, and ill-conditioned optimization problems. Often, traditional optimization schemes are inadequate or inapplicable for such tasks. Genetic Algorithms (GA's) are a class of optimization procedures whose mechanics are based on those of natural genetics. Mathematical arguments show how GAs bring substantial computational leverage to search problems, without requiring the mathematical characteristics often necessary for traditional optimization schemes (e.g., modality, continuity, availability of derivative information, etc.). GA's have proven effective in a variety of search tasks that arise in neural networks and fuzzy systems. This presentation begins by introducing the mechanism and theoretical underpinnings of GA's. GA's are then related to a class of rule-based machine learning systems called learning classifier systems (LCS's). An LCS implements a low-level production-system that uses a GA as its primary rule discovery mechanism. This presentation illustrates how, despite its rule-based framework, an LCS can be thought of as a competitive neural network. Neural network simulator code for an LCS is presented. In this context, the GA is doing more than optimizing and objective function. It is searching for an ecology of hidden nodes with limited connectivity. The GA attempts to evolve this ecology such that effective neural network performance results. The GA is particularly well adapted to this task, given its naturally-inspired basis. The LCS/neural network analogy extends itself to other, more traditional neural networks. Conclusions to the presentation discuss the implications of using GA's in ecological search problems that arise in neural and fuzzy systems.

Deep learning based hand gesture recognition in complex scenes

NASA Astrophysics Data System (ADS)

Ni, Zihan; Sang, Nong; Tan, Cheng

2018-03-01

Recently, region-based convolutional neural networks(R-CNNs) have achieved significant success in the field of object detection, but their accuracy is not too high for small objects and similar objects, such as the gestures. To solve this problem, we present an online hard example testing(OHET) technology to evaluate the confidence of the R-CNNs' outputs, and regard those outputs with low confidence as hard examples. In this paper, we proposed a cascaded networks to recognize the gestures. Firstly, we use the region-based fully convolutional neural network(R-FCN), which is capable of the detection for small object, to detect the gestures, and then use the OHET to select the hard examples. To enhance the accuracy of the gesture recognition, we re-classify the hard examples through VGG-19 classification network to obtain the final output of the gesture recognition system. Through the contrast experiments with other methods, we can see that the cascaded networks combined with the OHET reached to the state-of-the-art results of 99.3% mAP on small and similar gestures in complex scenes.

The neural code for face orientation in the human fusiform face area.

PubMed

Ramírez, Fernando M; Cichy, Radoslaw M; Allefeld, Carsten; Haynes, John-Dylan

2014-09-03

Humans recognize faces and objects with high speed and accuracy regardless of their orientation. Recent studies have proposed that orientation invariance in face recognition involves an intermediate representation where neural responses are similar for mirror-symmetric views. Here, we used fMRI, multivariate pattern analysis, and computational modeling to investigate the neural encoding of faces and vehicles at different rotational angles. Corroborating previous studies, we demonstrate a representation of face orientation in the fusiform face-selective area (FFA). We go beyond these studies by showing that this representation is category-selective and tolerant to retinal translation. Critically, by controlling for low-level confounds, we found the representation of orientation in FFA to be compatible with a linear angle code. Aspects of mirror-symmetric coding cannot be ruled out when FFA mean activity levels are considered as a dimension of coding. Finally, we used a parametric family of computational models, involving a biased sampling of view-tuned neuronal clusters, to compare different face angle encoding models. The best fitting model exhibited a predominance of neuronal clusters tuned to frontal views of faces. In sum, our findings suggest a category-selective and monotonic code of face orientation in the human FFA, in line with primate electrophysiology studies that observed mirror-symmetric tuning of neural responses at higher stages of the visual system, beyond the putative homolog of human FFA. Copyright © 2014 the authors 0270-6474/14/3412155-13$15.00/0.

An Artificial Neural Network Embedded Position and Orientation Determination Algorithm for Low Cost MEMS INS/GPS Integrated Sensors

PubMed Central

Chiang, Kai-Wei; Chang, Hsiu-Wen; Li, Chia-Yuan; Huang, Yun-Wen

2009-01-01

Digital mobile mapping, which integrates digital imaging with direct geo-referencing, has developed rapidly over the past fifteen years. Direct geo-referencing is the determination of the time-variable position and orientation parameters for a mobile digital imager. The most common technologies used for this purpose today are satellite positioning using Global Positioning System (GPS) and Inertial Navigation System (INS) using an Inertial Measurement Unit (IMU). They are usually integrated in such a way that the GPS receiver is the main position sensor, while the IMU is the main orientation sensor. The Kalman Filter (KF) is considered as the optimal estimation tool for real-time INS/GPS integrated kinematic position and orientation determination. An intelligent hybrid scheme consisting of an Artificial Neural Network (ANN) and KF has been proposed to overcome the limitations of KF and to improve the performance of the INS/GPS integrated system in previous studies. However, the accuracy requirements of general mobile mapping applications can’t be achieved easily, even by the use of the ANN-KF scheme. Therefore, this study proposes an intelligent position and orientation determination scheme that embeds ANN with conventional Rauch-Tung-Striebel (RTS) smoother to improve the overall accuracy of a MEMS INS/GPS integrated system in post-mission mode. By combining the Micro Electro Mechanical Systems (MEMS) INS/GPS integrated system and the intelligent ANN-RTS smoother scheme proposed in this study, a cheaper but still reasonably accurate position and orientation determination scheme can be anticipated. PMID:22574034

A Biologically Plausible Transform for Visual Recognition that is Invariant to Translation, Scale, and Rotation.

PubMed

Sountsov, Pavel; Santucci, David M; Lisman, John E

2011-01-01

Visual object recognition occurs easily despite differences in position, size, and rotation of the object, but the neural mechanisms responsible for this invariance are not known. We have found a set of transforms that achieve invariance in a neurally plausible way. We find that a transform based on local spatial frequency analysis of oriented segments and on logarithmic mapping, when applied twice in an iterative fashion, produces an output image that is unique to the object and that remains constant as the input image is shifted, scaled, or rotated.

A Biologically Plausible Transform for Visual Recognition that is Invariant to Translation, Scale, and Rotation

PubMed Central

Sountsov, Pavel; Santucci, David M.; Lisman, John E.

2011-01-01

Visual object recognition occurs easily despite differences in position, size, and rotation of the object, but the neural mechanisms responsible for this invariance are not known. We have found a set of transforms that achieve invariance in a neurally plausible way. We find that a transform based on local spatial frequency analysis of oriented segments and on logarithmic mapping, when applied twice in an iterative fashion, produces an output image that is unique to the object and that remains constant as the input image is shifted, scaled, or rotated. PMID:22125522

Recognition and classification of oscillatory patterns of electric brain activity using artificial neural network approach

NASA Astrophysics Data System (ADS)

Pchelintseva, Svetlana V.; Runnova, Anastasia E.; Musatov, Vyacheslav Yu.; Hramov, Alexander E.

2017-03-01

In the paper we study the problem of recognition type of the observed object, depending on the generated pattern and the registered EEG data. EEG recorded at the time of displaying cube Necker characterizes appropriate state of brain activity. As an image we use bistable image Necker cube. Subject selects the type of cube and interpret it either as aleft cube or as the right cube. To solve the problem of recognition, we use artificial neural networks. In our paper to create a classifier we have considered a multilayer perceptron. We examine the structure of the artificial neural network and define cubes recognition accuracy.

Higher-Order Neural Networks Applied to 2D and 3D Object Recognition

NASA Technical Reports Server (NTRS)

Spirkovska, Lilly; Reid, Max B.

1994-01-01

A Higher-Order Neural Network (HONN) can be designed to be invariant to geometric transformations such as scale, translation, and in-plane rotation. Invariances are built directly into the architecture of a HONN and do not need to be learned. Thus, for 2D object recognition, the network needs to be trained on just one view of each object class, not numerous scaled, translated, and rotated views. Because the 2D object recognition task is a component of the 3D object recognition task, built-in 2D invariance also decreases the size of the training set required for 3D object recognition. We present results for 2D object recognition both in simulation and within a robotic vision experiment and for 3D object recognition in simulation. We also compare our method to other approaches and show that HONNs have distinct advantages for position, scale, and rotation-invariant object recognition. The major drawback of HONNs is that the size of the input field is limited due to the memory required for the large number of interconnections in a fully connected network. We present partial connectivity strategies and a coarse-coding technique for overcoming this limitation and increasing the input field to that required by practical object recognition problems.

Neural networks application to divergence-based passive ranging

NASA Technical Reports Server (NTRS)

Barniv, Yair

1992-01-01

The purpose of this report is to summarize the state of knowledge and outline the planned work in divergence-based/neural networks approach to the problem of passive ranging derived from optical flow. Work in this and closely related areas is reviewed in order to provide the necessary background for further developments. New ideas about devising a monocular passive-ranging system are then introduced. It is shown that image-plan divergence is independent of image-plan location with respect to the focus of expansion and of camera maneuvers because it directly measures the object's expansion which, in turn, is related to the time-to-collision. Thus, a divergence-based method has the potential of providing a reliable range complementing other monocular passive-ranging methods which encounter difficulties in image areas close to the focus of expansion. Image-plan divergence can be thought of as some spatial/temporal pattern. A neural network realization was chosen for this task because neural networks have generally performed well in various other pattern recognition applications. The main goal of this work is to teach a neural network to derive the divergence from the imagery.

Lithofacies identification using multiple adaptive resonance theory neural networks and group decision expert system

USGS Publications Warehouse

Chang, H.-C.; Kopaska-Merkel, D. C.; Chen, H.-C.; Rocky, Durrans S.

2000-01-01

Lithofacies identification supplies qualitative information about rocks. Lithofacies represent rock textures and are important components of hydrocarbon reservoir description. Traditional techniques of lithofacies identification from core data are costly and different geologists may provide different interpretations. In this paper, we present a low-cost intelligent system consisting of three adaptive resonance theory neural networks and a rule-based expert system to consistently and objectively identify lithofacies from well-log data. The input data are altered into different forms representing different perspectives of observation of lithofacies. Each form of input is processed by a different adaptive resonance theory neural network. Among these three adaptive resonance theory neural networks, one neural network processes the raw continuous data, another processes categorial data, and the third processes fuzzy-set data. Outputs from these three networks are then combined by the expert system using fuzzy inference to determine to which facies the input data should be assigned. Rules are prioritized to emphasize the importance of firing order. This new approach combines the learning ability of neural networks, the adaptability of fuzzy logic, and the expertise of geologists to infer facies of the rocks. This approach is applied to the Appleton Field, an oil field located in Escambia County, Alabama. The hybrid intelligence system predicts lithofacies identity from log data with 87.6% accuracy. This prediction is more accurate than those of single adaptive resonance theory networks, 79.3%, 68.0% and 66.0%, using raw, fuzzy-set, and categorical data, respectively, and by an error-backpropagation neural network, 57.3%. (C) 2000 Published by Elsevier Science Ltd. All rights reserved.

Study on pattern recognition of Raman spectrum based on fuzzy neural network

NASA Astrophysics Data System (ADS)

Zheng, Xiangxiang; Lv, Xiaoyi; Mo, Jiaqing

2017-10-01

Hydatid disease is a serious parasitic disease in many regions worldwide, especially in Xinjiang, China. Raman spectrum of the serum of patients with echinococcosis was selected as the research object in this paper. The Raman spectrum of blood samples from healthy people and patients with echinococcosis are measured, of which the spectrum characteristics are analyzed. The fuzzy neural network not only has the ability of fuzzy logic to deal with uncertain information, but also has the ability to store knowledge of neural network, so it is combined with the Raman spectrum on the disease diagnosis problem based on Raman spectrum. Firstly, principal component analysis (PCA) is used to extract the principal components of the Raman spectrum, reducing the network input and accelerating the prediction speed and accuracy of Network based on remaining the original data. Then, the information of the extracted principal component is used as the input of the neural network, the hidden layer of the network is the generation of rules and the inference process, and the output layer of the network is fuzzy classification output. Finally, a part of samples are randomly selected for the use of training network, then the trained network is used for predicting the rest of the samples, and the predicted results are compared with general BP neural network to illustrate the feasibility and advantages of fuzzy neural network. Success in this endeavor would be helpful for the research work of spectroscopic diagnosis of disease and it can be applied in practice in many other spectral analysis technique fields.

Comparison of deep neural networks to spatio-temporal cortical dynamics of human visual object recognition reveals hierarchical correspondence

PubMed Central

Cichy, Radoslaw Martin; Khosla, Aditya; Pantazis, Dimitrios; Torralba, Antonio; Oliva, Aude

2016-01-01

The complex multi-stage architecture of cortical visual pathways provides the neural basis for efficient visual object recognition in humans. However, the stage-wise computations therein remain poorly understood. Here, we compared temporal (magnetoencephalography) and spatial (functional MRI) visual brain representations with representations in an artificial deep neural network (DNN) tuned to the statistics of real-world visual recognition. We showed that the DNN captured the stages of human visual processing in both time and space from early visual areas towards the dorsal and ventral streams. Further investigation of crucial DNN parameters revealed that while model architecture was important, training on real-world categorization was necessary to enforce spatio-temporal hierarchical relationships with the brain. Together our results provide an algorithmically informed view on the spatio-temporal dynamics of visual object recognition in the human visual brain. PMID:27282108

Comparison of deep neural networks to spatio-temporal cortical dynamics of human visual object recognition reveals hierarchical correspondence.

PubMed

Cichy, Radoslaw Martin; Khosla, Aditya; Pantazis, Dimitrios; Torralba, Antonio; Oliva, Aude

2016-06-10

The complex multi-stage architecture of cortical visual pathways provides the neural basis for efficient visual object recognition in humans. However, the stage-wise computations therein remain poorly understood. Here, we compared temporal (magnetoencephalography) and spatial (functional MRI) visual brain representations with representations in an artificial deep neural network (DNN) tuned to the statistics of real-world visual recognition. We showed that the DNN captured the stages of human visual processing in both time and space from early visual areas towards the dorsal and ventral streams. Further investigation of crucial DNN parameters revealed that while model architecture was important, training on real-world categorization was necessary to enforce spatio-temporal hierarchical relationships with the brain. Together our results provide an algorithmically informed view on the spatio-temporal dynamics of visual object recognition in the human visual brain.

Selected Flight Test Results for Online Learning Neural Network-Based Flight Control System

NASA Technical Reports Server (NTRS)

Williams-Hayes, Peggy S.

2004-01-01

The NASA F-15 Intelligent Flight Control System project team developed a series of flight control concepts designed to demonstrate neural network-based adaptive controller benefits, with the objective to develop and flight-test control systems using neural network technology to optimize aircraft performance under nominal conditions and stabilize the aircraft under failure conditions. This report presents flight-test results for an adaptive controller using stability and control derivative values from an online learning neural network. A dynamic cell structure neural network is used in conjunction with a real-time parameter identification algorithm to estimate aerodynamic stability and control derivative increments to baseline aerodynamic derivatives in flight. This open-loop flight test set was performed in preparation for a future phase in which the learning neural network and parameter identification algorithm output would provide the flight controller with aerodynamic stability and control derivative updates in near real time. Two flight maneuvers are analyzed - pitch frequency sweep and automated flight-test maneuver designed to optimally excite the parameter identification algorithm in all axes. Frequency responses generated from flight data are compared to those obtained from nonlinear simulation runs. Flight data examination shows that addition of flight-identified aerodynamic derivative increments into the simulation improved aircraft pitch handling qualities.

Object-oriented Tools for Distributed Computing

NASA Technical Reports Server (NTRS)

Adler, Richard M.

1993-01-01

Distributed computing systems are proliferating, owing to the availability of powerful, affordable microcomputers and inexpensive communication networks. A critical problem in developing such systems is getting application programs to interact with one another across a computer network. Remote interprogram connectivity is particularly challenging across heterogeneous environments, where applications run on different kinds of computers and operating systems. NetWorks! (trademark) is an innovative software product that provides an object-oriented messaging solution to these problems. This paper describes the design and functionality of NetWorks! and illustrates how it is being used to build complex distributed applications for NASA and in the commercial sector.

Two States Mapping Based Time Series Neural Network Model for Compensation Prediction Residual Error

NASA Astrophysics Data System (ADS)

Jung, Insung; Koo, Lockjo; Wang, Gi-Nam

2008-11-01

The objective of this paper was to design a model of human bio signal data prediction system for decreasing of prediction error using two states mapping based time series neural network BP (back-propagation) model. Normally, a lot of the industry has been applied neural network model by training them in a supervised manner with the error back-propagation algorithm for time series prediction systems. However, it still has got a residual error between real value and prediction result. Therefore, we designed two states of neural network model for compensation residual error which is possible to use in the prevention of sudden death and metabolic syndrome disease such as hypertension disease and obesity. We determined that most of the simulation cases were satisfied by the two states mapping based time series prediction model. In particular, small sample size of times series were more accurate than the standard MLP model.

An Intelligent Approach to Educational Data: Performance Comparison of the Multilayer Perceptron and the Radial Basis Function Artificial Neural Networks

ERIC Educational Resources Information Center

Kayri, Murat

2015-01-01

The objective of this study is twofold: (1) to investigate the factors that affect the success of university students by employing two artificial neural network methods (i.e., multilayer perceptron [MLP] and radial basis function [RBF]); and (2) to compare the effects of these methods on educational data in terms of predictive ability. The…

Ten-dimensional anthropomorphic arm control in a human brain-machine interface: difficulties, solutions, and limitations

NASA Astrophysics Data System (ADS)

Wodlinger, B.; Downey, J. E.; Tyler-Kabara, E. C.; Schwartz, A. B.; Boninger, M. L.; Collinger, J. L.

2015-02-01

Objective. In a previous study we demonstrated continuous translation, orientation and one-dimensional grasping control of a prosthetic limb (seven degrees of freedom) by a human subject with tetraplegia using a brain-machine interface (BMI). The current study, in the same subject, immediately followed the previous work and expanded the scope of the control signal by also extracting hand-shape commands from the two 96-channel intracortical electrode arrays implanted in the subject’s left motor cortex. Approach. Four new control signals, dictating prosthetic hand shape, replaced the one-dimensional grasping in the previous study, allowing the subject to control the prosthetic limb with ten degrees of freedom (three-dimensional (3D) translation, 3D orientation, four-dimensional hand shaping) simultaneously. Main results. Robust neural tuning to hand shaping was found, leading to ten-dimensional (10D) performance well above chance levels in all tests. Neural unit preferred directions were broadly distributed through the 10D space, with the majority of units significantly tuned to all ten dimensions, instead of being restricted to isolated domains (e.g. translation, orientation or hand shape). The addition of hand shaping emphasized object-interaction behavior. A fundamental component of BMIs is the calibration used to associate neural activity to intended movement. We found that the presence of an object during calibration enhanced successful shaping of the prosthetic hand as it closed around the object during grasping. Significance. Our results show that individual motor cortical neurons encode many parameters of movement, that object interaction is an important factor when extracting these signals, and that high-dimensional operation of prosthetic devices can be achieved with simple decoding algorithms. ClinicalTrials.gov Identifier: NCT01364480.

Study of the Gray Scale, Polychromatic, Distortion Invariant Neural Networks Using the Ipa Model.

NASA Astrophysics Data System (ADS)

Uang, Chii-Maw

Research in the optical neural network field is primarily motivated by the fact that humans recognize objects better than the conventional digital computers and the massively parallel inherent nature of optics. This research represents a continuous effort during the past several years in the exploitation of using neurocomputing for pattern recognition. Based on the interpattern association (IPA) model and Hamming net model, many new systems and applications are introduced. A gray level discrete associative memory that is based on object decomposition/composition is proposed for recognizing gray-level patterns. This technique extends the processing ability from the binary mode to gray-level mode, and thus the information capacity is increased. Two polychromatic optical neural networks using color liquid crystal television (LCTV) panels for color pattern recognition are introduced. By introducing a color encoding technique in conjunction with the interpattern associative algorithm, a color associative memory was realized. Based on the color decomposition and composition technique, a color exemplar-based Hamming net was built for color image classification. A shift-invariant neural network is presented through use of the translation invariant property of the modulus of the Fourier transformation and the hetero-associative interpattern association (IPA) memory. To extract the main features, a quadrantal sampling method is used to sampled data and then replace the training patterns. Using the concept of hetero-associative memory to recall the distorted object. A shift and rotation invariant neural network using an interpattern hetero-association (IHA) model is presented. To preserve the shift and rotation invariant properties, a set of binarized-encoded circular harmonic expansion (CHE) functions at the Fourier domain is used as the training set. We use the shift and symmetric properties of the modulus of the Fourier spectrum to avoid the problem of centering the CHE functions. Almost all neural networks have the positive and negative weights, which increases the difficulty of optical implementation. A method to construct a unipolar IPA IWM is discussed. By searching the redundant interconnection links, an effective way that removes all negative links is discussed.

Object-oriented analysis and design of an ECG storage and retrieval system integrated with an HIS.

PubMed

Wang, C; Ohe, K; Sakurai, T; Nagase, T; Kaihara, S

1996-03-01

For a hospital information system, object-oriented methodology plays an increasingly important role, especially for the management of digitized data, e.g., the electrocardiogram, electroencephalogram, electromyogram, spirogram, X-ray, CT and histopathological images, which are not yet computerized in most hospitals. As a first step in an object-oriented approach to hospital information management and storing medical data in an object-oriented database, we connected electrocardiographs to a hospital network and established the integration of ECG storage and retrieval systems with a hospital information system. In this paper, the object-oriented analysis and design of the ECG storage and retrieval systems is reported.

Pragmatically Framed Cross-Situational Noun Learning Using Computational Reinforcement Models

PubMed Central

Najnin, Shamima; Banerjee, Bonny

2018-01-01

Cross-situational learning and social pragmatic theories are prominent mechanisms for learning word meanings (i.e., word-object pairs). In this paper, the role of reinforcement is investigated for early word-learning by an artificial agent. When exposed to a group of speakers, the agent comes to understand an initial set of vocabulary items belonging to the language used by the group. Both cross-situational learning and social pragmatic theory are taken into account. As social cues, joint attention and prosodic cues in caregiver's speech are considered. During agent-caregiver interaction, the agent selects a word from the caregiver's utterance and learns the relations between that word and the objects in its visual environment. The “novel words to novel objects” language-specific constraint is assumed for computing rewards. The models are learned by maximizing the expected reward using reinforcement learning algorithms [i.e., table-based algorithms: Q-learning, SARSA, SARSA-λ, and neural network-based algorithms: Q-learning for neural network (Q-NN), neural-fitted Q-network (NFQ), and deep Q-network (DQN)]. Neural network-based reinforcement learning models are chosen over table-based models for better generalization and quicker convergence. Simulations are carried out using mother-infant interaction CHILDES dataset for learning word-object pairings. Reinforcement is modeled in two cross-situational learning cases: (1) with joint attention (Attentional models), and (2) with joint attention and prosodic cues (Attentional-prosodic models). Attentional-prosodic models manifest superior performance to Attentional ones for the task of word-learning. The Attentional-prosodic DQN outperforms existing word-learning models for the same task. PMID:29441027

From neural-based object recognition toward microelectronic eyes

NASA Technical Reports Server (NTRS)

Sheu, Bing J.; Bang, Sa Hyun

1994-01-01

Engineering neural network systems are best known for their abilities to adapt to the changing characteristics of the surrounding environment by adjusting system parameter values during the learning process. Rapid advances in analog current-mode design techniques have made possible the implementation of major neural network functions in custom VLSI chips. An electrically programmable analog synapse cell with large dynamic range can be realized in a compact silicon area. New designs of the synapse cells, neurons, and analog processor are presented. A synapse cell based on Gilbert multiplier structure can perform the linear multiplication for back-propagation networks. A double differential-pair synapse cell can perform the Gaussian function for radial-basis network. The synapse cells can be biased in the strong inversion region for high-speed operation or biased in the subthreshold region for low-power operation. The voltage gain of the sigmoid-function neurons is externally adjustable which greatly facilitates the search of optimal solutions in certain networks. Various building blocks can be intelligently connected to form useful industrial applications. Efficient data communication is a key system-level design issue for large-scale networks. We also present analog neural processors based on perceptron architecture and Hopfield network for communication applications. Biologically inspired neural networks have played an important role towards the creation of powerful intelligent machines. Accuracy, limitations, and prospects of analog current-mode design of the biologically inspired vision processing chips and cellular neural network chips are key design issues.

Automated detection of geological landforms on Mars using Convolutional Neural Networks

NASA Astrophysics Data System (ADS)

Palafox, Leon F.; Hamilton, Christopher W.; Scheidt, Stephen P.; Alvarez, Alexander M.

2017-04-01

The large volume of high-resolution images acquired by the Mars Reconnaissance Orbiter has opened a new frontier for developing automated approaches to detecting landforms on the surface of Mars. However, most landform classifiers focus on crater detection, which represents only one of many geological landforms of scientific interest. In this work, we use Convolutional Neural Networks (ConvNets) to detect both volcanic rootless cones and transverse aeolian ridges. Our system, named MarsNet, consists of five networks, each of which is trained to detect landforms of different sizes. We compare our detection algorithm with a widely used method for image recognition, Support Vector Machines (SVMs) using Histogram of Oriented Gradients (HOG) features. We show that ConvNets can detect a wide range of landforms and has better accuracy and recall in testing data than traditional classifiers based on SVMs.

Automated detection of geological landforms on Mars using Convolutional Neural Networks.

PubMed

Palafox, Leon F; Hamilton, Christopher W; Scheidt, Stephen P; Alvarez, Alexander M

2017-04-01

The large volume of high-resolution images acquired by the Mars Reconnaissance Orbiter has opened a new frontier for developing automated approaches to detecting landforms on the surface of Mars. However, most landform classifiers focus on crater detection, which represents only one of many geological landforms of scientific interest. In this work, we use Convolutional Neural Networks (ConvNets) to detect both volcanic rootless cones and transverse aeolian ridges. Our system, named MarsNet, consists of five networks, each of which is trained to detect landforms of different sizes. We compare our detection algorithm with a widely used method for image recognition, Support Vector Machines (SVMs) using Histogram of Oriented Gradients (HOG) features. We show that ConvNets can detect a wide range of landforms and has better accuracy and recall in testing data than traditional classifiers based on SVMs.

Spin switches for compact implementation of neuron and synapse

DOE Office of Scientific and Technical Information (OSTI.GOV)

Quang Diep, Vinh, E-mail: vdiep@purdue.edu; Sutton, Brian; Datta, Supriyo

2014-06-02

Nanomagnets driven by spin currents provide a natural implementation for a neuron and a synapse: currents allow convenient summation of multiple inputs, while the magnet provides the threshold function. The objective of this paper is to explore the possibility of a hardware neural network implementation using a spin switch (SS) as its basic building block. SS is a recently proposed device based on established technology with a transistor-like gain and input-output isolation. This allows neural networks to be constructed with purely passive interconnections without intervening clocks or amplifiers. The weights for the neural network are conveniently adjusted through analog voltagesmore » that can be stored in a non-volatile manner in an underlying CMOS layer using a floating gate low dropout voltage regulator. The operation of a multi-layer SS neural network designed for character recognition is demonstrated using a standard simulation model based on coupled Landau-Lifshitz-Gilbert equations, one for each magnet in the network.« less

Cellular automata with object-oriented features for parallel molecular network modeling.

PubMed

Zhu, Hao; Wu, Yinghui; Huang, Sui; Sun, Yan; Dhar, Pawan

2005-06-01

Cellular automata are an important modeling paradigm for studying the dynamics of large, parallel systems composed of multiple, interacting components. However, to model biological systems, cellular automata need to be extended beyond the large-scale parallelism and intensive communication in order to capture two fundamental properties characteristic of complex biological systems: hierarchy and heterogeneity. This paper proposes extensions to a cellular automata language, Cellang, to meet this purpose. The extended language, with object-oriented features, can be used to describe the structure and activity of parallel molecular networks within cells. Capabilities of this new programming language include object structure to define molecular programs within a cell, floating-point data type and mathematical functions to perform quantitative computation, message passing capability to describe molecular interactions, as well as new operators, statements, and built-in functions. We discuss relevant programming issues of these features, including the object-oriented description of molecular interactions with molecule encapsulation, message passing, and the description of heterogeneity and anisotropy at the cell and molecule levels. By enabling the integration of modeling at the molecular level with system behavior at cell, tissue, organ, or even organism levels, the program will help improve our understanding of how complex and dynamic biological activities are generated and controlled by parallel functioning of molecular networks. Index Terms-Cellular automata, modeling, molecular network, object-oriented.

Using a binaural biomimetic array to identify bottom objects ensonified by echolocating dolphins

USGS Publications Warehouse

Heiweg, D.A.; Moore, P.W.; Martin, S.W.; Dankiewicz, L.A.

2006-01-01

The development of a unique dolphin biomimetic sonar produced data that were used to study signal processing methods for object identification. Echoes from four metallic objects proud on the bottom, and a substrate-only condition, were generated by bottlenose dolphins trained to ensonify the targets in very shallow water. Using the two-element ('binaural') receive array, object echo spectra were collected and submitted for identification to four neural network architectures. Identification accuracy was evaluated over two receive array configurations, and five signal processing schemes. The four neural networks included backpropagation, learning vector quantization, genetic learning and probabilistic network architectures. The processing schemes included four methods that capitalized on the binaural data, plus a monaural benchmark process. All the schemes resulted in above-chance identification accuracy when applied to learning vector quantization and backpropagation. Beam-forming or concatenation of spectra from both receive elements outperformed the monaural benchmark, with higher sensitivity and lower bias. Ultimately, best object identification performance was achieved by the learning vector quantization network supplied with beam-formed data. The advantages of multi-element signal processing for object identification are clearly demonstrated in this development of a first-ever dolphin biomimetic sonar. ?? 2006 IOP Publishing Ltd.

Nonsmooth Finite-Time Synchronization of Switched Coupled Neural Networks.

PubMed

Liu, Xiaoyang; Cao, Jinde; Yu, Wenwu; Song, Qiang

2016-10-01

This paper is concerned with the finite-time synchronization (FTS) issue of switched coupled neural networks with discontinuous or continuous activations. Based on the framework of nonsmooth analysis, some discontinuous or continuous controllers are designed to force the coupled networks to synchronize to an isolated neural network. Some sufficient conditions are derived to ensure the FTS by utilizing the well-known finite-time stability theorem for nonlinear systems. Compared with the previous literatures, such synchronization objective will be realized when the activations and the controllers are both discontinuous. The obtained results in this paper include and extend the earlier works on the synchronization issue of coupled networks with Lipschitz continuous conditions. Moreover, an upper bound of the settling time for synchronization is estimated. Finally, numerical simulations are given to demonstrate the effectiveness of the theoretical results.

A neural network model of semantic memory linking feature-based object representation and words.

PubMed

Cuppini, C; Magosso, E; Ursino, M

2009-06-01

Recent theories in cognitive neuroscience suggest that semantic memory is a distributed process, which involves many cortical areas and is based on a multimodal representation of objects. The aim of this work is to extend a previous model of object representation to realize a semantic memory, in which sensory-motor representations of objects are linked with words. The model assumes that each object is described as a collection of features, coded in different cortical areas via a topological organization. Features in different objects are segmented via gamma-band synchronization of neural oscillators. The feature areas are further connected with a lexical area, devoted to the representation of words. Synapses among the feature areas, and among the lexical area and the feature areas are trained via a time-dependent Hebbian rule, during a period in which individual objects are presented together with the corresponding words. Simulation results demonstrate that, during the retrieval phase, the network can deal with the simultaneous presence of objects (from sensory-motor inputs) and words (from acoustic inputs), can correctly associate objects with words and segment objects even in the presence of incomplete information. Moreover, the network can realize some semantic links among words representing objects with shared features. These results support the idea that semantic memory can be described as an integrated process, whose content is retrieved by the co-activation of different multimodal regions. In perspective, extended versions of this model may be used to test conceptual theories, and to provide a quantitative assessment of existing data (for instance concerning patients with neural deficits).

Single- and Multiple-Objective Optimization with Differential Evolution and Neural Networks

NASA Technical Reports Server (NTRS)

Rai, Man Mohan

2006-01-01

Genetic and evolutionary algorithms have been applied to solve numerous problems in engineering design where they have been used primarily as optimization procedures. These methods have an advantage over conventional gradient-based search procedures became they are capable of finding global optima of multi-modal functions and searching design spaces with disjoint feasible regions. They are also robust in the presence of noisy data. Another desirable feature of these methods is that they can efficiently use distributed and parallel computing resources since multiple function evaluations (flow simulations in aerodynamics design) can be performed simultaneously and independently on ultiple processors. For these reasons genetic and evolutionary algorithms are being used more frequently in design optimization. Examples include airfoil and wing design and compressor and turbine airfoil design. They are also finding increasing use in multiple-objective and multidisciplinary optimization. This lecture will focus on an evolutionary method that is a relatively new member to the general class of evolutionary methods called differential evolution (DE). This method is easy to use and program and it requires relatively few user-specified constants. These constants are easily determined for a wide class of problems. Fine-tuning the constants will off course yield the solution to the optimization problem at hand more rapidly. DE can be efficiently implemented on parallel computers and can be used for continuous, discrete and mixed discrete/continuous optimization problems. It does not require the objective function to be continuous and is noise tolerant. DE and applications to single and multiple-objective optimization will be included in the presentation and lecture notes. A method for aerodynamic design optimization that is based on neural networks will also be included as a part of this lecture. The method offers advantages over traditional optimization methods. It is more flexible than other methods in dealing with design in the context of both steady and unsteady flows, partial and complete data sets, combined experimental and numerical data, inclusion of various constraints and rules of thumb, and other issues that characterize the aerodynamic design process. Neural networks provide a natural framework within which a succession of numerical solutions of increasing fidelity, incorporating more realistic flow physics, can be represented and utilized for optimization. Neural networks also offer an excellent framework for multiple-objective and multi-disciplinary design optimization. Simulation tools from various disciplines can be integrated within this framework and rapid trade-off studies involving one or many disciplines can be performed. The prospect of combining neural network based optimization methods and evolutionary algorithms to obtain a hybrid method with the best properties of both methods will be included in this presentation. Achieving solution diversity and accurate convergence to the exact Pareto front in multiple objective optimization usually requires a significant computational effort with evolutionary algorithms. In this lecture we will also explore the possibility of using neural networks to obtain estimates of the Pareto optimal front using non-dominated solutions generated by DE as training data. Neural network estimators have the potential advantage of reducing the number of function evaluations required to obtain solution accuracy and diversity, thus reducing cost to design.

(abstract) A High Throughput 3-D Inner Product Processor

NASA Technical Reports Server (NTRS)

Daud, Tuan

1996-01-01

A particularily challenging image processing application is the real time scene acquisition and object discrimination. It requires spatio-temporal recognition of point and resolved objects at high speeds with parallel processing algorithms. Neural network paradigms provide fine grain parallism and, when implemented in hardware, offer orders of magnitude speed up. However, neural networks implemented on a VLSI chip are planer architectures capable of efficient processing of linear vector signals rather than 2-D images. Therefore, for processing of images, a 3-D stack of neural-net ICs receiving planar inputs and consuming minimal power are required. Details of the circuits with chip architectures will be described with need to develop ultralow-power electronics. Further, use of the architecture in a system for high-speed processing will be illustrated.

Social Attention and the Brain

PubMed Central

Klein, Jeffrey T.; Shepherd, Stephen V.; Platt, Michael L.

2012-01-01

Humans and other animals pay attention to other members of their groups to acquire valuable social information about them, including information about their identity, dominance, fertility, emotions, and likely intent. In primates, attention to other group members and the objects of their attention is mediated by neural circuits that transduce sensory information about others and translate that information into value signals that bias orienting. This process likely proceeds via two distinct but integrated pathways: an ancestral, subcortical route that mediates crude but fast orienting to animate objects and faces; and a more derived route involving cortical orienting circuits that mediate nuanced and context-dependent social attention. PMID:19889376

Verification and Validation of Adaptive and Intelligent Systems with Flight Test Results

NASA Technical Reports Server (NTRS)

Burken, John J.; Larson, Richard R.

2009-01-01

F-15 IFCS project goals are: a) Demonstrate Control Approaches that can Efficiently Optimize Aircraft Performance in both Normal and Failure Conditions [A] & [B] failures. b) Advance Neural Network-Based Flight Control Technology for New Aerospace Systems Designs with a Pilot in the Loop. Gen II objectives include; a) Implement and Fly a Direct Adaptive Neural Network Based Flight Controller; b) Demonstrate the Ability of the System to Adapt to Simulated System Failures: 1) Suppress Transients Associated with Failure; 2) Re-Establish Sufficient Control and Handling of Vehicle for Safe Recovery. c) Provide Flight Experience for Development of Verification and Validation Processes for Flight Critical Neural Network Software.

Identification of Resting State Networks Involved in Executive Function.

PubMed

Connolly, Joanna; McNulty, Jonathan P; Boran, Lorraine; Roche, Richard A P; Delany, David; Bokde, Arun L W

2016-06-01

The structural networks in the human brain are consistent across subjects, and this is reflected also in that functional networks across subjects are relatively consistent. These findings are not only present during performance of a goal oriented task but there are also consistent functional networks during resting state. It suggests that goal oriented activation patterns may be a function of component networks identified using resting state. The current study examines the relationship between resting state networks measured and patterns of neural activation elicited during a Stroop task. The association between the Stroop-activated networks and the resting state networks was quantified using spatial linear regression. In addition, we investigated if the degree of spatial association of resting state networks with the Stroop task may predict performance on the Stroop task. The results of this investigation demonstrated that the Stroop activated network can be decomposed into a number of resting state networks, which were primarily associated with attention, executive function, visual perception, and the default mode network. The close spatial correspondence between the functional organization of the resting brain and task-evoked patterns supports the relevance of resting state networks in cognitive function.

Pruning Neural Networks with Distribution Estimation Algorithms

DOE Office of Scientific and Technical Information (OSTI.GOV)

Cantu-Paz, E

2003-01-15

This paper describes the application of four evolutionary algorithms to the pruning of neural networks used in classification problems. Besides of a simple genetic algorithm (GA), the paper considers three distribution estimation algorithms (DEAs): a compact GA, an extended compact GA, and the Bayesian Optimization Algorithm. The objective is to determine if the DEAs present advantages over the simple GA in terms of accuracy or speed in this problem. The experiments used a feed forward neural network trained with standard back propagation and public-domain and artificial data sets. The pruned networks seemed to have better or equal accuracy than themore » original fully-connected networks. Only in a few cases, pruning resulted in less accurate networks. We found few differences in the accuracy of the networks pruned by the four EAs, but found important differences in the execution time. The results suggest that a simple GA with a small population might be the best algorithm for pruning networks on the data sets we tested.« less

Image Understanding by Image-Seeking Adaptive Networks (ISAN).

DTIC Science & Technology

1987-08-10

our reserch on adaptive neural networks in the visual and sensory-motor cortex of cats. We demonstrate that, under certain conditions, plasticity is...understanding in organisms proceeds directly from adaptively seeking whole images and not via a preliminary analysis of elementary features, followed by object...empirical reserch has always been that ultimately any neural system has to serve behavior and that behavior serves survival. Evolutionary selection makes it

Abnormal Functional Activation and Connectivity in the Working Memory Network in Early-Onset Schizophrenia

ERIC Educational Resources Information Center

Kyriakopoulos, Marinos; Dima, Danai; Roiser, Jonathan P.; Corrigall, Richard; Barker, Gareth J.; Frangou, Sophia

2012-01-01

Objective: Disruption within the working memory (WM) neural network is considered an integral feature of schizophrenia. The WM network, and the dorsolateral prefrontal cortex (DLPFC) in particular, undergo significant remodeling in late adolescence. Potential interactions between developmental changes in the WM network and disease-related…

Neural network approximation of tip-abrasion effects in AFM imaging

NASA Astrophysics Data System (ADS)

Bakucz, Peter; Yacoot, Andrew; Dziomba, Thorsten; Koenders, Ludger; Krüger-Sehm, Rolf

2008-06-01

The abrasion (wear) of tips used in scanning force microscopy (SFM) directly influences SFM image quality and is therefore of great relevance to quantitative SFM measurements. The increasing implementation of automated SFM measurement schemes has become a strong driving force for increasing efforts towards the prediction of tip wear, as it needs to be ensured that the probe is exchanged before a level of tip wear is reached that adversely affects the measurement quality. In this paper, we describe the identification of tip abrasion in a system of SFM measurements. We attempt to model the tip-abrasion process as a concatenation of a mapping from the measured AFM data to a regression vector and a nonlinear mapping from the regressor space to the output space. The mapping is formed as a basis function expansion. Feedforward neural networks are used to approximate this mapping. The one-hidden layer network gave a good quality of fit for the training and test sets for the tip-abrasion system. We illustrate our method with AFM measurements of both fine periodic structures and randomly oriented sharp features and compare our neural network results with those obtained using other methods.

Distorted Character Recognition Via An Associative Neural Network

NASA Astrophysics Data System (ADS)

Messner, Richard A.; Szu, Harold H.

1987-03-01

The purpose of this paper is two-fold. First, it is intended to provide some preliminary results of a character recognition scheme which has foundations in on-going neural network architecture modeling, and secondly, to apply some of the neural network results in a real application area where thirty years of effort has had little effect on providing the machine an ability to recognize distorted objects within the same object class. It is the author's belief that the time is ripe to start applying in ernest the results of over twenty years of effort in neural modeling to some of the more difficult problems which seem so hard to solve by conventional means. The character recognition scheme proposed utilizes a preprocessing stage which performs a 2-dimensional Walsh transform of an input cartesian image field, then sequency filters this spectrum into three feature bands. Various features are then extracted and organized into three sets of feature vectors. These vector patterns that are stored and recalled associatively. Two possible associative neural memory models are proposed for further investigation. The first being an outer-product linear matrix associative memory with a threshold function controlling the strength of the output pattern (similar to Kohonen's crosscorrelation approach [1]). The second approach is based upon a modified version of Grossberg's neural architecture [2] which provides better self-organizing properties due to its adaptive nature. Preliminary results of the sequency filtering and feature extraction preprocessing stage and discussion about the use of the proposed neural architectures is included.

Resonator memories and optical novelty filters

NASA Astrophysics Data System (ADS)

Anderson, Dana Z.; Erle, Marie C.

Optical resonators having holographic elements are potential candidates for storing information that can be accessed through content addressable or associative recall. Closely related to the resonator memory is the optical novelty filter, which can detect the differences between a test object and a set of reference objects. We discuss implementations of these devices using continuous optical media such as photorefractive materials. The discussion is framed in the context of neural network models. There are both formal and qualitative similarities between the resonator memory and optical novelty filter and network models. Mode competition arises in the theory of the resonator memory, much as it does in some network models. We show that the role of the phenomena of "daydreaming" in the real-time programmable optical resonator is very much akin to the role of "unlearning" in neural network memories. The theory of programming the real-time memory for a single mode is given in detail. This leads to a discussion of the optical novelty filter. Experimental results for the resonator memory, the real-time programmable memory, and the optical tracking novelty filter are reviewed. We also point to several issues that need to be addressed in order to implement more formal models of neural networks.

Resonator Memories And Optical Novelty Filters

NASA Astrophysics Data System (ADS)

Anderson, Dana Z.; Erie, Marie C.

1987-05-01

Optical resonators having holographic elements are potential candidates for storing information that can be accessed through content-addressable or associative recall. Closely related to the resonator memory is the optical novelty filter, which can detect the differences between a test object and a set of reference objects. We discuss implementations of these devices using continuous optical media such as photorefractive ma-terials. The discussion is framed in the context of neural network models. There are both formal and qualitative similarities between the resonator memory and optical novelty filter and network models. Mode competition arises in the theory of the resonator memory, much as it does in some network models. We show that the role of the phenomena of "daydream-ing" in the real-time programmable optical resonator is very much akin to the role of "unlearning" in neural network memories. The theory of programming the real-time memory for a single mode is given in detail. This leads to a discussion of the optical novelty filter. Experimental results for the resonator memory, the real-time programmable memory, and the optical tracking novelty filter are reviewed. We also point to several issues that need to be addressed in order to implement more formal models of neural networks.

Nonlinear Motion Tracking by Deep Learning Architecture

NASA Astrophysics Data System (ADS)

Verma, Arnav; Samaiya, Devesh; Gupta, Karunesh K.

2018-03-01

In the world of Artificial Intelligence, object motion tracking is one of the major problems. The extensive research is being carried out to track people in crowd. This paper presents a unique technique for nonlinear motion tracking in the absence of prior knowledge of nature of nonlinear path that the object being tracked may follow. We achieve this by first obtaining the centroid of the object and then using the centroid as the current example for a recurrent neural network trained using real-time recurrent learning. We have tweaked the standard algorithm slightly and have accumulated the gradient for few previous iterations instead of using just the current iteration as is the norm. We show that for a single object, such a recurrent neural network is highly capable of approximating the nonlinearity of its path.

A neural network technique for remeshing of bone microstructure.

PubMed

Fischer, Anath; Holdstein, Yaron

2012-01-01

Today, there is major interest within the biomedical community in developing accurate noninvasive means for the evaluation of bone microstructure and bone quality. Recent improvements in 3D imaging technology, among them development of micro-CT and micro-MRI scanners, allow in-vivo 3D high-resolution scanning and reconstruction of large specimens or even whole bone models. Thus, the tendency today is to evaluate bone features using 3D assessment techniques rather than traditional 2D methods. For this purpose, high-quality meshing methods are required. However, the 3D meshes produced from current commercial systems usually are of low quality with respect to analysis and rapid prototyping. 3D model reconstruction of bone is difficult due to the complexity of bone microstructure. The small bone features lead to a great deal of neighborhood ambiguity near each vertex. The relatively new neural network method for mesh reconstruction has the potential to create or remesh 3D models accurately and quickly. A neural network (NN), which resembles an artificial intelligence (AI) algorithm, is a set of interconnected neurons, where each neuron is capable of making an autonomous arithmetic calculation. Moreover, each neuron is affected by its surrounding neurons through the structure of the network. This paper proposes an extension of the growing neural gas (GNN) neural network technique for remeshing a triangular manifold mesh that represents bone microstructure. This method has the advantage of reconstructing the surface of a genus-n freeform object without a priori knowledge regarding the original object, its topology, or its shape.

Biologically plausible learning in neural networks: a lesson from bacterial chemotaxis.

PubMed

Shimansky, Yury P

2009-12-01

Learning processes in the brain are usually associated with plastic changes made to optimize the strength of connections between neurons. Although many details related to biophysical mechanisms of synaptic plasticity have been discovered, it is unclear how the concurrent performance of adaptive modifications in a huge number of spatial locations is organized to minimize a given objective function. Since direct experimental observation of even a relatively small subset of such changes is not feasible, computational modeling is an indispensable investigation tool for solving this problem. However, the conventional method of error back-propagation (EBP) employed for optimizing synaptic weights in artificial neural networks is not biologically plausible. This study based on computational experiments demonstrated that such optimization can be performed rather efficiently using the same general method that bacteria employ for moving closer to an attractant or away from a repellent. With regard to neural network optimization, this method consists of regulating the probability of an abrupt change in the direction of synaptic weight modification according to the temporal gradient of the objective function. Neural networks utilizing this method (regulation of modification probability, RMP) can be viewed as analogous to swimming in the multidimensional space of their parameters in the flow of biochemical agents carrying information about the optimality criterion. The efficiency of RMP is comparable to that of EBP, while RMP has several important advantages. Since the biological plausibility of RMP is beyond a reasonable doubt, the RMP concept provides a constructive framework for the experimental analysis of learning in natural neural networks.

Grain-Boundary Resistance in Copper Interconnects: From an Atomistic Model to a Neural Network

NASA Astrophysics Data System (ADS)

Valencia, Daniel; Wilson, Evan; Jiang, Zhengping; Valencia-Zapata, Gustavo A.; Wang, Kuang-Chung; Klimeck, Gerhard; Povolotskyi, Michael

2018-04-01

Orientation effects on the specific resistance of copper grain boundaries are studied systematically with two different atomistic tight-binding methods. A methodology is developed to model the specific resistance of grain boundaries in the ballistic limit using the embedded atom model, tight- binding methods, and nonequilibrium Green's functions. The methodology is validated against first-principles calculations for thin films with a single coincident grain boundary, with 6.4% deviation in the specific resistance. A statistical ensemble of 600 large, random structures with grains is studied. For structures with three grains, it is found that the distribution of specific resistances is close to normal. Finally, a compact model for grain-boundary-specific resistance is constructed based on a neural network.

Object-oriented Approach to High-level Network Monitoring and Management

NASA Technical Reports Server (NTRS)

Mukkamala, Ravi

2000-01-01

An absolute prerequisite for the management of large investigating methods to build high-level monitoring computer networks is the ability to measure their systems that are built on top of existing monitoring performance. Unless we monitor a system, we cannot tools. Due to the heterogeneous nature of the hope to manage and control its performance. In this underlying systems at NASA Langley Research Center, paper, we describe a network monitoring system that we use an object-oriented approach for the design, we are currently designing and implementing. Keeping, first, we use UML (Unified Modeling Language) to in mind the complexity of the task and the required model users' requirements. Second, we identify the flexibility for future changes, we use an object-oriented existing capabilities of the underlying monitoring design methodology. The system is built using the system. Third, we try to map the former with the latter. APIs offered by the HP OpenView system.

Imbalance aware lithography hotspot detection: a deep learning approach

NASA Astrophysics Data System (ADS)

Yang, Haoyu; Luo, Luyang; Su, Jing; Lin, Chenxi; Yu, Bei

2017-03-01

With the advancement of VLSI technology nodes, light diffraction caused lithographic hotspots have become a serious problem affecting manufacture yield. Lithography hotspot detection at the post-OPC stage is imperative to check potential circuit failures when transferring designed patterns onto silicon wafers. Although conventional lithography hotspot detection methods, such as machine learning, have gained satisfactory performance, with extreme scaling of transistor feature size and more and more complicated layout patterns, conventional methodologies may suffer from performance degradation. For example, manual or ad hoc feature extraction in a machine learning framework may lose important information when predicting potential errors in ultra-large-scale integrated circuit masks. In this paper, we present a deep convolutional neural network (CNN) targeting representative feature learning in lithography hotspot detection. We carefully analyze impact and effectiveness of different CNN hyper-parameters, through which a hotspot-detection-oriented neural network model is established. Because hotspot patterns are always minorities in VLSI mask design, the training data set is highly imbalanced. In this situation, a neural network is no longer reliable, because a trained model with high classification accuracy may still suffer from high false negative results (missing hotspots), which is fatal in hotspot detection problems. To address the imbalance problem, we further apply minority upsampling and random-mirror flipping before training the network. Experimental results show that our proposed neural network model achieves highly comparable or better performance on the ICCAD 2012 contest benchmark compared to state-of-the-art hotspot detectors based on deep or representative machine leaning.

Implementation of neuromorphic systems: from discrete components to analog VLSI chips (testing and communication issues).

PubMed

Dante, V; Del Giudice, P; Mattia, M

2001-01-01

We review a series of implementations of electronic devices aiming at imitating to some extent structure and function of simple neural systems, with particular emphasis on communication issues. We first provide a short overview of general features of such "neuromorphic" devices and the implications of setting up "tests" for them. We then review the developments directly related to our work at the Istituto Superiore di Sanità (ISS): a pilot electronic neural network implementing a simple classifier, autonomously developing internal representations of incoming stimuli; an output network, collecting information from the previous classifier and extracting the relevant part to be forwarded to the observer; an analog, VLSI (very large scale integration) neural chip implementing a recurrent network of spiking neurons and plastic synapses, and the test setup for it; a board designed to interface the standard PCI (peripheral component interconnect) bus of a PC with a special purpose, asynchronous bus for communication among neuromorphic chips; a short and preliminary account of an application-oriented device, taking advantage of the above communication infrastructure.

Prediction of Compressional Wave Velocity Using Regression and Neural Network Modeling and Estimation of Stress Orientation in Bokaro Coalfield, India

NASA Astrophysics Data System (ADS)

Paul, Suman; Ali, Muhammad; Chatterjee, Rima

2018-01-01

Velocity of compressional wave ( V P) of coal and non-coal lithology is predicted from five wells from the Bokaro coalfield (CF), India. Shear sonic travel time logs are not recorded for all wells under the study area. Shear wave velocity ( Vs) is available only for two wells: one from east and other from west Bokaro CF. The major lithologies of this CF are dominated by coal, shaly coal of Barakar formation. This paper focuses on the (a) relationship between Vp and Vs, (b) prediction of Vp using regression and neural network modeling and (c) estimation of maximum horizontal stress from image log. Coal characterizes with low acoustic impedance (AI) as compared to the overlying and underlying strata. The cross-plot between AI and Vp/ Vs is able to identify coal, shaly coal, shale and sandstone from wells in Bokaro CF. The relationship between Vp and Vs is obtained with excellent goodness of fit ( R 2) ranging from 0.90 to 0.93. Linear multiple regression and multi-layered feed-forward neural network (MLFN) models are developed for prediction Vp from two wells using four input log parameters: gamma ray, resistivity, bulk density and neutron porosity. Regression model predicted Vp shows poor fit (from R 2 = 0.28) to good fit ( R 2 = 0.79) with the observed velocity. MLFN model predicted Vp indicates satisfactory to good R2 values varying from 0.62 to 0.92 with the observed velocity. Maximum horizontal stress orientation from a well at west Bokaro CF is studied from Formation Micro-Imager (FMI) log. Breakouts and drilling-induced fractures (DIFs) are identified from the FMI log. Breakout length of 4.5 m is oriented towards N60°W whereas the orientation of DIFs for a cumulative length of 26.5 m is varying from N15°E to N35°E. The mean maximum horizontal stress in this CF is towards N28°E.

Effective Multifocus Image Fusion Based on HVS and BP Neural Network

PubMed Central

Yang, Yong

2014-01-01

The aim of multifocus image fusion is to fuse the images taken from the same scene with different focuses to obtain a resultant image with all objects in focus. In this paper, a novel multifocus image fusion method based on human visual system (HVS) and back propagation (BP) neural network is presented. Three features which reflect the clarity of a pixel are firstly extracted and used to train a BP neural network to determine which pixel is clearer. The clearer pixels are then used to construct the initial fused image. Thirdly, the focused regions are detected by measuring the similarity between the source images and the initial fused image followed by morphological opening and closing operations. Finally, the final fused image is obtained by a fusion rule for those focused regions. Experimental results show that the proposed method can provide better performance and outperform several existing popular fusion methods in terms of both objective and subjective evaluations. PMID:24683327

Training feed-forward neural networks with gain constraints

PubMed

Hartman

2000-04-01

Inaccurate input-output gains (partial derivatives of outputs with respect to inputs) are common in neural network models when input variables are correlated or when data are incomplete or inaccurate. Accurate gains are essential for optimization, control, and other purposes. We develop and explore a method for training feedforward neural networks subject to inequality or equality-bound constraints on the gains of the learned mapping. Gain constraints are implemented as penalty terms added to the objective function, and training is done using gradient descent. Adaptive and robust procedures are devised for balancing the relative strengths of the various terms in the objective function, which is essential when the constraints are inconsistent with the data. The approach has the virtue that the model domain of validity can be extended via extrapolation training, which can dramatically improve generalization. The algorithm is demonstrated here on artificial and real-world problems with very good results and has been advantageously applied to dozens of models currently in commercial use.

View-Tolerant Face Recognition and Hebbian Learning Imply Mirror-Symmetric Neural Tuning to Head Orientation.

PubMed

Leibo, Joel Z; Liao, Qianli; Anselmi, Fabio; Freiwald, Winrich A; Poggio, Tomaso

2017-01-09

The primate brain contains a hierarchy of visual areas, dubbed the ventral stream, which rapidly computes object representations that are both specific for object identity and robust against identity-preserving transformations, like depth rotations [1, 2]. Current computational models of object recognition, including recent deep-learning networks, generate these properties through a hierarchy of alternating selectivity-increasing filtering and tolerance-increasing pooling operations, similar to simple-complex cells operations [3-6]. Here, we prove that a class of hierarchical architectures and a broad set of biologically plausible learning rules generate approximate invariance to identity-preserving transformations at the top level of the processing hierarchy. However, all past models tested failed to reproduce the most salient property of an intermediate representation of a three-level face-processing hierarchy in the brain: mirror-symmetric tuning to head orientation [7]. Here, we demonstrate that one specific biologically plausible Hebb-type learning rule generates mirror-symmetric tuning to bilaterally symmetric stimuli, like faces, at intermediate levels of the architecture and show why it does so. Thus, the tuning properties of individual cells inside the visual stream appear to result from group properties of the stimuli they encode and to reflect the learning rules that sculpted the information-processing system within which they reside. Copyright © 2017 Elsevier Ltd. All rights reserved.

A neural network based reputation bootstrapping approach for service selection

NASA Astrophysics Data System (ADS)

Wu, Quanwang; Zhu, Qingsheng; Li, Peng

2015-10-01

With the concept of service-oriented computing becoming widely accepted in enterprise application integration, more and more computing resources are encapsulated as services and published online. Reputation mechanism has been studied to establish trust on prior unknown services. One of the limitations of current reputation mechanisms is that they cannot assess the reputation of newly deployed services as no record of their previous behaviours exists. Most of the current bootstrapping approaches merely assign default reputation values to newcomers. However, by this kind of methods, either newcomers or existing services will be favoured. In this paper, we present a novel reputation bootstrapping approach, where correlations between features and performance of existing services are learned through an artificial neural network (ANN) and they are then generalised to establish a tentative reputation when evaluating new and unknown services. Reputations of services published previously by the same provider are also incorporated for reputation bootstrapping if available. The proposed reputation bootstrapping approach is seamlessly embedded into an existing reputation model and implemented in the extended service-oriented architecture. Empirical studies of the proposed approach are shown at last.

Spontaneous default mode network phase-locking moderates performance perceptions under stereotype threat

PubMed Central

Leitner, Jordan B.; Duran-Jordan, Kelly; Magerman, Adam B.; Schmader, Toni; Allen, John J. B.

2015-01-01

This study assessed whether individual differences in self-oriented neural processing were associated with performance perceptions of minority students under stereotype threat. Resting electroencephalographic activity recorded in white and minority participants was used to predict later estimates of task errors and self-doubt on a presumed measure of intelligence. We assessed spontaneous phase-locking between dipole sources in left lateral parietal cortex (LPC), precuneus/posterior cingulate cortex (P/PCC), and medial prefrontal cortex (MPFC); three regions of the default mode network (DMN) that are integral for self-oriented processing. Results revealed that minorities with greater LPC-P/PCC phase-locking in the theta band reported more accurate error estimations. All individuals experienced less self-doubt to the extent they exhibited greater LPC-MPFC phase-locking in the alpha band but this effect was driven by minorities. Minorities also reported more self-doubt to the extent they overestimated errors. Findings reveal novel neural moderators of stereotype threat effects on subjective experience. Spontaneous synchronization between DMN regions may play a role in anticipatory coping mechanisms that buffer individuals from stereotype threat. PMID:25398433

Center for Neural Engineering: applications of pulse-coupled neural networks

NASA Astrophysics Data System (ADS)

Malkani, Mohan; Bodruzzaman, Mohammad; Johnson, John L.; Davis, Joel

1999-03-01

Pulsed-Coupled Neural Network (PCNN) is an oscillatory model neural network where grouping of cells and grouping among the groups that form the output time series (number of cells that fires in each input presentation also called `icon'). This is based on the synchronicity of oscillations. Recent work by Johnson and others demonstrated the functional capabilities of networks containing such elements for invariant feature extraction using intensity maps. PCNN thus presents itself as a more biologically plausible model with solid functional potential. This paper will present the summary of several projects and their results where we successfully applied PCNN. In project one, the PCNN was applied for object recognition and classification through a robotic vision system. The features (icons) generated by the PCNN were then fed into a feedforward neural network for classification. In project two, we developed techniques for sensory data fusion. The PCNN algorithm was implemented and tested on a B14 mobile robot. The PCNN-based features were extracted from the images taken from the robot vision system and used in conjunction with the map generated by data fusion of the sonar and wheel encoder data for the navigation of the mobile robot. In our third project, we applied the PCNN for speaker recognition. The spectrogram image of speech signals are fed into the PCNN to produce invariant feature icons which are then fed into a feedforward neural network for speaker identification.

Reconfigurable Control with Neural Network Augmentation for a Modified F-15 Aircraft

NASA Technical Reports Server (NTRS)

Burken, John J.

2007-01-01

This paper describes the performance of a simplified dynamic inversion controller with neural network supplementation. This 6 DOF (Degree-of-Freedom) simulation study focuses on the results with and without adaptation of neural networks using a simulation of the NASA modified F-15 which has canards. One area of interest is the performance of a simulated surface failure while attempting to minimize the inertial cross coupling effect of a [B] matrix failure (a control derivative anomaly associated with a jammed or missing control surface). Another area of interest and presented is simulated aerodynamic failures ([A] matrix) such as a canard failure. The controller uses explicit models to produce desired angular rate commands. The dynamic inversion calculates the necessary surface commands to achieve the desired rates. The simplified dynamic inversion uses approximate short period and roll axis dynamics. Initial results indicated that the transient response for a [B] matrix failure using a Neural Network (NN) improved the control behavior when compared to not using a neural network for a given failure, However, further evaluation of the controller was comparable, with objections io the cross coupling effects (after changes were made to the controller). This paper describes the methods employed to reduce the cross coupling effect and maintain adequate tracking errors. The IA] matrix failure results show that control of the aircraft without adaptation is more difficult [leas damped) than with active neural networks, Simulation results show Neural Network augmentation of the controller improves performance in terms of backing error and cross coupling reduction and improved performance with aerodynamic-type failures.

Pilots Rate Augmented Generalized Predictive Control for Reconfiguration

NASA Technical Reports Server (NTRS)

Soloway, Don; Haley, Pam

2004-01-01

The objective of this paper is to report the results from the research being conducted in reconfigurable fight controls at NASA Ames. A study was conducted with three NASA Dryden test pilots to evaluate two approaches of reconfiguring an aircraft's control system when failures occur in the control surfaces and engine. NASA Ames is investigating both a Neural Generalized Predictive Control scheme and a Neural Network based Dynamic Inverse controller. This paper highlights the Predictive Control scheme where a simple augmentation to reduce zero steady-state error led to the neural network predictor model becoming redundant for the task. Instead of using a neural network predictor model, a nominal single point linear model was used and then augmented with an error corrector. This paper shows that the Generalized Predictive Controller and the Dynamic Inverse Neural Network controller perform equally well at reconfiguration, but with less rate requirements from the actuators. Also presented are the pilot ratings for each controller for various failure scenarios and two samples of the required control actuation during reconfiguration. Finally, the paper concludes by stepping through the Generalized Predictive Control's reconfiguration process for an elevator failure.

Neural associative memories for the integration of language, vision and action in an autonomous agent.

PubMed

Markert, H; Kaufmann, U; Kara Kayikci, Z; Palm, G

2009-03-01

Language understanding is a long-standing problem in computer science. However, the human brain is capable of processing complex languages with seemingly no difficulties. This paper shows a model for language understanding using biologically plausible neural networks composed of associative memories. The model is able to deal with ambiguities on the single word and grammatical level. The language system is embedded into a robot in order to demonstrate the correct semantical understanding of the input sentences by letting the robot perform corresponding actions. For that purpose, a simple neural action planning system has been combined with neural networks for visual object recognition and visual attention control mechanisms.

A Lagrangian Formulation of Neural Networks I: Theory and Analog Dynamics

NASA Technical Reports Server (NTRS)

Mjolsness, Eric; Miranker, Willard L.

1997-01-01

We expand the mathematicla apparatus for relaxation networks, which conventionally consists of an objective function E and a dynamics given by a system of differenctial equations along whose trajectories E is diminished.

Fuzzy-Neural Controller in Service Requests Distribution Broker for SOA-Based Systems

NASA Astrophysics Data System (ADS)

Fras, Mariusz; Zatwarnicka, Anna; Zatwarnicki, Krzysztof

The evolution of software architectures led to the rising importance of the Service Oriented Architecture (SOA) concept. This architecture paradigm support building flexible distributed service systems. In the paper the architecture of service request distribution broker designed for use in SOA-based systems is proposed. The broker is built with idea of fuzzy control. The functional and non-functional request requirements in conjunction with monitoring of execution and communication links are used to distribute requests. Decisions are made with use of fuzzy-neural network.

Optimizing Virtual Network Functions Placement in Virtual Data Center Infrastructure Using Machine Learning

NASA Astrophysics Data System (ADS)

Bolodurina, I. P.; Parfenov, D. I.

2018-01-01

We have elaborated a neural network model of virtual network flow identification based on the statistical properties of flows circulating in the network of the data center and characteristics that describe the content of packets transmitted through network objects. This enabled us to establish the optimal set of attributes to identify virtual network functions. We have established an algorithm for optimizing the placement of virtual data functions using the data obtained in our research. Our approach uses a hybrid method of visualization using virtual machines and containers, which enables to reduce the infrastructure load and the response time in the network of the virtual data center. The algorithmic solution is based on neural networks, which enables to scale it at any number of the network function copies.

A Neural Network Aero Design System for Advanced Turbo-Engines

NASA Technical Reports Server (NTRS)

Sanz, Jose M.

1999-01-01

An inverse design method calculates the blade shape that produces a prescribed input pressure distribution. By controlling this input pressure distribution the aerodynamic design objectives can easily be met. Because of the intrinsic relationship between pressure distribution and airfoil physical properties, a Neural Network can be trained to choose the optimal pressure distribution that would meet a set of physical requirements. Neural network systems have been attempted in the context of direct design methods. From properties ascribed to a set of blades the neural network is trained to infer the properties of an 'interpolated' blade shape. The problem is that, especially in transonic regimes where we deal with intrinsically non linear and ill posed problems, small perturbations of the blade shape can produce very large variations of the flow parameters. It is very unlikely that, under these circumstances, a neural network will be able to find the proper solution. The unique situation in the present method is that the neural network can be trained to extract the required input pressure distribution from a database of pressure distributions while the inverse method will still compute the exact blade shape that corresponds to this 'interpolated' input pressure distribution. In other words, the interpolation process is transferred to a smoother problem, namely, finding what pressure distribution would produce the required flow conditions and, once this is done, the inverse method will compute the exact solution for this problem. The use of neural network is, in this context, highly related to the use of proper optimization techniques. The optimization is used essentially as an automation procedure to force the input pressure distributions to achieve the required aero and structural design parameters. A multilayered feed forward network with back-propagation is used to train the system for pattern association and classification.

A Physics-driven Neural Networks-based Simulation System (PhyNNeSS) for multimodal interactive virtual environments involving nonlinear deformable objects

PubMed Central

De, Suvranu; Deo, Dhannanjay; Sankaranarayanan, Ganesh; Arikatla, Venkata S.

2012-01-01

Background While an update rate of 30 Hz is considered adequate for real time graphics, a much higher update rate of about 1 kHz is necessary for haptics. Physics-based modeling of deformable objects, especially when large nonlinear deformations and complex nonlinear material properties are involved, at these very high rates is one of the most challenging tasks in the development of real time simulation systems. While some specialized solutions exist, there is no general solution for arbitrary nonlinearities. Methods In this work we present PhyNNeSS - a Physics-driven Neural Networks-based Simulation System - to address this long-standing technical challenge. The first step is an off-line pre-computation step in which a database is generated by applying carefully prescribed displacements to each node of the finite element models of the deformable objects. In the next step, the data is condensed into a set of coefficients describing neurons of a Radial Basis Function network (RBFN). During real-time computation, these neural networks are used to reconstruct the deformation fields as well as the interaction forces. Results We present realistic simulation examples from interactive surgical simulation with real time force feedback. As an example, we have developed a deformable human stomach model and a Penrose-drain model used in the Fundamentals of Laparoscopic Surgery (FLS) training tool box. Conclusions A unique computational modeling system has been developed that is capable of simulating the response of nonlinear deformable objects in real time. The method distinguishes itself from previous efforts in that a systematic physics-based pre-computational step allows training of neural networks which may be used in real time simulations. We show, through careful error analysis, that the scheme is scalable, with the accuracy being controlled by the number of neurons used in the simulation. PhyNNeSS has been integrated into SoFMIS (Software Framework for Multimodal Interactive Simulation) for general use. PMID:22629108

Machine Learning and Infrared Thermography for Fiber Orientation Assessment on Randomly-Oriented Strands Parts.

PubMed

Fernandes, Henrique; Zhang, Hai; Figueiredo, Alisson; Malheiros, Fernando; Ignacio, Luis Henrique; Sfarra, Stefano; Ibarra-Castanedo, Clemente; Guimaraes, Gilmar; Maldague, Xavier

2018-01-19

The use of fiber reinforced materials such as randomly-oriented strands has grown in recent years, especially for manufacturing of aerospace composite structures. This growth is mainly due to their advantageous properties: they are lighter and more resistant to corrosion when compared to metals and are more easily shaped than continuous fiber composites. The resistance and stiffness of these materials are directly related to their fiber orientation. Thus, efficient approaches to assess their fiber orientation are in demand. In this paper, a non-destructive evaluation method is applied to assess the fiber orientation on laminates reinforced with randomly-oriented strands. More specifically, a method called pulsed thermal ellipsometry combined with an artificial neural network, a machine learning technique, is used in order to estimate the fiber orientation on the surface of inspected parts. Results showed that the method can be potentially used to inspect large areas with good accuracy and speed.

Machine Learning and Infrared Thermography for Fiber Orientation Assessment on Randomly-Oriented Strands Parts

PubMed Central

Maldague, Xavier

2018-01-01

The use of fiber reinforced materials such as randomly-oriented strands has grown in recent years, especially for manufacturing of aerospace composite structures. This growth is mainly due to their advantageous properties: they are lighter and more resistant to corrosion when compared to metals and are more easily shaped than continuous fiber composites. The resistance and stiffness of these materials are directly related to their fiber orientation. Thus, efficient approaches to assess their fiber orientation are in demand. In this paper, a non-destructive evaluation method is applied to assess the fiber orientation on laminates reinforced with randomly-oriented strands. More specifically, a method called pulsed thermal ellipsometry combined with an artificial neural network, a machine learning technique, is used in order to estimate the fiber orientation on the surface of inspected parts. Results showed that the method can be potentially used to inspect large areas with good accuracy and speed. PMID:29351240

Generating description with multi-feature fusion and saliency maps of image

NASA Astrophysics Data System (ADS)

Liu, Lisha; Ding, Yuxuan; Tian, Chunna; Yuan, Bo

2018-04-01

Generating description for an image can be regard as visual understanding. It is across artificial intelligence, machine learning, natural language processing and many other areas. In this paper, we present a model that generates description for images based on RNN (recurrent neural network) with object attention and multi-feature of images. The deep recurrent neural networks have excellent performance in machine translation, so we use it to generate natural sentence description for images. The proposed method uses single CNN (convolution neural network) that is trained on ImageNet to extract image features. But we think it can not adequately contain the content in images, it may only focus on the object area of image. So we add scene information to image feature using CNN which is trained on Places205. Experiments show that model with multi-feature extracted by two CNNs perform better than which with a single feature. In addition, we make saliency weights on images to emphasize the salient objects in images. We evaluate our model on MSCOCO based on public metrics, and the results show that our model performs better than several state-of-the-art methods.

Upon the opportunity to apply ART2 Neural Network for clusterization of biodiesel fuels

NASA Astrophysics Data System (ADS)

Petkov, T.; Mustafa, Z.; Sotirov, S.; Milina, R.; Moskovkina, M.

2016-03-01

A chemometric approach using artificial neural network for clusterization of biodiesels was developed. It is based on artificial ART2 neural network. Gas chromatography (GC) and Gas Chromatography - mass spectrometry (GC-MS) were used for quantitative and qualitative analysis of biodiesels, produced from different feedstocks, and FAME (fatty acid methyl esters) profiles were determined. Totally 96 analytical results for 7 different classes of biofuel plants: sunflower, rapeseed, corn, soybean, palm, peanut, "unknown" were used as objects. The analysis of biodiesels showed the content of five major FAME (C16:0, C18:0, C18:1, C18:2, C18:3) and those components were used like inputs in the model. After training with 6 samples, for which the origin was known, ANN was verified and tested with ninety "unknown" samples. The present research demonstrated the successful application of neural network for recognition of biodiesels according to their feedstock which give information upon their properties and handling.

Artificial Neural Networks for Processing Graphs with Application to Image Understanding: A Survey

NASA Astrophysics Data System (ADS)

Bianchini, Monica; Scarselli, Franco

In graphical pattern recognition, each data is represented as an arrangement of elements, that encodes both the properties of each element and the relations among them. Hence, patterns are modelled as labelled graphs where, in general, labels can be attached to both nodes and edges. Artificial neural networks able to process graphs are a powerful tool for addressing a great variety of real-world problems, where the information is naturally organized in entities and relationships among entities and, in fact, they have been widely used in computer vision, f.i. in logo recognition, in similarity retrieval, and for object detection. In this chapter, we propose a survey of neural network models able to process structured information, with a particular focus on those architectures tailored to address image understanding applications. Starting from the original recursive model (RNNs), we subsequently present different ways to represent images - by trees, forests of trees, multiresolution trees, directed acyclic graphs with labelled edges, general graphs - and, correspondingly, neural network architectures appropriate to process such structures.

Human Age Recognition by Electrocardiogram Signal Based on Artificial Neural Network

NASA Astrophysics Data System (ADS)

Dasgupta, Hirak

2016-12-01

The objective of this work is to make a neural network function approximation model to detect human age from the electrocardiogram (ECG) signal. The input vectors of the neural network are the Katz fractal dimension of the ECG signal, frequencies in the QRS complex, male or female (represented by numeric constant) and the average of successive R-R peak distance of a particular ECG signal. The QRS complex has been detected by short time Fourier transform algorithm. The successive R peak has been detected by, first cutting the signal into periods by auto-correlation method and then finding the absolute of the highest point in each period. The neural network used in this problem consists of two layers, with Sigmoid neuron in the input and linear neuron in the output layer. The result shows the mean of errors as -0.49, 1.03, 0.79 years and the standard deviation of errors as 1.81, 1.77, 2.70 years during training, cross validation and testing with unknown data sets, respectively.

Modeling gravity-dependent plasticity of the angular vestibuloocular reflex with a physiologically based neural network.

PubMed

Xiang, Yongqing; Yakushin, Sergei B; Cohen, Bernard; Raphan, Theodore

2006-12-01

A neural network model was developed to explain the gravity-dependent properties of gain adaptation of the angular vestibuloocular reflex (aVOR). Gain changes are maximal at the head orientation where the gain is adapted and decrease as the head is tilted away from that position and can be described by the sum of gravity-independent and gravity-dependent components. The adaptation process was modeled by modifying the weights and bias values of a three-dimensional physiologically based neural network of canal-otolith-convergent neurons that drive the aVOR. Model parameters were trained using experimental vertical aVOR gain values. The learning rule aimed to reduce the error between eye velocities obtained from experimental gain values and model output in the position of adaptation. Although the model was trained only at specific head positions, the model predicted the experimental data at all head positions in three dimensions. Altering the relative learning rates of the weights and bias improved the model-data fits. Model predictions in three dimensions compared favorably with those of a double-sinusoid function, which is a fit that minimized the mean square error at every head position and served as the standard by which we compared the model predictions. The model supports the hypothesis that gravity-dependent adaptation of the aVOR is realized in three dimensions by a direct otolith input to canal-otolith neurons, whose canal sensitivities are adapted by the visual-vestibular mismatch. The adaptation is tuned by how the weights from otolith input to the canal-otolith-convergent neurons are adapted for a given head orientation.

An integrated GIS-based data model for multimodal urban public transportation analysis and management

NASA Astrophysics Data System (ADS)

Chen, Shaopei; Tan, Jianjun; Ray, C.; Claramunt, C.; Sun, Qinqin

2008-10-01

Diversity is one of the main characteristics of transportation data collected from multiple sources or formats, which can be extremely complex and disparate. Moreover, these multimodal transportation data are usually characterised by spatial and temporal properties. Multimodal transportation network data modelling involves both an engineering and research domain that has attracted the design of a number of spatio-temporal data models in the geographic information system (GIS). However, the application of these specific models to multimodal transportation network is still a challenging task. This research addresses this challenge from both integrated multimodal data organization and object-oriented modelling perspectives, that is, how a complex urban transportation network should be organized, represented and modeled appropriately when considering a multimodal point of view, and using object-oriented modelling method. We proposed an integrated GIS-based data model for multimodal urban transportation network that lays a foundation to enhance the multimodal transportation network analysis and management. This modelling method organizes and integrates multimodal transit network data, and supports multiple representations for spatio-temporal objects and relationship as both visual and graphic views. The data model is expressed by using a spatio-temporal object-oriented modelling method, i.e., the unified modelling language (UML) extended to spatial and temporal plug-in for visual languages (PVLs), which provides an essential support to the spatio-temporal data modelling for transportation GIS.

Deep Neural Networks Reveal a Gradient in the Complexity of Neural Representations across the Ventral Stream.

PubMed

Güçlü, Umut; van Gerven, Marcel A J

2015-07-08

Converging evidence suggests that the primate ventral visual pathway encodes increasingly complex stimulus features in downstream areas. We quantitatively show that there indeed exists an explicit gradient for feature complexity in the ventral pathway of the human brain. This was achieved by mapping thousands of stimulus features of increasing complexity across the cortical sheet using a deep neural network. Our approach also revealed a fine-grained functional specialization of downstream areas of the ventral stream. Furthermore, it allowed decoding of representations from human brain activity at an unsurpassed degree of accuracy, confirming the quality of the developed approach. Stimulus features that successfully explained neural responses indicate that population receptive fields were explicitly tuned for object categorization. This provides strong support for the hypothesis that object categorization is a guiding principle in the functional organization of the primate ventral stream. Copyright © 2015 the authors 0270-6474/15/3510005-10$15.00/0.

Computer-assisted cervical cancer screening using neural networks.

PubMed

Mango, L J

1994-03-15

A practical and effective system for the computer-assisted screening of conventionally prepared cervical smears is presented and described. Recent developments in neural network technology have made computerized analysis of the complex cellular scenes found on Pap smears possible. The PAPNET Cytological Screening System uses neural networks to automatically analyze conventional smears by locating and recognizing potentially abnormal cells. It then displays images of these objects for review and final diagnosis by qualified cytologists. The results of the studies presented indicate that the PAPNET system could be a useful tool for both the screening and rescreening of cervical smears. In addition, the system has been shown to be sensitive to some types of abnormalities which have gone undetected during manual screening.

Pulse-coupled neural network implementation in FPGA

NASA Astrophysics Data System (ADS)

Waldemark, Joakim T. A.; Lindblad, Thomas; Lindsey, Clark S.; Waldemark, Karina E.; Oberg, Johnny; Millberg, Mikael

1998-03-01

Pulse Coupled Neural Networks (PCNN) are biologically inspired neural networks, mainly based on studies of the visual cortex of small mammals. The PCNN is very well suited as a pre- processor for image processing, particularly in connection with object isolation, edge detection and segmentation. Several implementations of PCNN on von Neumann computers, as well as on special parallel processing hardware devices (e.g. SIMD), exist. However, these implementations are not as flexible as required for many applications. Here we present an implementation in Field Programmable Gate Arrays (FPGA) together with a performance analysis. The FPGA hardware implementation may be considered a platform for further, extended implementations and easily expanded into various applications. The latter may include advanced on-line image analysis with close to real-time performance.

3-d interpolation in object perception: evidence from an objective performance paradigm.

PubMed

Kellman, Philip J; Garrigan, Patrick; Shipley, Thomas F; Yin, Carol; Machado, Liana

2005-06-01

Object perception requires interpolation processes that connect visible regions despite spatial gaps. Some research has suggested that interpolation may be a 3-D process, but objective performance data and evidence about the conditions leading to interpolation are needed. The authors developed an objective performance paradigm for testing 3-D interpolation and tested a new theory of 3-D contour interpolation, termed 3-D relatability. The theory indicates for a given edge which orientations and positions of other edges in space may be connected to it by interpolation. Results of 5 experiments showed that processing of orientation relations in 3-D relatable displays was superior to processing in 3-D nonrelatable displays and that these effects depended on object formation. 3-D interpolation and 3-D relatabilty are discussed in terms of their implications for computational and neural models of object perception, which have typically been based on 2-D-orientation-sensitive units. ((c) 2005 APA, all rights reserved).

An insect-inspired model for visual binding I: learning objects and their characteristics.

PubMed

Northcutt, Brandon D; Dyhr, Jonathan P; Higgins, Charles M

2017-04-01

Visual binding is the process of associating the responses of visual interneurons in different visual submodalities all of which are responding to the same object in the visual field. Recently identified neuropils in the insect brain termed optic glomeruli reside just downstream of the optic lobes and have an internal organization that could support visual binding. Working from anatomical similarities between optic and olfactory glomeruli, we have developed a model of visual binding based on common temporal fluctuations among signals of independent visual submodalities. Here we describe and demonstrate a neural network model capable both of refining selectivity of visual information in a given visual submodality, and of associating visual signals produced by different objects in the visual field by developing inhibitory neural synaptic weights representing the visual scene. We also show that this model is consistent with initial physiological data from optic glomeruli. Further, we discuss how this neural network model may be implemented in optic glomeruli at a neuronal level.

Non-invasive classification of gas-liquid two-phase horizontal flow regimes using an ultrasonic Doppler sensor and a neural network

NASA Astrophysics Data System (ADS)

Musa Abbagoni, Baba; Yeung, Hoi

2016-08-01

The identification of flow pattern is a key issue in multiphase flow which is encountered in the petrochemical industry. It is difficult to identify the gas-liquid flow regimes objectively with the gas-liquid two-phase flow. This paper presents the feasibility of a clamp-on instrument for an objective flow regime classification of two-phase flow using an ultrasonic Doppler sensor and an artificial neural network, which records and processes the ultrasonic signals reflected from the two-phase flow. Experimental data is obtained on a horizontal test rig with a total pipe length of 21 m and 5.08 cm internal diameter carrying air-water two-phase flow under slug, elongated bubble, stratified-wavy and, stratified flow regimes. Multilayer perceptron neural networks (MLPNNs) are used to develop the classification model. The classifier requires features as an input which is representative of the signals. Ultrasound signal features are extracted by applying both power spectral density (PSD) and discrete wavelet transform (DWT) methods to the flow signals. A classification scheme of ‘1-of-C coding method for classification’ was adopted to classify features extracted into one of four flow regime categories. To improve the performance of the flow regime classifier network, a second level neural network was incorporated by using the output of a first level networks feature as an input feature. The addition of the two network models provided a combined neural network model which has achieved a higher accuracy than single neural network models. Classification accuracies are evaluated in the form of both the PSD and DWT features. The success rates of the two models are: (1) using PSD features, the classifier missed 3 datasets out of 24 test datasets of the classification and scored 87.5% accuracy; (2) with the DWT features, the network misclassified only one data point and it was able to classify the flow patterns up to 95.8% accuracy. This approach has demonstrated the success of a clamp-on ultrasound sensor for flow regime classification that would be possible in industry practice. It is considerably more promising than other techniques as it uses a non-invasive and non-radioactive sensor.

A Collaborative Neurodynamic Approach to Multiple-Objective Distributed Optimization.

PubMed

Yang, Shaofu; Liu, Qingshan; Wang, Jun

2018-04-01

This paper is concerned with multiple-objective distributed optimization. Based on objective weighting and decision space decomposition, a collaborative neurodynamic approach to multiobjective distributed optimization is presented. In the approach, a system of collaborative neural networks is developed to search for Pareto optimal solutions, where each neural network is associated with one objective function and given constraints. Sufficient conditions are derived for ascertaining the convergence to a Pareto optimal solution of the collaborative neurodynamic system. In addition, it is proved that each connected subsystem can generate a Pareto optimal solution when the communication topology is disconnected. Then, a switching-topology-based method is proposed to compute multiple Pareto optimal solutions for discretized approximation of Pareto front. Finally, simulation results are discussed to substantiate the performance of the collaborative neurodynamic approach. A portfolio selection application is also given.

Automatic Railway Traffic Object Detection System Using Feature Fusion Refine Neural Network under Shunting Mode.

PubMed

Ye, Tao; Wang, Baocheng; Song, Ping; Li, Juan

2018-06-12

Many accidents happen under shunting mode when the speed of a train is below 45 km/h. In this mode, train attendants observe the railway condition ahead using the traditional manual method and tell the observation results to the driver in order to avoid danger. To address this problem, an automatic object detection system based on convolutional neural network (CNN) is proposed to detect objects ahead in shunting mode, which is called Feature Fusion Refine neural network (FR-Net). It consists of three connected modules, i.e., the depthwise-pointwise convolution, the coarse detection module, and the object detection module. Depth-wise-pointwise convolutions are used to improve the detection in real time. The coarse detection module coarsely refine the locations and sizes of prior anchors to provide better initialization for the subsequent module and also reduces search space for the classification, whereas the object detection module aims to regress accurate object locations and predict the class labels for the prior anchors. The experimental results on the railway traffic dataset show that FR-Net achieves 0.8953 mAP with 72.3 FPS performance on a machine with a GeForce GTX1080Ti with the input size of 320 × 320 pixels. The results imply that FR-Net takes a good tradeoff both on effectiveness and real time performance. The proposed method can meet the needs of practical application in shunting mode.

Multisensor fusion for 3-D defect characterization using wavelet basis function neural networks

NASA Astrophysics Data System (ADS)

Lim, Jaein; Udpa, Satish S.; Udpa, Lalita; Afzal, Muhammad

2001-04-01

The primary objective of multi-sensor data fusion, which offers both quantitative and qualitative benefits, has the ability to draw inferences that may not be feasible with data from a single sensor alone. In this paper, data from two sets of sensors are fused to estimate the defect profile from magnetic flux leakage (MFL) inspection data. The two sensors measure the axial and circumferential components of the MFL. Data is fused at the signal level. If the flux is oriented axially, the samples of the axial signal are measured along a direction parallel to the flaw, while the circumferential signal is measured in a direction that is perpendicular to the flaw. The two signals are combined as the real and imaginary components of a complex valued signal. Signals from an array of sensors are arranged in contiguous rows to obtain a complex valued image. A boundary extraction algorithm is used to extract the defect areas in the image. Signals from the defect regions are then processed to minimize noise and the effects of lift-off. Finally, a wavelet basis function (WBF) neural network is employed to map the complex valued image appropriately to obtain the geometrical profile of the defect. The feasibility of the approach was evaluated using the data obtained from the MFL inspection of natural gas transmission pipelines. Results show the effectiveness of the approach.

Implementing a Bayes Filter in a Neural Circuit: The Case of Unknown Stimulus Dynamics.

PubMed

Sokoloski, Sacha

2017-09-01

In order to interact intelligently with objects in the world, animals must first transform neural population responses into estimates of the dynamic, unknown stimuli that caused them. The Bayesian solution to this problem is known as a Bayes filter, which applies Bayes' rule to combine population responses with the predictions of an internal model. The internal model of the Bayes filter is based on the true stimulus dynamics, and in this note, we present a method for training a theoretical neural circuit to approximately implement a Bayes filter when the stimulus dynamics are unknown. To do this we use the inferential properties of linear probabilistic population codes to compute Bayes' rule and train a neural network to compute approximate predictions by the method of maximum likelihood. In particular, we perform stochastic gradient descent on the negative log-likelihood of the neural network parameters with a novel approximation of the gradient. We demonstrate our methods on a finite-state, a linear, and a nonlinear filtering problem and show how the hidden layer of the neural network develops tuning curves consistent with findings in experimental neuroscience.

Development of Methodologies for IV and V of Neural Networks

NASA Technical Reports Server (NTRS)

Taylor, Brian; Darrah, Marjorie

2003-01-01

Non-deterministic systems often rely upon neural network (NN) technology to "lean" to manage flight systems under controlled conditions using carefully chosen training sets. How can these adaptive systems be certified to ensure that they will become increasingly efficient and behave appropriately in real-time situations? The bulk of Independent Verification and Validation (IV&V) research of non-deterministic software control systems such as Adaptive Flight Controllers (AFC's) addresses NNs in well-behaved and constrained environments such as simulations and strict process control. However, neither substantive research, nor effective IV&V techniques have been found to address AFC's learning in real-time and adapting to live flight conditions. Adaptive flight control systems offer good extensibility into commercial aviation as well as military aviation and transportation. Consequently, this area of IV&V represents an area of growing interest and urgency. ISR proposes to further the current body of knowledge to meet two objectives: Research the current IV&V methods and assess where these methods may be applied toward a methodology for the V&V of Neural Network; and identify effective methods for IV&V of NNs that learn in real-time, including developing a prototype test bed for IV&V of AFC's. Currently. no practical method exists. lSR will meet these objectives through the tasks identified and described below. First, ISR will conduct a literature review of current IV&V technology. TO do this, ISR will collect the existing body of research on IV&V of non-deterministic systems and neural network. ISR will also develop the framework for disseminating this information through specialized training. This effort will focus on developing NASA's capability to conduct IV&V of neural network systems and to provide training to meet the increasing need for IV&V expertise in such systems.

Identifing Atmospheric Pollutant Sources Using Artificial Neural Networks

NASA Astrophysics Data System (ADS)

Paes, F. F.; Campos, H. F.; Luz, E. P.; Carvalho, A. R.

2008-05-01

The estimation of the area source pollutant strength is a relevant issue for atmospheric environment. This characterizes an inverse problem in the atmospheric pollution dispersion. In the inverse analysis, an area source domain is considered, where the strength of such area source term is assumed unknown. The inverse problem is solved by using a supervised artificial neural network: multi-layer perceptron. The conection weights of the neural network are computed from delta rule - learning process. The neural network inversion is compared with results from standard inverse analysis (regularized inverse solution). In the regularization method, the inverse problem is formulated as a non-linear optimization approach, whose the objective function is given by the square difference between the measured pollutant concentration and the mathematical models, associated with a regularization operator. In our numerical experiments, the forward problem is addressed by a source-receptor scheme, where a regressive Lagrangian model is applied to compute the transition matrix. The second order maximum entropy regularization is used, and the regularization parameter is calculated by the L-curve technique. The objective function is minimized employing a deterministic scheme (a quasi-Newton algorithm) [1] and a stochastic technique (PSO: particle swarm optimization) [2]. The inverse problem methodology is tested with synthetic observational data, from six measurement points in the physical domain. The best inverse solutions were obtained with neural networks. References: [1] D. R. Roberti, D. Anfossi, H. F. Campos Velho, G. A. Degrazia (2005): Estimating Emission Rate and Pollutant Source Location, Ciencia e Natura, p. 131-134. [2] E.F.P. da Luz, H.F. de Campos Velho, J.C. Becceneri, D.R. Roberti (2007): Estimating Atmospheric Area Source Strength Through Particle Swarm Optimization. Inverse Problems, Desing and Optimization Symposium IPDO-2007, April 16-18, Miami (FL), USA, vol 1, p. 354-359.

Neural networks for simultaneous classification and parameter estimation in musical instrument control

NASA Astrophysics Data System (ADS)

Lee, Michael; Freed, Adrian; Wessel, David

1992-08-01

In this report we present our tools for prototyping adaptive user interfaces in the context of real-time musical instrument control. Characteristic of most human communication is the simultaneous use of classified events and estimated parameters. We have integrated a neural network object into the MAX language to explore adaptive user interfaces that considers these facets of human communication. By placing the neural processing in the context of a flexible real-time musical programming environment, we can rapidly prototype experiments on applications of adaptive interfaces and learning systems to musical problems. We have trained networks to recognize gestures from a Mathews radio baton, Nintendo Power GloveTM, and MIDI keyboard gestural input devices. In one experiment, a network successfully extracted classification and attribute data from gestural contours transduced by a continuous space controller, suggesting their application in the interpretation of conducting gestures and musical instrument control. We discuss network architectures, low-level features extracted for the networks to operate on, training methods, and musical applications of adaptive techniques.

A conditioned visual orientation requires the ellipsoid body in Drosophila

PubMed Central

Guo, Chao; Du, Yifei; Yuan, Deliang; Li, Meixia; Gong, Haiyun; Gong, Zhefeng

2015-01-01

Orientation, the spatial organization of animal behavior, is an essential faculty of animals. Bacteria and lower animals such as insects exhibit taxis, innate orientation behavior, directly toward or away from a directional cue. Organisms can also orient themselves at a specific angle relative to the cues. In this study, using Drosophila as a model system, we established a visual orientation conditioning paradigm based on a flight simulator in which a stationary flying fly could control the rotation of a visual object. By coupling aversive heat shocks to a fly's orientation toward one side of the visual object, we found that the fly could be conditioned to orientate toward the left or right side of the frontal visual object and retain this conditioned visual orientation. The lower and upper visual fields have different roles in conditioned visual orientation. Transfer experiments showed that conditioned visual orientation could generalize between visual targets of different sizes, compactness, or vertical positions, but not of contour orientation. Rut—Type I adenylyl cyclase and Dnc—phosphodiesterase were dispensable for visual orientation conditioning. Normal activity and scb signaling in R3/R4d neurons of the ellipsoid body were required for visual orientation conditioning. Our studies established a visual orientation conditioning paradigm and examined the behavioral properties and neural circuitry of visual orientation, an important component of the insect's spatial navigation. PMID:25512578

Neural Networks for Signal Processing and Control

NASA Astrophysics Data System (ADS)

Hesselroth, Ted Daniel

Neural networks are developed for controlling a robot-arm and camera system and for processing images. The networks are based upon computational schemes that may be found in the brain. In the first network, a neural map algorithm is employed to control a five-joint pneumatic robot arm and gripper through feedback from two video cameras. The pneumatically driven robot arm employed shares essential mechanical characteristics with skeletal muscle systems. To control the position of the arm, 200 neurons formed a network representing the three-dimensional workspace embedded in a four-dimensional system of coordinates from the two cameras, and learned a set of pressures corresponding to the end effector positions, as well as a set of Jacobian matrices for interpolating between these positions. Because of the properties of the rubber-tube actuators of the arm, the position as a function of supplied pressure is nonlinear, nonseparable, and exhibits hysteresis. Nevertheless, through the neural network learning algorithm the position could be controlled to an accuracy of about one pixel (~3 mm) after two hundred learning steps. Applications of repeated corrections in each step via the Jacobian matrices leads to a very robust control algorithm since the Jacobians learned by the network have to satisfy the weak requirement that they yield a reduction of the distance between gripper and target. The second network is proposed as a model for the mammalian vision system in which backward connections from the primary visual cortex (V1) to the lateral geniculate nucleus play a key role. The application of hebbian learning to the forward and backward connections causes the formation of receptive fields which are sensitive to edges, bars, and spatial frequencies of preferred orientations. The receptive fields are learned in such a way as to maximize the rate of transfer of information from the LGN to V1. Orientational preferences are organized into a feature map in the primary visual cortex by the application of lateral interactions during the learning phase. The organization of the mature network is compared to that found in the macaque monkey by several analytical tests. The capacity of the network to process images is investigated. By a method of reconstructing the input images in terms of V1 activities, the simulations show that images can be faithfully represented in V1 by the proposed network. The signal-to-noise ratio of the image is improved by the representation, and compression ratios of well over two-hundred are possible. Lateral interactions between V1 neurons sharpen their orientational tuning. We further study the dynamics of the processing, showing that the rate of decrease of the error of the reconstruction is maximized for the receptive fields used. Lastly, we employ a Fokker-Planck equation for a more detailed prediction of the error value vs. time. The Fokker-Planck equation for an underdamped system with a driving force is derived, yielding an energy-dependent diffusion coefficient which is the integral of the spectral densities of the force and the velocity of the system. The theory is applied to correlated noise activation and resonant activation. Simulation results for the error of the network vs time are compared to the solution of the Fokker-Planck equation.

A link prediction method for heterogeneous networks based on BP neural network

NASA Astrophysics Data System (ADS)

Li, Ji-chao; Zhao, Dan-ling; Ge, Bing-Feng; Yang, Ke-Wei; Chen, Ying-Wu

2018-04-01

Most real-world systems, composed of different types of objects connected via many interconnections, can be abstracted as various complex heterogeneous networks. Link prediction for heterogeneous networks is of great significance for mining missing links and reconfiguring networks according to observed information, with considerable applications in, for example, friend and location recommendations and disease-gene candidate detection. In this paper, we put forward a novel integrated framework, called MPBP (Meta-Path feature-based BP neural network model), to predict multiple types of links for heterogeneous networks. More specifically, the concept of meta-path is introduced, followed by the extraction of meta-path features for heterogeneous networks. Next, based on the extracted meta-path features, a supervised link prediction model is built with a three-layer BP neural network. Then, the solution algorithm of the proposed link prediction model is put forward to obtain predicted results by iteratively training the network. Last, numerical experiments on the dataset of examples of a gene-disease network and a combat network are conducted to verify the effectiveness and feasibility of the proposed MPBP. It shows that the MPBP with very good performance is superior to the baseline methods.

Neural Network Classification of Receiver Functions as a Step Towards Automatic Crustal Parameter Determination

NASA Astrophysics Data System (ADS)

Jemberie, A.; Dugda, M. T.; Reusch, D.; Nyblade, A.

2006-12-01

Neural networks are decision making mathematical/engineering tools, which if trained properly, can do jobs automatically (and objectively) that normally require particular expertise and/or tedious repetition. Here we explore two techniques from the field of artificial neural networks (ANNs) that seek to reduce the time requirements and increase the objectivity of quality control (QC) and Event Identification (EI) on seismic datasets. We explore to apply the multiplayer Feed Forward (FF) Artificial Neural Networks (ANN) and Self- Organizing Maps (SOM) in combination with Hk stacking of receiver functions in an attempt to test the extent of the usefulness of automatic classification of receiver functions for crustal parameter determination. Feed- forward ANNs (FFNNs) are a supervised classification tool while self-organizing maps (SOMs) are able to provide unsupervised classification of large, complex geophysical data sets into a fixed number of distinct generalized patterns or modes. Hk stacking is a methodology that is used to stack receiver functions based on the relative arrival times of P-to-S converted phase and next two reverberations to determine crustal thickness H and Vp-to-Vs ratio (k). We use receiver functions from teleseismic events recorded by the 2000- 2002 Ethiopia Broadband Seismic Experiment. Preliminary results of applying FFNN neural network and Hk stacking of receiver functions for automatic receiver functions classification as a step towards an effort of automatic crustal parameter determination look encouraging. After training a FFNN neural network, the network could classify the best receiver functions from bad ones with a success rate of about 75 to 95%. Applying H? stacking on the receiver functions classified by this FFNN as the best receiver functions, we could obtain crustal thickness and Vp/Vs ratio of 31±4 km and 1.75±0.05, respectively, for the crust beneath station ARBA in the Main Ethiopian Rift. To make comparison, we applied Hk stacking on the receiver functions which we ourselves classified as the best set and found that the crustal thickness and Vp/Vs ratio are 31±2 km and 1.75±0.02, respectively.

Deep Learning with Convolutional Neural Networks Applied to Electromyography Data: A Resource for the Classification of Movements for Prosthetic Hands

PubMed Central

Atzori, Manfredo; Cognolato, Matteo; Müller, Henning

2016-01-01

Natural control methods based on surface electromyography (sEMG) and pattern recognition are promising for hand prosthetics. However, the control robustness offered by scientific research is still not sufficient for many real life applications, and commercial prostheses are capable of offering natural control for only a few movements. In recent years deep learning revolutionized several fields of machine learning, including computer vision and speech recognition. Our objective is to test its methods for natural control of robotic hands via sEMG using a large number of intact subjects and amputees. We tested convolutional networks for the classification of an average of 50 hand movements in 67 intact subjects and 11 transradial amputees. The simple architecture of the neural network allowed to make several tests in order to evaluate the effect of pre-processing, layer architecture, data augmentation and optimization. The classification results are compared with a set of classical classification methods applied on the same datasets. The classification accuracy obtained with convolutional neural networks using the proposed architecture is higher than the average results obtained with the classical classification methods, but lower than the results obtained with the best reference methods in our tests. The results show that convolutional neural networks with a very simple architecture can produce accurate results comparable to the average classical classification methods. They show that several factors (including pre-processing, the architecture of the net and the optimization parameters) can be fundamental for the analysis of sEMG data. Larger networks can achieve higher accuracy on computer vision and object recognition tasks. This fact suggests that it may be interesting to evaluate if larger networks can increase sEMG classification accuracy too. PMID:27656140

Deep Learning with Convolutional Neural Networks Applied to Electromyography Data: A Resource for the Classification of Movements for Prosthetic Hands.

PubMed

Atzori, Manfredo; Cognolato, Matteo; Müller, Henning

2016-01-01

Natural control methods based on surface electromyography (sEMG) and pattern recognition are promising for hand prosthetics. However, the control robustness offered by scientific research is still not sufficient for many real life applications, and commercial prostheses are capable of offering natural control for only a few movements. In recent years deep learning revolutionized several fields of machine learning, including computer vision and speech recognition. Our objective is to test its methods for natural control of robotic hands via sEMG using a large number of intact subjects and amputees. We tested convolutional networks for the classification of an average of 50 hand movements in 67 intact subjects and 11 transradial amputees. The simple architecture of the neural network allowed to make several tests in order to evaluate the effect of pre-processing, layer architecture, data augmentation and optimization. The classification results are compared with a set of classical classification methods applied on the same datasets. The classification accuracy obtained with convolutional neural networks using the proposed architecture is higher than the average results obtained with the classical classification methods, but lower than the results obtained with the best reference methods in our tests. The results show that convolutional neural networks with a very simple architecture can produce accurate results comparable to the average classical classification methods. They show that several factors (including pre-processing, the architecture of the net and the optimization parameters) can be fundamental for the analysis of sEMG data. Larger networks can achieve higher accuracy on computer vision and object recognition tasks. This fact suggests that it may be interesting to evaluate if larger networks can increase sEMG classification accuracy too.

The Prediction of Length-of-day Variations Based on Gaussian Processes

NASA Astrophysics Data System (ADS)

Lei, Y.; Zhao, D. N.; Gao, Y. P.; Cai, H. B.

2015-01-01

Due to the complicated time-varying characteristics of the length-of-day (LOD) variations, the accuracies of traditional strategies for the prediction of the LOD variations such as the least squares extrapolation model, the time-series analysis model, and so on, have not met the requirements for real-time and high-precision applications. In this paper, a new machine learning algorithm --- the Gaussian process (GP) model is employed to forecast the LOD variations. Its prediction precisions are analyzed and compared with those of the back propagation neural networks (BPNN), general regression neural networks (GRNN) models, and the Earth Orientation Parameters Prediction Comparison Campaign (EOP PCC). The results demonstrate that the application of the GP model to the prediction of the LOD variations is efficient and feasible.

Review On Applications Of Neural Network To Computer Vision

NASA Astrophysics Data System (ADS)

Li, Wei; Nasrabadi, Nasser M.

1989-03-01

Neural network models have many potential applications to computer vision due to their parallel structures, learnability, implicit representation of domain knowledge, fault tolerance, and ability of handling statistical data. This paper demonstrates the basic principles, typical models and their applications in this field. Variety of neural models, such as associative memory, multilayer back-propagation perceptron, self-stabilized adaptive resonance network, hierarchical structured neocognitron, high order correlator, network with gating control and other models, can be applied to visual signal recognition, reinforcement, recall, stereo vision, motion, object tracking and other vision processes. Most of the algorithms have been simulated on com-puters. Some have been implemented with special hardware. Some systems use features, such as edges and profiles, of images as the data form for input. Other systems use raw data as input signals to the networks. We will present some novel ideas contained in these approaches and provide a comparison of these methods. Some unsolved problems are mentioned, such as extracting the intrinsic properties of the input information, integrating those low level functions to a high-level cognitive system, achieving invariances and other problems. Perspectives of applications of some human vision models and neural network models are analyzed.

Deep neural networks for texture classification-A theoretical analysis.

PubMed

Basu, Saikat; Mukhopadhyay, Supratik; Karki, Manohar; DiBiano, Robert; Ganguly, Sangram; Nemani, Ramakrishna; Gayaka, Shreekant

2018-01-01

We investigate the use of Deep Neural Networks for the classification of image datasets where texture features are important for generating class-conditional discriminative representations. To this end, we first derive the size of the feature space for some standard textural features extracted from the input dataset and then use the theory of Vapnik-Chervonenkis dimension to show that hand-crafted feature extraction creates low-dimensional representations which help in reducing the overall excess error rate. As a corollary to this analysis, we derive for the first time upper bounds on the VC dimension of Convolutional Neural Network as well as Dropout and Dropconnect networks and the relation between excess error rate of Dropout and Dropconnect networks. The concept of intrinsic dimension is used to validate the intuition that texture-based datasets are inherently higher dimensional as compared to handwritten digits or other object recognition datasets and hence more difficult to be shattered by neural networks. We then derive the mean distance from the centroid to the nearest and farthest sampling points in an n-dimensional manifold and show that the Relative Contrast of the sample data vanishes as dimensionality of the underlying vector space tends to infinity. Copyright © 2017 Elsevier Ltd. All rights reserved.

Setup of a Parameterized FE Model for the Die Roll Prediction in Fine Blanking using Artificial Neural Networks

NASA Astrophysics Data System (ADS)

Stanke, J.; Trauth, D.; Feuerhack, A.; Klocke, F.

2017-09-01

Die roll is a morphological feature of fine blanked sheared edges. The die roll reduces the functional part of the sheared edge. To compensate for the die roll thicker sheet metal strips and secondary machining must be used. However, in order to avoid this, the influence of various fine blanking process parameters on the die roll has been experimentally and numerically studied, but there is still a lack of knowledge on the effects of some factors and especially factor interactions on the die roll. Recent changes in the field of artificial intelligence motivate the hybrid use of the finite element method and artificial neural networks to account for these non-considered parameters. Therefore, a set of simulations using a validated finite element model of fine blanking is firstly used to train an artificial neural network. Then the artificial neural network is trained with thousands of experimental trials. Thus, the objective of this contribution is to develop an artificial neural network that reliably predicts the die roll. Therefore, in this contribution, the setup of a fully parameterized 2D FE model is presented that will be used for batch training of an artificial neural network. The FE model enables an automatic variation of the edge radii of blank punch and die plate, the counter and blank holder force, the sheet metal thickness and part diameter, V-ring height and position, cutting velocity as well as material parameters covered by the Hensel-Spittel model for 16MnCr5 (1.7131, AISI/SAE 5115). The FE model is validated using experimental trails. The results of this contribution is a FE model suitable to perform 9.623 simulations and to pass the simulated die roll width and height automatically to an artificial neural network.

Cotton genotypes selection through artificial neural networks.

PubMed

Júnior, E G Silva; Cardoso, D B O; Reis, M C; Nascimento, A F O; Bortolin, D I; Martins, M R; Sousa, L B

2017-09-27

Breeding programs currently use statistical analysis to assist in the identification of superior genotypes at various stages of a cultivar's development. Differently from these analyses, the computational intelligence approach has been little explored in genetic improvement of cotton. Thus, this study was carried out with the objective of presenting the use of artificial neural networks as auxiliary tools in the improvement of the cotton to improve fiber quality. To demonstrate the applicability of this approach, this research was carried out using the evaluation data of 40 genotypes. In order to classify the genotypes for fiber quality, the artificial neural networks were trained with replicate data of 20 genotypes of cotton evaluated in the harvests of 2013/14 and 2014/15, regarding fiber length, uniformity of length, fiber strength, micronaire index, elongation, short fiber index, maturity index, reflectance degree, and fiber quality index. This quality index was estimated by means of a weighted average on the determined score (1 to 5) of each characteristic of the HVI evaluated, according to its industry standards. The artificial neural networks presented a high capacity of correct classification of the 20 selected genotypes based on the fiber quality index, so that when using fiber length associated with the short fiber index, fiber maturation, and micronaire index, the artificial neural networks presented better results than using only fiber length and previous associations. It was also observed that to submit data of means of new genotypes to the neural networks trained with data of repetition, provides better results of classification of the genotypes. When observing the results obtained in the present study, it was verified that the artificial neural networks present great potential to be used in the different stages of a genetic improvement program of the cotton, aiming at the improvement of the fiber quality of the future cultivars.

Coarse-to-fine deep neural network for fast pedestrian detection

NASA Astrophysics Data System (ADS)

Li, Yaobin; Yang, Xinmei; Cao, Lijun

2017-11-01

Pedestrian detection belongs to a category of object detection is a key issue in the field of video surveillance and automatic driving. Although recent object detection methods, such as Fast/Faster RCNN, have achieved excellent performance, it is difficult to meet real-time requirements and limits the application in real scenarios. A coarse-to-fine deep neural network for fast pedestrian detection is proposed in this paper. Two-stage approach is presented to realize fine trade-off between accuracy and speed. In the coarse stage, we train a fast deep convolution neural network to generate most pedestrian candidates at the cost of a number of false positives. The detector can cover the majority of scales, sizes, and occlusions of pedestrians. After that, a classification network is introduced to refine the pedestrian candidates generated from the previous stage. Refining through classification network, most of false detections will be excluded easily and the final pedestrian predictions with bounding box and confidence score are produced. Competitive results have been achieved on INRIA dataset in terms of accuracy, especially the method can achieve real-time detection that is faster than the previous leading methods. The effectiveness of coarse-to-fine approach to detect pedestrians is verified, and the accuracy and stability are also improved.

Neural networks modeling and control of dynamical systems

NASA Technical Reports Server (NTRS)

Soloway, Don

1992-01-01

The topics are presented in viewgraph form and include: an overview of research; first year research objectives (starting 5/91); background; current work; accomplishments from 5/91-9/91; and second year research objectives.

Prediction of U-Mo dispersion nuclear fuels with Al-Si alloy using artificial neural network

DOE Office of Scientific and Technical Information (OSTI.GOV)

Susmikanti, Mike, E-mail: mike@batan.go.id; Sulistyo, Jos, E-mail: soj@batan.go.id

2014-09-30

Dispersion nuclear fuels, consisting of U-Mo particles dispersed in an Al-Si matrix, are being developed as fuel for research reactors. The equilibrium relationship for a mixture component can be expressed in the phase diagram. It is important to analyze whether a mixture component is in equilibrium phase or another phase. The purpose of this research it is needed to built the model of the phase diagram, so the mixture component is in the stable or melting condition. Artificial neural network (ANN) is a modeling tool for processes involving multivariable non-linear relationships. The objective of the present work is to developmore » code based on artificial neural network models of system equilibrium relationship of U-Mo in Al-Si matrix. This model can be used for prediction of type of resulting mixture, and whether the point is on the equilibrium phase or in another phase region. The equilibrium model data for prediction and modeling generated from experimentally data. The artificial neural network with resilient backpropagation method was chosen to predict the dispersion of nuclear fuels U-Mo in Al-Si matrix. This developed code was built with some function in MATLAB. For simulations using ANN, the Levenberg-Marquardt method was also used for optimization. The artificial neural network is able to predict the equilibrium phase or in the phase region. The develop code based on artificial neural network models was built, for analyze equilibrium relationship of U-Mo in Al-Si matrix.« less

An efficient fully unsupervised video object segmentation scheme using an adaptive neural-network classifier architecture.

PubMed

Doulamis, A; Doulamis, N; Ntalianis, K; Kollias, S

2003-01-01

In this paper, an unsupervised video object (VO) segmentation and tracking algorithm is proposed based on an adaptable neural-network architecture. The proposed scheme comprises: 1) a VO tracking module and 2) an initial VO estimation module. Object tracking is handled as a classification problem and implemented through an adaptive network classifier, which provides better results compared to conventional motion-based tracking algorithms. Network adaptation is accomplished through an efficient and cost effective weight updating algorithm, providing a minimum degradation of the previous network knowledge and taking into account the current content conditions. A retraining set is constructed and used for this purpose based on initial VO estimation results. Two different scenarios are investigated. The first concerns extraction of human entities in video conferencing applications, while the second exploits depth information to identify generic VOs in stereoscopic video sequences. Human face/ body detection based on Gaussian distributions is accomplished in the first scenario, while segmentation fusion is obtained using color and depth information in the second scenario. A decision mechanism is also incorporated to detect time instances for weight updating. Experimental results and comparisons indicate the good performance of the proposed scheme even in sequences with complicated content (object bending, occlusion).

Distinct neural substrates for visual short-term memory of actions.

PubMed

Cai, Ying; Urgolites, Zhisen; Wood, Justin; Chen, Chuansheng; Li, Siyao; Chen, Antao; Xue, Gui

2018-06-26

Fundamental theories of human cognition have long posited that the short-term maintenance of actions is supported by one of the "core knowledge" systems of human visual cognition, yet its neural substrates are still not well understood. In particular, it is unclear whether the visual short-term memory (VSTM) of actions has distinct neural substrates or, as proposed by the spatio-object architecture of VSTM, shares them with VSTM of objects and spatial locations. In two experiments, we tested these two competing hypotheses by directly contrasting the neural substrates for VSTM of actions with those for objects and locations. Our results showed that the bilateral middle temporal cortex (MT) was specifically involved in VSTM of actions because its activation and its functional connectivity with the frontal-parietal network (FPN) were only modulated by the memory load of actions, but not by that of objects/agents or locations. Moreover, the brain regions involved in the maintenance of spatial location information (i.e., superior parietal lobule, SPL) was also recruited during the maintenance of actions, consistent with the temporal-spatial nature of actions. Meanwhile, the frontoparietal network (FPN) was commonly involved in all types of VSTM and showed flexible functional connectivity with the domain-specific regions, depending on the current working memory tasks. Together, our results provide clear evidence for a distinct neural system for maintaining actions in VSTM, which supports the core knowledge system theory and the domain-specific and domain-general architectures of VSTM. © 2018 Wiley Periodicals, Inc.

Imbalance aware lithography hotspot detection: a deep learning approach

NASA Astrophysics Data System (ADS)

Yang, Haoyu; Luo, Luyang; Su, Jing; Lin, Chenxi; Yu, Bei

2017-07-01

With the advancement of very large scale integrated circuits (VLSI) technology nodes, lithographic hotspots become a serious problem that affects manufacture yield. Lithography hotspot detection at the post-OPC stage is imperative to check potential circuit failures when transferring designed patterns onto silicon wafers. Although conventional lithography hotspot detection methods, such as machine learning, have gained satisfactory performance, with the extreme scaling of transistor feature size and layout patterns growing in complexity, conventional methodologies may suffer from performance degradation. For example, manual or ad hoc feature extraction in a machine learning framework may lose important information when predicting potential errors in ultra-large-scale integrated circuit masks. We present a deep convolutional neural network (CNN) that targets representative feature learning in lithography hotspot detection. We carefully analyze the impact and effectiveness of different CNN hyperparameters, through which a hotspot-detection-oriented neural network model is established. Because hotspot patterns are always in the minority in VLSI mask design, the training dataset is highly imbalanced. In this situation, a neural network is no longer reliable, because a trained model with high classification accuracy may still suffer from a high number of false negative results (missing hotspots), which is fatal in hotspot detection problems. To address the imbalance problem, we further apply hotspot upsampling and random-mirror flipping before training the network. Experimental results show that our proposed neural network model achieves comparable or better performance on the ICCAD 2012 contest benchmark compared to state-of-the-art hotspot detectors based on deep or representative machine leaning.

Spatiotemporal Recurrent Convolutional Networks for Traffic Prediction in Transportation Networks

PubMed Central

Yu, Haiyang; Wu, Zhihai; Wang, Shuqin; Wang, Yunpeng; Ma, Xiaolei

2017-01-01

Predicting large-scale transportation network traffic has become an important and challenging topic in recent decades. Inspired by the domain knowledge of motion prediction, in which the future motion of an object can be predicted based on previous scenes, we propose a network grid representation method that can retain the fine-scale structure of a transportation network. Network-wide traffic speeds are converted into a series of static images and input into a novel deep architecture, namely, spatiotemporal recurrent convolutional networks (SRCNs), for traffic forecasting. The proposed SRCNs inherit the advantages of deep convolutional neural networks (DCNNs) and long short-term memory (LSTM) neural networks. The spatial dependencies of network-wide traffic can be captured by DCNNs, and the temporal dynamics can be learned by LSTMs. An experiment on a Beijing transportation network with 278 links demonstrates that SRCNs outperform other deep learning-based algorithms in both short-term and long-term traffic prediction. PMID:28672867

Spatiotemporal Recurrent Convolutional Networks for Traffic Prediction in Transportation Networks.

PubMed

Yu, Haiyang; Wu, Zhihai; Wang, Shuqin; Wang, Yunpeng; Ma, Xiaolei

2017-06-26

Predicting large-scale transportation network traffic has become an important and challenging topic in recent decades. Inspired by the domain knowledge of motion prediction, in which the future motion of an object can be predicted based on previous scenes, we propose a network grid representation method that can retain the fine-scale structure of a transportation network. Network-wide traffic speeds are converted into a series of static images and input into a novel deep architecture, namely, spatiotemporal recurrent convolutional networks (SRCNs), for traffic forecasting. The proposed SRCNs inherit the advantages of deep convolutional neural networks (DCNNs) and long short-term memory (LSTM) neural networks. The spatial dependencies of network-wide traffic can be captured by DCNNs, and the temporal dynamics can be learned by LSTMs. An experiment on a Beijing transportation network with 278 links demonstrates that SRCNs outperform other deep learning-based algorithms in both short-term and long-term traffic prediction.

Abnormal neural activities of directional brain networks in patients with long-term bilateral hearing loss.

PubMed

Xu, Long-Chun; Zhang, Gang; Zou, Yue; Zhang, Min-Feng; Zhang, Dong-Sheng; Ma, Hua; Zhao, Wen-Bo; Zhang, Guang-Yu

2017-10-13

The objective of the study is to provide some implications for rehabilitation of hearing impairment by investigating changes of neural activities of directional brain networks in patients with long-term bilateral hearing loss. Firstly, we implemented neuropsychological tests of 21 subjects (11 patients with long-term bilateral hearing loss, and 10 subjects with normal hearing), and these tests revealed significant differences between the deaf group and the controls. Then we constructed the individual specific virtual brain based on functional magnetic resonance data of participants by utilizing effective connectivity and multivariate regression methods. We exerted the stimulating signal to the primary auditory cortices of the virtual brain and observed the brain region activations. We found that patients with long-term bilateral hearing loss presented weaker brain region activations in the auditory and language networks, but enhanced neural activities in the default mode network as compared with normally hearing subjects. Especially, the right cerebral hemisphere presented more changes than the left. Additionally, weaker neural activities in the primary auditor cortices were also strongly associated with poorer cognitive performance. Finally, causal analysis revealed several interactional circuits among activated brain regions, and these interregional causal interactions implied that abnormal neural activities of the directional brain networks in the deaf patients impacted cognitive function.

Piecewise convexity of artificial neural networks.

PubMed

Rister, Blaine; Rubin, Daniel L

2017-10-01

Although artificial neural networks have shown great promise in applications including computer vision and speech recognition, there remains considerable practical and theoretical difficulty in optimizing their parameters. The seemingly unreasonable success of gradient descent methods in minimizing these non-convex functions remains poorly understood. In this work we offer some theoretical guarantees for networks with piecewise affine activation functions, which have in recent years become the norm. We prove three main results. First, that the network is piecewise convex as a function of the input data. Second, that the network, considered as a function of the parameters in a single layer, all others held constant, is again piecewise convex. Third, that the network as a function of all its parameters is piecewise multi-convex, a generalization of biconvexity. From here we characterize the local minima and stationary points of the training objective, showing that they minimize the objective on certain subsets of the parameter space. We then analyze the performance of two optimization algorithms on multi-convex problems: gradient descent, and a method which repeatedly solves a number of convex sub-problems. We prove necessary convergence conditions for the first algorithm and both necessary and sufficient conditions for the second, after introducing regularization to the objective. Finally, we remark on the remaining difficulty of the global optimization problem. Under the squared error objective, we show that by varying the training data, a single rectifier neuron admits local minima arbitrarily far apart, both in objective value and parameter space. Copyright © 2017 Elsevier Ltd. All rights reserved.

Directional harmonic theory: a computational Gestalt model to account for illusory contour and vertex formation.

PubMed

Lehar, Steven

2003-01-01

Visual illusions and perceptual grouping phenomena offer an invaluable tool for probing the computational mechanism of low-level visual processing. Some illusions, like the Kanizsa figure, reveal illusory contours that form edges collinear with the inducing stimulus. This kind of illusory contour has been modeled by neural network models by way of cells equipped with elongated spatial receptive fields designed to detect and complete the collinear alignment. There are, however, other illusory groupings which are not so easy to account for in neural network terms. The Ehrenstein illusion exhibits an illusory contour that forms a contour orthogonal to the stimulus instead of collinear with it. Other perceptual grouping effects reveal illusory contours that exhibit a sharp corner or vertex, and still others take the form of vertices defined by the intersection of three, four, or more illusory contours that meet at a point. A direct extension of the collinear completion models to account for these phenomena tends towards a combinatorial explosion, because it would suggest cells with specialized receptive fields configured to perform each of those completion types, each of which would have to be replicated at every location and every orientation across the visual field. These phenomena therefore challenge the adequacy of the neural network approach to account for these diverse perceptual phenomena. I have proposed elsewhere an alternative paradigm of neurocomputation in the harmonic resonance theory (Lehar 1999, see website), whereby pattern recognition and completion are performed by spatial standing waves across the neural substrate. The standing waves perform a computational function analogous to that of the spatial receptive fields of the neural network approach, except that, unlike that paradigm, a single resonance mechanism performs a function equivalent to a whole array of spatial receptive fields of different spatial configurations and of different orientations, and thereby avoids the combinatorial explosion inherent in the older paradigm. The present paper presents the directional harmonic model, a more specific development of the harmonic resonance theory, designed to account for specific perceptual grouping phenomena. Computer simulations of the directional harmonic model show that it can account for collinear contours as observed in the Kanizsa figure, orthogonal contours as seen in the Ehrenstein illusion, and a number of illusory vertex percepts composed of two, three, or more illusory contours that meet in a variety of configurations.

Incidents Prediction in Road Junctions Using Artificial Neural Networks

NASA Astrophysics Data System (ADS)

Hajji, Tarik; Alami Hassani, Aicha; Ouazzani Jamil, Mohammed

2018-05-01

The implementation of an incident detection system (IDS) is an indispensable operation in the analysis of the road traffics. However the IDS may, in no case, represent an alternative to the classical monitoring system controlled by the human eye. The aim of this work is to increase detection and prediction probability of incidents in camera-monitored areas. Knowing that, these areas are monitored by multiple cameras and few supervisors. Our solution is to use Artificial Neural Networks (ANN) to analyze moving objects trajectories on captured images. We first propose a modelling of the trajectories and their characteristics, after we develop a learning database for valid and invalid trajectories, and then we carry out a comparative study to find the artificial neural network architecture that maximizes the rate of valid and invalid trajectories recognition.

Application of heterogeneous pulse coupled neural network in image quantization

NASA Astrophysics Data System (ADS)

Huang, Yi; Ma, Yide; Li, Shouliang; Zhan, Kun

2016-11-01

On the basis of the different strengths of synaptic connections between actual neurons, this paper proposes a heterogeneous pulse coupled neural network (HPCNN) algorithm to perform quantization on images. HPCNNs are developed from traditional pulse coupled neural network (PCNN) models, which have different parameters corresponding to different image regions. This allows pixels of different gray levels to be classified broadly into two categories: background regional and object regional. Moreover, an HPCNN also satisfies human visual characteristics. The parameters of the HPCNN model are calculated automatically according to these categories, and quantized results will be optimal and more suitable for humans to observe. At the same time, the experimental results of natural images from the standard image library show the validity and efficiency of our proposed quantization method.

Neural network identification of aircraft nonlinear aerodynamic characteristics

NASA Astrophysics Data System (ADS)

Egorchev, M. V.; Tiumentsev, Yu V.

2018-02-01

The simulation problem for the controlled aircraft motion is considered in the case of imperfect knowledge of the modeling object and its operating conditions. The work aims to develop a class of modular semi-empirical dynamic models that combine the capabilities of theoretical and neural network modeling. We consider the use of semi-empirical neural network models for solving the problem of identifying aerodynamic characteristics of an aircraft. We also discuss the formation problem for a representative set of data characterizing the behavior of a simulated dynamic system, which is one of the critical tasks in the synthesis of ANN-models. The effectiveness of the proposed approach is demonstrated using a simulation example of the aircraft angular motion and identifying the corresponding coefficients of aerodynamic forces and moments.

Development of Tool Representations in the Dorsal and Ventral Visual Object Processing Pathways

PubMed Central

Kersey, Alyssa J.; Clark, Tyia S.; Lussier, Courtney A.; Mahon, Bradford Z.; Cantlon, Jessica F.

2016-01-01

Tools represent a special class of objects, because they are processed across both the dorsal and ventral visual object processing pathways. Three core regions are known to be involved in tool processing: the left posterior middle temporal gyrus, the medial fusiform gyrus (bilaterally), and the left inferior parietal lobule. A critical and relatively unexplored issue concerns whether, in development, tool preferences emerge at the same time and to a similar degree across all regions of the tool-processing network. To test this issue, we used functional magnetic resonance imaging to measure the neural amplitude, peak location, and the dispersion of tool-related neural responses in the youngest sample of children tested to date in this domain (ages 4–8 years). We show that children recruit overlapping regions of the adult tool-processing network and also exhibit similar patterns of co-activation across the network to adults. The amplitude and co-activation data show that the core components of the tool-processing network are established by age 4. Our findings on the distributions of peak location and dispersion of activation indicate that the tool network undergoes refinement between ages 4 and 8 years. PMID:26108614

Modeling of bromate formation by ozonation of surface waters in drinking water treatment.

PubMed

Legube, Bernard; Parinet, Bernard; Gelinet, Karine; Berne, Florence; Croue, Jean-Philippe

2004-04-01

The main objective of this paper is to try to develop statistically and chemically rational models for bromate formation by ozonation of clarified surface waters. The results presented here show that bromate formation by ozonation of natural waters in drinking water treatment is directly proportional to the "Ct" value ("Ctau" in this study). Moreover, this proportionality strongly depends on many parameters: increasing of pH, temperature and bromide level leading to an increase of bromate formation; ammonia and dissolved organic carbon concentrations causing a reverse effect. Taking into account limitation of theoretical modeling, we proposed to predict bromate formation by stochastic simulations (multi-linear regression and artificial neural networks methods) from 40 experiments (BrO(3)(-) vs. "Ctau") carried out with three sand filtered waters sampled on three different waterworks. With seven selected variables we used a simple architecture of neural networks, optimized by "neural connection" of SPSS Inc./Recognition Inc. The bromate modeling by artificial neural networks gives better result than multi-linear regression. The artificial neural networks model allowed us classifying variables by decreasing order of influence (for the studied cases in our variables scale): "Ctau", [N-NH(4)(+)], [Br(-)], pH, temperature, DOC, alkalinity.

Practical aspects of using a neural network to solve inverse geophysical problems

NASA Astrophysics Data System (ADS)

Yakimenko, A. A.; Morozov, A. E.; Karavaev, D. A.

2018-05-01

In this paper, an approach to solve an inverse problem of geophysics, such as determining the position of an object (cavity or cavern) and its geometrical parameters according to the propagation picture of a wave field, is proposed. At present there are no fast and accurate methods for determining such parameters. In this paper, a method based on neural networks (NNs) is proposed and a possible architecture of the NN is presented. The results of experiments on implementing and training the NN are also presented. The model obtained shows the presence of an "understanding" of the input data, demonstrating answers that are similar to the original data. In the NN answers, one can identify a relationship between the quality of the network response and the number of waves that have passed through the medium’s object being investigated.

A feedback model of figure-ground assignment.

PubMed

Domijan, Drazen; Setić, Mia

2008-05-30

A computational model is proposed in order to explain how bottom-up and top-down signals are combined into a unified perception of figure and background. The model is based on the interaction between the ventral and the dorsal stream. The dorsal stream computes saliency based on boundary signals provided by the simple and the complex cortical cells. Output from the dorsal stream is projected to the surface network which serves as a blackboard on which the surface representation is formed. The surface network is a recurrent network which segregates different surfaces by assigning different firing rates to them. The figure is labeled by the maximal firing rate. Computer simulations showed that the model correctly assigns figural status to the surface with a smaller size, a greater contrast, convexity, surroundedness, horizontal-vertical orientation and a higher spatial frequency content. The simple gradient of activity in the dorsal stream enables the simulation of the new principles of the lower region and the top-bottom polarity. The model also explains how the exogenous attention and the endogenous attention may reverse the figural assignment. Due to the local excitation in the surface network, neural activity at the cued region will spread over the whole surface representation. Therefore, the model implements the object-based attentional selection.

Effects of lesions to the left lateral prefrontal cortex on task-specific top-down biases and response strategies in blocked-cyclic naming.

PubMed

Belke, Eva

Anders, Riès, van Maanen and Alario put forward evidence accumulation modelling of object naming times as an alternative to neural network models of lexical retrieval. The authors exemplify their approach using data from the blocked-cyclic naming paradigm, requiring speakers to repeatedly name small sets of related or unrelated objects. The effects observed with this paradigm are understood reasonably well within the tradition of neural network modelling. However, implemented neural network models do not specify interfaces for task-specific top-down influences and response strategies that are likely to play a role in the blocked-cyclic naming paradigm, distinguishing it from continuous, non-cyclic manipulations of the naming context. I argue that the evidence accumulation approach falls short on this account as well, as it does not specify the potential contribution of task-specific top-down processes and strategic facilitation effects to the response time distributions. Future endeavours to model or fit data from blocked-cyclic naming experiments should strive to do so by simultaneously considering data from continuous context manipulations.

Object based technique for delineating and mapping 15 tree species using VHR WorldView-2 imagery

NASA Astrophysics Data System (ADS)

Mustafa, Yaseen T.; Habeeb, Hindav N.

2014-10-01

Monitoring and analyzing forests and trees are required task to manage and establish a good plan for the forest sustainability. To achieve such a task, information and data collection of the trees are requested. The fastest way and relatively low cost technique is by using satellite remote sensing. In this study, we proposed an approach to identify and map 15 tree species in the Mangish sub-district, Kurdistan Region-Iraq. Image-objects (IOs) were used as the tree species mapping unit. This is achieved using the shadow index, normalized difference vegetation index and texture measurements. Four classification methods (Maximum Likelihood, Mahalanobis Distance, Neural Network, and Spectral Angel Mapper) were used to classify IOs using selected IO features derived from WorldView-2 imagery. Results showed that overall accuracy was increased 5-8% using the Neural Network method compared with other methods with a Kappa coefficient of 69%. This technique gives reasonable results of various tree species classifications by means of applying the Neural Network method with IOs techniques on WorldView-2 imagery.

Detection of Foreign Matter in Transfusion Solution Based on Gaussian Background Modeling and an Optimized BP Neural Network

PubMed Central

Zhou, Fuqiang; Su, Zhen; Chai, Xinghua; Chen, Lipeng

2014-01-01

This paper proposes a new method to detect and identify foreign matter mixed in a plastic bottle filled with transfusion solution. A spin-stop mechanism and mixed illumination style are applied to obtain high contrast images between moving foreign matter and a static transfusion background. The Gaussian mixture model is used to model the complex background of the transfusion image and to extract moving objects. A set of features of moving objects are extracted and selected by the ReliefF algorithm, and optimal feature vectors are fed into the back propagation (BP) neural network to distinguish between foreign matter and bubbles. The mind evolutionary algorithm (MEA) is applied to optimize the connection weights and thresholds of the BP neural network to obtain a higher classification accuracy and faster convergence rate. Experimental results show that the proposed method can effectively detect visible foreign matter in 250-mL transfusion bottles. The misdetection rate and false alarm rate are low, and the detection accuracy and detection speed are satisfactory. PMID:25347581

Contact-force distribution optimization and control for quadruped robots using both gradient and adaptive neural networks.

PubMed

Li, Zhijun; Ge, Shuzhi Sam; Liu, Sibang

2014-08-01

This paper investigates optimal feet forces' distribution and control of quadruped robots under external disturbance forces. First, we formulate a constrained dynamics of quadruped robots and derive a reduced-order dynamical model of motion/force. Consider an external wrench on quadruped robots; the distribution of required forces and moments on the supporting legs of a quadruped robot is handled as a tip-point force distribution and used to equilibrate the external wrench. Then, a gradient neural network is adopted to deal with the optimized objective function formulated as to minimize this quadratic objective function subjected to linear equality and inequality constraints. For the obtained optimized tip-point force and the motion of legs, we propose the hybrid motion/force control based on an adaptive neural network to compensate for the perturbations in the environment and approximate feedforward force and impedance of the leg joints. The proposed control can confront the uncertainties including approximation error and external perturbation. The verification of the proposed control is conducted using a simulation.

Similarity networks as a knowledge representation for space applications

NASA Technical Reports Server (NTRS)

Bailey, David; Thompson, Donna; Feinstein, Jerald

1987-01-01

Similarity networks are a powerful form of knowledge representation that are useful for many artificial intelligence applications. Similarity networks are used in applications ranging from information analysis and case based reasoning to machine learning and linking symbolic to neural processing. Strengths of similarity networks include simple construction, intuitive object storage, and flexible retrieval techniques that facilitate inferencing. Therefore, similarity networks provide great potential for space applications.

Imagery May Arise from Associations Formed through Sensory Experience: A Network of Spiking Neurons Controlling a Robot Learns Visual Sequences in Order to Perform a Mental Rotation Task

PubMed Central

McKinstry, Jeffrey L.; Fleischer, Jason G.; Chen, Yanqing; Gall, W. Einar; Edelman, Gerald M.

2016-01-01

Mental imagery occurs “when a representation of the type created during the initial phases of perception is present but the stimulus is not actually being perceived.” How does the capability to perform mental imagery arise? Extending the idea that imagery arises from learned associations, we propose that mental rotation, a specific form of imagery, could arise through the mechanism of sequence learning–that is, by learning to regenerate the sequence of mental images perceived while passively observing a rotating object. To demonstrate the feasibility of this proposal, we constructed a simulated nervous system and embedded it within a behaving humanoid robot. By observing a rotating object, the system learns the sequence of neural activity patterns generated by the visual system in response to the object. After learning, it can internally regenerate a similar sequence of neural activations upon briefly viewing the static object. This system learns to perform a mental rotation task in which the subject must determine whether two objects are identical despite differences in orientation. As with human subjects, the time taken to respond is proportional to the angular difference between the two stimuli. Moreover, as reported in humans, the system fills in intermediate angles during the task, and this putative mental rotation activates the same pathways that are activated when the system views physical rotation. This work supports the proposal that mental rotation arises through sequence learning and the idea that mental imagery aids perception through learned associations, and suggests testable predictions for biological experiments. PMID:27653977

System and Method for Modeling the Flow Performance Features of an Object

NASA Technical Reports Server (NTRS)

Jorgensen, Charles (Inventor); Ross, James (Inventor)

1997-01-01

The method and apparatus includes a neural network for generating a model of an object in a wind tunnel from performance data on the object. The network is trained from test input signals (e.g., leading edge flap position, trailing edge flap position, angle of attack, and other geometric configurations, and power settings) and test output signals (e.g., lift, drag, pitching moment, or other performance features). In one embodiment, the neural network training method employs a modified Levenberg-Marquardt optimization technique. The model can be generated 'real time' as wind tunnel testing proceeds. Once trained, the model is used to estimate performance features associated with the aircraft given geometric configuration and/or power setting input. The invention can also be applied in other similar static flow modeling applications in aerodynamics, hydrodynamics, fluid dynamics, and other such disciplines. For example, the static testing of cars, sails, and foils, propellers, keels, rudders, turbines, fins, and the like, in a wind tunnel, water trough, or other flowing medium.

Action-Driven Visual Object Tracking With Deep Reinforcement Learning.

PubMed

Yun, Sangdoo; Choi, Jongwon; Yoo, Youngjoon; Yun, Kimin; Choi, Jin Young

2018-06-01

In this paper, we propose an efficient visual tracker, which directly captures a bounding box containing the target object in a video by means of sequential actions learned using deep neural networks. The proposed deep neural network to control tracking actions is pretrained using various training video sequences and fine-tuned during actual tracking for online adaptation to a change of target and background. The pretraining is done by utilizing deep reinforcement learning (RL) as well as supervised learning. The use of RL enables even partially labeled data to be successfully utilized for semisupervised learning. Through the evaluation of the object tracking benchmark data set, the proposed tracker is validated to achieve a competitive performance at three times the speed of existing deep network-based trackers. The fast version of the proposed method, which operates in real time on graphics processing unit, outperforms the state-of-the-art real-time trackers with an accuracy improvement of more than 8%.

Neural-adaptive control of single-master-multiple-slaves teleoperation for coordinated multiple mobile manipulators with time-varying communication delays and input uncertainties.

PubMed

Li, Zhijun; Su, Chun-Yi

2013-09-01

In this paper, adaptive neural network control is investigated for single-master-multiple-slaves teleoperation in consideration of time delays and input dead-zone uncertainties for multiple mobile manipulators carrying a common object in a cooperative manner. Firstly, concise dynamics of teleoperation systems consisting of a single master robot, multiple coordinated slave robots, and the object are developed in the task space. To handle asymmetric time-varying delays in communication channels and unknown asymmetric input dead zones, the nonlinear dynamics of the teleoperation system are transformed into two subsystems through feedback linearization: local master or slave dynamics including the unknown input dead zones and delayed dynamics for the purpose of synchronization. Then, a model reference neural network control strategy based on linear matrix inequalities (LMI) and adaptive techniques is proposed. The developed control approach ensures that the defined tracking errors converge to zero whereas the coordination internal force errors remain bounded and can be made arbitrarily small. Throughout this paper, stability analysis is performed via explicit Lyapunov techniques under specific LMI conditions. The proposed adaptive neural network control scheme is robust against motion disturbances, parametric uncertainties, time-varying delays, and input dead zones, which is validated by simulation studies.

Neural system applied on an invariant industrial character recognition

NASA Astrophysics Data System (ADS)

Lecoeuche, Stephane; Deguillemont, Denis; Dubus, Jean-Paul

1997-04-01

Besides the variety of fonts, character recognition systems for the industrial world are confronted with specific problems like: the variety of support (metal, wood, paper, ceramics . . .) as well as the variety of marking (printing, engraving, . . .) and conditions of lighting. We present a system that is able to solve a part of this problem. It implements a collaboration between two neural networks. The first network specialized in vision allows the system to extract the character from an image. Besides this capability, we have equipped our system with characteristics allowing it to obtain an invariant model from the presented character. Thus, whatever the position, the size and the orientation of the character during the capture are, the model presented to the input of the second network will be identical. The second network, thanks to a learning phase, permits us to obtain a character recognition system independent of the type of fonts used. Furthermore, its capabilities of generalization permit us to recognize degraded and/or distorted characters. A feedback loop between the two networks permits the first one to modify the quality of vision.The cooperation between these two networks allows us to recognize characters whatever the support and the marking.

Semantic Segmentation of Convolutional Neural Network for Supervised Classification of Multispectral Remote Sensing

NASA Astrophysics Data System (ADS)

Xue, L.; Liu, C.; Wu, Y.; Li, H.

2018-04-01

Semantic segmentation is a fundamental research in remote sensing image processing. Because of the complex maritime environment, the classification of roads, vegetation, buildings and water from remote Sensing Imagery is a challenging task. Although the neural network has achieved excellent performance in semantic segmentation in the last years, there are a few of works using CNN for ground object segmentation and the results could be further improved. This paper used convolution neural network named U-Net, its structure has a contracting path and an expansive path to get high resolution output. In the network , We added BN layers, which is more conducive to the reverse pass. Moreover, after upsampling convolution , we add dropout layers to prevent overfitting. They are promoted to get more precise segmentation results. To verify this network architecture, we used a Kaggle dataset. Experimental results show that U-Net achieved good performance compared with other architectures, especially in high-resolution remote sensing imagery.

Lidar detection of underwater objects using a neuro-SVM-based architecture.

PubMed

Mitra, Vikramjit; Wang, Chia-Jiu; Banerjee, Satarupa

2006-05-01

This paper presents a neural network architecture using a support vector machine (SVM) as an inference engine (IE) for classification of light detection and ranging (Lidar) data. Lidar data gives a sequence of laser backscatter intensities obtained from laser shots generated from an airborne object at various altitudes above the earth surface. Lidar data is pre-filtered to remove high frequency noise. As the Lidar shots are taken from above the earth surface, it has some air backscatter information, which is of no importance for detecting underwater objects. Because of these, the air backscatter information is eliminated from the data and a segment of this data is subsequently selected to extract features for classification. This is then encoded using linear predictive coding (LPC) and polynomial approximation. The coefficients thus generated are used as inputs to the two branches of a parallel neural architecture. The decisions obtained from the two branches are vector multiplied and the result is fed to an SVM-based IE that presents the final inference. Two parallel neural architectures using multilayer perception (MLP) and hybrid radial basis function (HRBF) are considered in this paper. The proposed structure fits the Lidar data classification task well due to the inherent classification efficiency of neural networks and accurate decision-making capability of SVM. A Bayesian classifier and a quadratic classifier were considered for the Lidar data classification task but they failed to offer high prediction accuracy. Furthermore, a single-layered artificial neural network (ANN) classifier was also considered and it failed to offer good accuracy. The parallel ANN architecture proposed in this paper offers high prediction accuracy (98.9%) and is found to be the most suitable architecture for the proposed task of Lidar data classification.

Identification of hand motion using background subtraction method and extraction of image binary with backpropagation neural network on skeleton model

NASA Astrophysics Data System (ADS)

Fauziah; Wibowo, E. P.; Madenda, S.; Hustinawati

2018-03-01

Capturing and recording motion in human is mostly done with the aim for sports, health, animation films, criminality, and robotic applications. In this study combined background subtraction and back propagation neural network. This purpose to produce, find similarity movement. The acquisition process using 8 MP resolution camera MP4 format, duration 48 seconds, 30frame/rate. video extracted produced 1444 pieces and results hand motion identification process. Phase of image processing performed is segmentation process, feature extraction, identification. Segmentation using bakground subtraction, extracted feature basically used to distinguish between one object to another object. Feature extraction performed by using motion based morfology analysis based on 7 invariant moment producing four different classes motion: no object, hand down, hand-to-side and hands-up. Identification process used to recognize of hand movement using seven inputs. Testing and training with a variety of parameters tested, it appears that architecture provides the highest accuracy in one hundred hidden neural network. The architecture is used propagate the input value of the system implementation process into the user interface. The result of the identification of the type of the human movement has been clone to produce the highest acuracy of 98.5447%. The training process is done to get the best results.

Neural adaptation accounts for the dynamic resizing of peripersonal space: evidence from a psychophysical-computational approach.

PubMed

Noel, Jean-Paul; Blanke, Olaf; Magosso, Elisa; Serino, Andrea

2018-06-01

Interactions between the body and the environment occur within the peripersonal space (PPS), the space immediately surrounding the body. The PPS is encoded by multisensory (audio-tactile, visual-tactile) neurons that possess receptive fields (RFs) anchored on the body and restricted in depth. The extension in depth of PPS neurons' RFs has been documented to change dynamically as a function of the velocity of incoming stimuli, but the underlying neural mechanisms are still unknown. Here, by integrating a psychophysical approach with neural network modeling, we propose a mechanistic explanation behind this inherent dynamic property of PPS. We psychophysically mapped the size of participant's peri-face and peri-trunk space as a function of the velocity of task-irrelevant approaching auditory stimuli. Findings indicated that the peri-trunk space was larger than the peri-face space, and, importantly, as for the neurophysiological delineation of RFs, both of these representations enlarged as the velocity of incoming sound increased. We propose a neural network model to mechanistically interpret these findings: the network includes reciprocal connections between unisensory areas and higher order multisensory neurons, and it implements neural adaptation to persistent stimulation as a mechanism sensitive to stimulus velocity. The network was capable of replicating the behavioral observations of PPS size remapping and relates behavioral proxies of PPS size to neurophysiological measures of multisensory neurons' RF size. We propose that a biologically plausible neural adaptation mechanism embedded within the network encoding for PPS can be responsible for the dynamic alterations in PPS size as a function of the velocity of incoming stimuli. NEW & NOTEWORTHY Interactions between body and environment occur within the peripersonal space (PPS). PPS neurons are highly dynamic, adapting online as a function of body-object interactions. The mechanistic underpinning PPS dynamic properties are unexplained. We demonstrate with a psychophysical approach that PPS enlarges as incoming stimulus velocity increases, efficiently preventing contacts with faster approaching objects. We present a neurocomputational model of multisensory PPS implementing neural adaptation to persistent stimulation to propose a neurophysiological mechanism underlying this effect.

Spontaneous default mode network phase-locking moderates performance perceptions under stereotype threat.

PubMed

Forbes, Chad E; Leitner, Jordan B; Duran-Jordan, Kelly; Magerman, Adam B; Schmader, Toni; Allen, John J B

2015-07-01

This study assessed whether individual differences in self-oriented neural processing were associated with performance perceptions of minority students under stereotype threat. Resting electroencephalographic activity recorded in white and minority participants was used to predict later estimates of task errors and self-doubt on a presumed measure of intelligence. We assessed spontaneous phase-locking between dipole sources in left lateral parietal cortex (LPC), precuneus/posterior cingulate cortex (P/PCC), and medial prefrontal cortex (MPFC); three regions of the default mode network (DMN) that are integral for self-oriented processing. Results revealed that minorities with greater LPC-P/PCC phase-locking in the theta band reported more accurate error estimations. All individuals experienced less self-doubt to the extent they exhibited greater LPC-MPFC phase-locking in the alpha band but this effect was driven by minorities. Minorities also reported more self-doubt to the extent they overestimated errors. Findings reveal novel neural moderators of stereotype threat effects on subjective experience. Spontaneous synchronization between DMN regions may play a role in anticipatory coping mechanisms that buffer individuals from stereotype threat. © The Author (2014). Published by Oxford University Press. For Permissions, please email: journals.permissions@oup.com.

Underwater Inherent Optical Properties Estimation Using a Depth Aided Deep Neural Network.

PubMed

Yu, Zhibin; Wang, Yubo; Zheng, Bing; Zheng, Haiyong; Wang, Nan; Gu, Zhaorui

2017-01-01

Underwater inherent optical properties (IOPs) are the fundamental clues to many research fields such as marine optics, marine biology, and underwater vision. Currently, beam transmissometers and optical sensors are considered as the ideal IOPs measuring methods. But these methods are inflexible and expensive to be deployed. To overcome this problem, we aim to develop a novel measuring method using only a single underwater image with the help of deep artificial neural network. The power of artificial neural network has been proved in image processing and computer vision fields with deep learning technology. However, image-based IOPs estimation is a quite different and challenging task. Unlike the traditional applications such as image classification or localization, IOP estimation looks at the transparency of the water between the camera and the target objects to estimate multiple optical properties simultaneously. In this paper, we propose a novel Depth Aided (DA) deep neural network structure for IOPs estimation based on a single RGB image that is even noisy. The imaging depth information is considered as an aided input to help our model make better decision.

Enhancement of digital radiography image quality using a convolutional neural network.

PubMed

Sun, Yuewen; Li, Litao; Cong, Peng; Wang, Zhentao; Guo, Xiaojing

2017-01-01

Digital radiography system is widely used for noninvasive security check and medical imaging examination. However, the system has a limitation of lower image quality in spatial resolution and signal to noise ratio. In this study, we explored whether the image quality acquired by the digital radiography system can be improved with a modified convolutional neural network to generate high-resolution images with reduced noise from the original low-quality images. The experiment evaluated on a test dataset, which contains 5 X-ray images, showed that the proposed method outperformed the traditional methods (i.e., bicubic interpolation and 3D block-matching approach) as measured by peak signal to noise ratio (PSNR) about 1.3 dB while kept highly efficient processing time within one second. Experimental results demonstrated that a residual to residual (RTR) convolutional neural network remarkably improved the image quality of object structural details by increasing the image resolution and reducing image noise. Thus, this study indicated that applying this RTR convolutional neural network system was useful to improve image quality acquired by the digital radiography system.

Detection and Localization of Robotic Tools in Robot-Assisted Surgery Videos Using Deep Neural Networks for Region Proposal and Detection.

PubMed

Sarikaya, Duygu; Corso, Jason J; Guru, Khurshid A

2017-07-01

Video understanding of robot-assisted surgery (RAS) videos is an active research area. Modeling the gestures and skill level of surgeons presents an interesting problem. The insights drawn may be applied in effective skill acquisition, objective skill assessment, real-time feedback, and human-robot collaborative surgeries. We propose a solution to the tool detection and localization open problem in RAS video understanding, using a strictly computer vision approach and the recent advances of deep learning. We propose an architecture using multimodal convolutional neural networks for fast detection and localization of tools in RAS videos. To the best of our knowledge, this approach will be the first to incorporate deep neural networks for tool detection and localization in RAS videos. Our architecture applies a region proposal network (RPN) and a multimodal two stream convolutional network for object detection to jointly predict objectness and localization on a fusion of image and temporal motion cues. Our results with an average precision of 91% and a mean computation time of 0.1 s per test frame detection indicate that our study is superior to conventionally used methods for medical imaging while also emphasizing the benefits of using RPN for precision and efficiency. We also introduce a new data set, ATLAS Dione, for RAS video understanding. Our data set provides video data of ten surgeons from Roswell Park Cancer Institute, Buffalo, NY, USA, performing six different surgical tasks on the daVinci Surgical System (dVSS) with annotations of robotic tools per frame.

Gravity Influences the Visual Representation of Object Tilt in Parietal Cortex

PubMed Central

Angelaki, Dora E.

2014-01-01

Sensory systems encode the environment in egocentric (e.g., eye, head, or body) reference frames, creating inherently unstable representations that shift and rotate as we move. However, it is widely speculated that the brain transforms these signals into an allocentric, gravity-centered representation of the world that is stable and independent of the observer's spatial pose. Where and how this representation may be achieved is currently unknown. Here we demonstrate that a subpopulation of neurons in the macaque caudal intraparietal area (CIP) visually encodes object tilt in nonegocentric coordinates defined relative to the gravitational vector. Neuronal responses to the tilt of a visually presented planar surface were measured with the monkey in different spatial orientations (upright and rolled left/right ear down) and then compared. This revealed a continuum of representations in which planar tilt was encoded in a gravity-centered reference frame in approximately one-tenth of the comparisons, intermediate reference frames ranging between gravity-centered and egocentric in approximately two-tenths of the comparisons, and in an egocentric reference frame in less than half of the comparisons. Altogether, almost half of the comparisons revealed a shift in the preferred tilt and/or a gain change consistent with encoding object orientation in nonegocentric coordinates. Through neural network modeling, we further show that a purely gravity-centered representation of object tilt can be achieved directly from the population activity of CIP-like units. These results suggest that area CIP may play a key role in creating a stable, allocentric representation of the environment defined relative to an “earth-vertical” direction. PMID:25339732

Improved Object Localization Using Accurate Distance Estimation in Wireless Multimedia Sensor Networks

PubMed Central

Ur Rehman, Yasar Abbas; Tariq, Muhammad; Khan, Omar Usman

2015-01-01

Object localization plays a key role in many popular applications of Wireless Multimedia Sensor Networks (WMSN) and as a result, it has acquired a significant status for the research community. A significant body of research performs this task without considering node orientation, object geometry and environmental variations. As a result, the localized object does not reflect the real world scenarios. In this paper, a novel object localization scheme for WMSN has been proposed that utilizes range free localization, computer vision, and principle component analysis based algorithms. The proposed approach provides the best possible approximation of distance between a wmsn sink and an object, and the orientation of the object using image based information. Simulation results report 99% efficiency and an error ratio of 0.01 (around 1 ft) when compared to other popular techniques. PMID:26528919

Detecting central fixation by means of artificial neural networks in a pediatric vision screener using retinal birefringence scanning.

PubMed

Gramatikov, Boris I

2017-04-27

Reliable detection of central fixation and eye alignment is essential in the diagnosis of amblyopia ("lazy eye"), which can lead to blindness. Our lab has developed and reported earlier a pediatric vision screener that performs scanning of the retina around the fovea and analyzes changes in the polarization state of light as the scan progresses. Depending on the direction of gaze and the instrument design, the screener produces several signal frequencies that can be utilized in the detection of central fixation. The objective of this study was to compare artificial neural networks with classical statistical methods, with respect to their ability to detect central fixation reliably. A classical feedforward, pattern recognition, two-layer neural network architecture was used, consisting of one hidden layer and one output layer. The network has four inputs, representing normalized spectral powers at four signal frequencies generated during retinal birefringence scanning. The hidden layer contains four neurons. The output suggests presence or absence of central fixation. Backpropagation was used to train the network, using the gradient descent algorithm and the cross-entropy error as the performance function. The network was trained, validated and tested on a set of controlled calibration data obtained from 600 measurements from ten eyes in a previous study, and was additionally tested on a clinical set of 78 eyes, independently diagnosed by an ophthalmologist. In the first part of this study, a neural network was designed around the calibration set. With a proper architecture and training, the network provided performance that was comparable to classical statistical methods, allowing perfect separation between the central and paracentral fixation data, with both the sensitivity and the specificity of the instrument being 100%. In the second part of the study, the neural network was applied to the clinical data. It allowed reliable separation between normal subjects and affected subjects, its accuracy again matching that of the statistical methods. With a proper choice of a neural network architecture and a good, uncontaminated training data set, the artificial neural network can be an efficient classification tool for detecting central fixation based on retinal birefringence scanning.

Detection of whale calls in noise: performance comparison between a beluga whale, human listeners, and a neural network.

PubMed

Erbe, C

2000-07-01

This article examines the masking by anthropogenic noise of beluga whale calls. Results from human masking experiments and a software backpropagation neural network are compared to the performance of a trained beluga whale. The goal was to find an accurate, reliable, and fast model to replace lengthy and expensive animal experiments. A beluga call was masked by three types of noise, an icebreaker's bubbler system and propeller noise, and ambient arctic ice-cracking noise. Both the human experiment and the neural network successfully modeled the beluga data in the sense that they classified the noises in the same order from strongest to weakest masking as the whale and with similar call-detection thresholds. The neural network slightly outperformed the humans. Both models were then used to predict the masking of a fourth type of noise, Gaussian white noise. Their prediction ability was judged by returning to the aquarium to measure masked-hearing thresholds of a beluga in white noise. Both models and the whale identified bubbler noise as the strongest masker, followed by ramming, then white noise. Natural ice-cracking noise masked the least. However, the humans and the neural network slightly overpredicted the amount of masking for white noise. This is neglecting individual variation in belugas, because only one animal could be trained. Comparing the human model to the neural network model, the latter has the advantage of objectivity, reproducibility of results, and efficiency, particularly if the interference of a large number of signals and noise is to be examined.

Selected Flight Test Results for Online Learning Neural Network-Based Flight Control System

NASA Technical Reports Server (NTRS)

Williams, Peggy S.

2004-01-01

The NASA F-15 Intelligent Flight Control System project team has developed a series of flight control concepts designed to demonstrate the benefits of a neural network-based adaptive controller. The objective of the team is to develop and flight-test control systems that use neural network technology to optimize the performance of the aircraft under nominal conditions as well as stabilize the aircraft under failure conditions. Failure conditions include locked or failed control surfaces as well as unforeseen damage that might occur to the aircraft in flight. This report presents flight-test results for an adaptive controller using stability and control derivative values from an online learning neural network. A dynamic cell structure neural network is used in conjunction with a real-time parameter identification algorithm to estimate aerodynamic stability and control derivative increments to the baseline aerodynamic derivatives in flight. This set of open-loop flight tests was performed in preparation for a future phase of flights in which the learning neural network and parameter identification algorithm output would provide the flight controller with aerodynamic stability and control derivative updates in near real time. Two flight maneuvers are analyzed a pitch frequency sweep and an automated flight-test maneuver designed to optimally excite the parameter identification algorithm in all axes. Frequency responses generated from flight data are compared to those obtained from nonlinear simulation runs. An examination of flight data shows that addition of the flight-identified aerodynamic derivative increments into the simulation improved the pitch handling qualities of the aircraft.

Fast response and high sensitivity to microsaccades in a cascading-adaptation neural network with short-term synaptic depression

NASA Astrophysics Data System (ADS)

Yuan, Wu-Jie; Zhou, Jian-Fang; Zhou, Changsong

2016-04-01

Microsaccades are very small eye movements during fixation. Experimentally, they have been found to play an important role in visual information processing. However, neural responses induced by microsaccades are not yet well understood and are rarely studied theoretically. Here we propose a network model with a cascading adaptation including both retinal adaptation and short-term depression (STD) at thalamocortical synapses. In the neural network model, we compare the microsaccade-induced neural responses in the presence of STD and those without STD. It is found that the cascading with STD can give rise to faster and sharper responses to microsaccades. Moreover, STD can enhance response effectiveness and sensitivity to microsaccadic spatiotemporal changes, suggesting improved detection of small eye movements (or moving visual objects). We also explore the mechanism of the response properties in the model. Our studies strongly indicate that STD plays an important role in neural responses to microsaccades. Our model considers simultaneously retinal adaptation and STD at thalamocortical synapses in the study of microsaccade-induced neural activity, and may be useful for further investigation of the functional roles of microsaccades in visual information processing.

Object recognition with hierarchical discriminant saliency networks.

PubMed

Han, Sunhyoung; Vasconcelos, Nuno

2014-01-01

The benefits of integrating attention and object recognition are investigated. While attention is frequently modeled as a pre-processor for recognition, we investigate the hypothesis that attention is an intrinsic component of recognition and vice-versa. This hypothesis is tested with a recognition model, the hierarchical discriminant saliency network (HDSN), whose layers are top-down saliency detectors, tuned for a visual class according to the principles of discriminant saliency. As a model of neural computation, the HDSN has two possible implementations. In a biologically plausible implementation, all layers comply with the standard neurophysiological model of visual cortex, with sub-layers of simple and complex units that implement a combination of filtering, divisive normalization, pooling, and non-linearities. In a convolutional neural network implementation, all layers are convolutional and implement a combination of filtering, rectification, and pooling. The rectification is performed with a parametric extension of the now popular rectified linear units (ReLUs), whose parameters can be tuned for the detection of target object classes. This enables a number of functional enhancements over neural network models that lack a connection to saliency, including optimal feature denoising mechanisms for recognition, modulation of saliency responses by the discriminant power of the underlying features, and the ability to detect both feature presence and absence. In either implementation, each layer has a precise statistical interpretation, and all parameters are tuned by statistical learning. Each saliency detection layer learns more discriminant saliency templates than its predecessors and higher layers have larger pooling fields. This enables the HDSN to simultaneously achieve high selectivity to target object classes and invariance. The performance of the network in saliency and object recognition tasks is compared to those of models from the biological and computer vision literatures. This demonstrates benefits for all the functional enhancements of the HDSN, the class tuning inherent to discriminant saliency, and saliency layers based on templates of increasing target selectivity and invariance. Altogether, these experiments suggest that there are non-trivial benefits in integrating attention and recognition.

Searching for High Proper Motion Sources Towards the Galactic Center using Convolution Neural Networks

NASA Astrophysics Data System (ADS)

Giongo Fernandes, Alexandre; Benjamin, Robert A.; Babler, Brian

2018-01-01

Two sets of infrared images of the Galactic Center region (|L|< 1 degree and |B| < 0.75 degrees) taken by the Spitzer Space Telescope in IRAC 3.6 micron and 4.5 micron bands are searched for high proper motion objects (> 100 mas/year). The two image sets come from GALCEN observations in 2005 and GLIMPSE proper observations in 2015 with matched observation modes. We use three different methods to search for these objects in extremely crowded fields: (1) comparing matched point source lists, (2) crowd sourcing by several college introductory astronomy classes in the state of Wisconsin (700 volunteers), and (3) convolutional neural networks trained using objects from the previous two methods. Before our search six high proper objects were known, four of which were found by the VVV near-infrared Galactic plane survey. We compare and describe our methods for this search, and present a preliminary catalog of high proper motions objects.

A Compact Optical Instrument with Artificial Neural Network for pH Determination

PubMed Central

Capel-Cuevas, Sonia; López-Ruiz, Nuria; Martinez-Olmos, Antonio; Cuéllar, Manuel P.; Pegalajar, Maria del Carmen; Palma, Alberto José; de Orbe-Payá, Ignacio; Capitán-Vallvey, Luis Fermin

2012-01-01

The aim of this work was the determination of pH with a sensor array-based optical portable instrument. This sensor array consists of eleven membranes with selective colour changes at different pH intervals. The method for the pH calculation is based on the implementation of artificial neural networks that use the responses of the membranes to generate a final pH value. A multi-objective algorithm was used to select the minimum number of sensing elements required to achieve an accurate pH determination from the neural network, and also to minimise the network size. This helps to minimise instrument and array development costs and save on microprocessor energy consumption. A set of artificial neural networks that fulfils these requirements is proposed using different combinations of the membranes in the sensor array, and is evaluated in terms of accuracy and reliability. In the end, the network including the response of the eleven membranes in the sensor was selected for validation in the instrument prototype because of its high accuracy. The performance of the instrument was evaluated by measuring the pH of a large set of real samples, showing that high precision can be obtained in the full range. PMID:22778668

Functional connectivity mapping of regions associated with self- and other-processing.

PubMed

Murray, Ryan J; Debbané, Martin; Fox, Peter T; Bzdok, Danilo; Eickhoff, Simon B

2015-04-01

Neuroscience literature increasingly suggests a conceptual self composed of interacting neural regions, rather than independent local activations, yet such claims have yet to be investigated. We, thus, combined task-dependent meta-analytic connectivity modeling (MACM) with task-independent resting-state (RS) connectivity analysis to delineate the neural network of the self, across both states. Given psychological evidence implicating the self's interdependence on social information, we also delineated the neural network underlying conceptual other-processing. To elucidate the relation between the self-/other-networks and their function, we mined the MACM metadata to generate a cognitive-behavioral profile for an empirically identified region specific to conceptual self, the pregenual anterior cingulate (pACC), and conceptual other, posterior cingulate/precuneus (PCC/PC). Mining of 7,200 published, task-dependent, neuroimaging studies, using healthy human subjects, yielded 193 studies activating the self-related seed and were conjoined with RS connectivity analysis to delineate a differentiated self-network composed of the pACC (seed) and anterior insula, relative to other functional connectivity. Additionally, 106 studies activating the other-related seed were conjoined with RS connectivity analysis to delineate a differentiated other-network of PCC/PC (seed) and angular gyrus/temporoparietal junction, relative to self-functional connectivity. The self-network seed related to emotional conflict resolution and motivational processing, whereas the other-network seed related to socially oriented processing and contextual information integration. Notably, our findings revealed shared RS connectivity between ensuing self-/other-networks within the ventromedial prefrontal cortex and medial orbitofrontal cortex, suggesting self-updating via integration of self-relevant social information. We, therefore, present initial neurobiological evidence corroborating the increasing claims of an intricate self-network, the architecture of which may promote social value processing. © 2014 Wiley Periodicals, Inc.

FE-ANN based modeling of 3D Simple Reinforced Concrete Girders for Objective Structural Health Evaluation : Tech Transfer Summary

DOT National Transportation Integrated Search

2017-06-01

The objective of this study was to develop an objective, quantitative method for evaluating damage to bridge girders by using artificial neural networks (ANNs). This evaluation method, which is a supplement to visual inspection, requires only the res...

Memory and pattern storage in neural networks with activity dependent synapses

NASA Astrophysics Data System (ADS)

Mejias, J. F.; Torres, J. J.

2009-01-01

We present recently obtained results on the influence of the interplay between several activity dependent synaptic mechanisms, such as short-term depression and facilitation, on the maximum memory storage capacity in an attractor neural network [1]. In contrast with the case of synaptic depression, which drastically reduces the capacity of the network to store and retrieve activity patterns [2], synaptic facilitation is able to enhance the memory capacity in different situations. In particular, we find that a convenient balance between depression and facilitation can enhance the memory capacity, reaching maximal values similar to those obtained with static synapses, that is, without activity-dependent processes. We also argue, employing simple arguments, that this level of balance is compatible with experimental data recorded from some cortical areas, where depression and facilitation may play an important role for both memory-oriented tasks and information processing. We conclude that depressing synapses with a certain level of facilitation allow to recover the good retrieval properties of networks with static synapses while maintaining the nonlinear properties of dynamic synapses, convenient for information processing and coding.

Classification and recognition of texture collagen obtaining by multiphoton microscope with neural network analysis

NASA Astrophysics Data System (ADS)

Wu, Shulian; Peng, Yuanyuan; Hu, Liangjun; Zhang, Xiaoman; Li, Hui

2016-01-01

Second harmonic generation microscopy (SHGM) was used to monitor the process of chronological aging skin in vivo. The collagen structures of mice model with different ages were obtained using SHGM. Then, texture feature with contrast, correlation and entropy were extracted and analysed using the grey level co-occurrence matrix. At last, the neural network tool of Matlab was applied to train the texture of collagen in different statues during the aging process. And the simulation of mice collagen texture was carried out. The results indicated that the classification accuracy reach 85%. Results demonstrated that the proposed approach effectively detected the target object in the collagen texture image during the chronological aging process and the analysis tool based on neural network applied the skin of classification and feature extraction method is feasible.

An architectural approach to create self organizing control systems for practical autonomous robots

NASA Technical Reports Server (NTRS)

Greiner, Helen

1991-01-01

For practical industrial applications, the development of trainable robots is an important and immediate objective. Therefore, the developing of flexible intelligence directly applicable to training is emphasized. It is generally agreed upon by the AI community that the fusion of expert systems, neural networks, and conventionally programmed modules (e.g., a trajectory generator) is promising in the quest for autonomous robotic intelligence. Autonomous robot development is hindered by integration and architectural problems. Some obstacles towards the construction of more general robot control systems are as follows: (1) Growth problem; (2) Software generation; (3) Interaction with environment; (4) Reliability; and (5) Resource limitation. Neural networks can be successfully applied to some of these problems. However, current implementations of neural networks are hampered by the resource limitation problem and must be trained extensively to produce computationally accurate output. A generalization of conventional neural nets is proposed, and an architecture is offered in an attempt to address the above problems.

Convergence and rate analysis of neural networks for sparse approximation.

PubMed

Balavoine, Aurèle; Romberg, Justin; Rozell, Christopher J

2012-09-01

We present an analysis of the Locally Competitive Algorithm (LCA), which is a Hopfield-style neural network that efficiently solves sparse approximation problems (e.g., approximating a vector from a dictionary using just a few nonzero coefficients). This class of problems plays a significant role in both theories of neural coding and applications in signal processing. However, the LCA lacks analysis of its convergence properties, and previous results on neural networks for nonsmooth optimization do not apply to the specifics of the LCA architecture. We show that the LCA has desirable convergence properties, such as stability and global convergence to the optimum of the objective function when it is unique. Under some mild conditions, the support of the solution is also proven to be reached in finite time. Furthermore, some restrictions on the problem specifics allow us to characterize the convergence rate of the system by showing that the LCA converges exponentially fast with an analytically bounded convergence rate. We support our analysis with several illustrative simulations.

A General Connectionist Model of Attitude Structure and Change: The ACS (Attitudes as Constraint Satisfaction) Model

ERIC Educational Resources Information Center

Monroe, Brian M.; Read, Stephen J.

2008-01-01

A localist, parallel constraint satisfaction, artificial neural network model is presented that accounts for a broad collection of attitude and attitude-change phenomena. The network represents the attitude object and cognitions and beliefs related to the attitude, as well as how to integrate a persuasive message into this network. Short-term…

Temporal Sequence of Hemispheric Network Activation during Semantic Processing: A Functional Network Connectivity Analysis

ERIC Educational Resources Information Center

Assaf, Michal; Jagannathan, Kanchana; Calhoun, Vince; Kraut, Michael; Hart, John, Jr.; Pearlson, Godfrey

2009-01-01

To explore the temporal sequence of, and the relationship between, the left and right hemispheres (LH and RH) during semantic memory (SM) processing we identified the neural networks involved in the performance of functional MRI semantic object retrieval task (SORT) using group independent component analysis (ICA) in 47 healthy individuals. SORT…

Hierarchical Neural Representation of Dreamed Objects Revealed by Brain Decoding with Deep Neural Network Features.

PubMed

Horikawa, Tomoyasu; Kamitani, Yukiyasu

2017-01-01

Dreaming is generally thought to be generated by spontaneous brain activity during sleep with patterns common to waking experience. This view is supported by a recent study demonstrating that dreamed objects can be predicted from brain activity during sleep using statistical decoders trained with stimulus-induced brain activity. However, it remains unclear whether and how visual image features associated with dreamed objects are represented in the brain. In this study, we used a deep neural network (DNN) model for object recognition as a proxy for hierarchical visual feature representation, and DNN features for dreamed objects were analyzed with brain decoding of fMRI data collected during dreaming. The decoders were first trained with stimulus-induced brain activity labeled with the feature values of the stimulus image from multiple DNN layers. The decoders were then used to decode DNN features from the dream fMRI data, and the decoded features were compared with the averaged features of each object category calculated from a large-scale image database. We found that the feature values decoded from the dream fMRI data positively correlated with those associated with dreamed object categories at mid- to high-level DNN layers. Using the decoded features, the dreamed object category could be identified at above-chance levels by matching them to the averaged features for candidate categories. The results suggest that dreaming recruits hierarchical visual feature representations associated with objects, which may support phenomenal aspects of dream experience.

Recurrent neural network based virtual detection line

NASA Astrophysics Data System (ADS)

Kadikis, Roberts

2018-04-01

The paper proposes an efficient method for detection of moving objects in the video. The objects are detected when they cross a virtual detection line. Only the pixels of the detection line are processed, which makes the method computationally efficient. A Recurrent Neural Network processes these pixels. The machine learning approach allows one to train a model that works in different and changing outdoor conditions. Also, the same network can be trained for various detection tasks, which is demonstrated by the tests on vehicle and people counting. In addition, the paper proposes a method for semi-automatic acquisition of labeled training data. The labeling method is used to create training and testing datasets, which in turn are used to train and evaluate the accuracy and efficiency of the detection method. The method shows similar accuracy as the alternative efficient methods but provides greater adaptability and usability for different tasks.

Resource constrained design of artificial neural networks using comparator neural network

NASA Technical Reports Server (NTRS)

Wah, Benjamin W.; Karnik, Tanay S.

1992-01-01

We present a systematic design method executed under resource constraints for automating the design of artificial neural networks using the back error propagation algorithm. Our system aims at finding the best possible configuration for solving the given application with proper tradeoff between the training time and the network complexity. The design of such a system is hampered by three related problems. First, there are infinitely many possible network configurations, each may take an exceedingly long time to train; hence, it is impossible to enumerate and train all of them to completion within fixed time, space, and resource constraints. Second, expert knowledge on predicting good network configurations is heuristic in nature and is application dependent, rendering it difficult to characterize fully in the design process. A learning procedure that refines this knowledge based on examples on training neural networks for various applications is, therefore, essential. Third, the objective of the network to be designed is ill-defined, as it is based on a subjective tradeoff between the training time and the network cost. A design process that proposes alternate configurations under different cost-performance tradeoff is important. We have developed a Design System which schedules the available time, divided into quanta, for testing alternative network configurations. Its goal is to select/generate and test alternative network configurations in each quantum, and find the best network when time is expended. Since time is limited, a dynamic schedule that determines the network configuration to be tested in each quantum is developed. The schedule is based on relative comparison of predicted training times of alternative network configurations using comparator network paradigm. The comparator network has been trained to compare training times for a large variety of traces of TSSE-versus-time collected during back-propagation learning of various applications.

Network architectures and circuit function: testing alternative hypotheses in multifunctional networks.

PubMed

Leonard, J L

2000-05-01

Understanding how species-typical movement patterns are organized in the nervous system is a central question in neurobiology. The current explanations involve 'alphabet' models in which an individual neuron may participate in the circuit for several behaviors but each behavior is specified by a specific neural circuit. However, not all of the well-studied model systems fit the 'alphabet' model. The 'equation' model provides an alternative possibility, whereby a system of parallel motor neurons, each with a unique (but overlapping) field of innervation, can account for the production of stereotyped behavior patterns by variable circuits. That is, it is possible for such patterns to arise as emergent properties of a generalized neural network in the absence of feedback, a simple version of a 'self-organizing' behavioral system. Comparison of systems of identified neurons suggest that the 'alphabet' model may account for most observations where CPGs act to organize motor patterns. Other well-known model systems, involving architectures corresponding to feed-forward neural networks with a hidden layer, may organize patterned behavior in a manner consistent with the 'equation' model. Such architectures are found in the Mauthner and reticulospinal circuits, 'escape' locomotion in cockroaches, CNS control of Aplysia gill, and may also be important in the coordination of sensory information and motor systems in insect mushroom bodies and the vertebrate hippocampus. The hidden layer of such networks may serve as an 'internal representation' of the behavioral state and/or body position of the animal, allowing the animal to fine-tune oriented, or particularly context-sensitive, movements to the prevalent conditions. Experiments designed to distinguish between the two models in cases where they make mutually exclusive predictions provide an opportunity to elucidate the neural mechanisms by which behavior is organized in vivo and in vitro. Copyright 2000 S. Karger AG, Basel

Metric invariance in object recognition: a review and further evidence.

PubMed

Cooper, E E; Biederman, I; Hummel, J E

1992-06-01

Phenomenologically, human shape recognition appears to be invariant with changes of orientation in depth (up to parts occlusion), position in the visual field, and size. Recent versions of template theories (e.g., Ullman, 1989; Lowe, 1987) assume that these invariances are achieved through the application of transformations such as rotation, translation, and scaling of the image so that it can be matched metrically to a stored template. Presumably, such transformations would require time for their execution. We describe recent priming experiments in which the effects of a prior brief presentation of an image on its subsequent recognition are assessed. The results of these experiments indicate that the invariance is complete: The magnitude of visual priming (as distinct from name or basic level concept priming) is not affected by a change in position, size, orientation in depth, or the particular lines and vertices present in the image, as long as representations of the same components can be activated. An implemented seven layer neural network model (Hummel & Biederman, 1992) that captures these fundamental properties of human object recognition is described. Given a line drawing of an object, the model activates a viewpoint-invariant structural description of the object, specifying its parts and their interrelations. Visual priming is interpreted as a change in the connection weights for the activation of: a) cells, termed geon feature assemblies (GFAs), that conjoin the output of units that represent invariant, independent properties of a single geon and its relations (such as its type, aspect ratio, relations to other geons), or b) a change in the connection weights by which several GFAs activate a cell representing an object.

A Balanced Comparison of Object Invariances in Monkey IT Neurons.

PubMed

Ratan Murty, N Apurva; Arun, Sripati P

2017-01-01

Our ability to recognize objects across variations in size, position, or rotation is based on invariant object representations in higher visual cortex. However, we know little about how these invariances are related. Are some invariances harder than others? Do some invariances arise faster than others? These comparisons can be made only upon equating image changes across transformations. Here, we targeted invariant neural representations in the monkey inferotemporal (IT) cortex using object images with balanced changes in size, position, and rotation. Across the recorded population, IT neurons generalized across size and position both stronger and faster than to rotations in the image plane as well as in depth. We obtained a similar ordering of invariances in deep neural networks but not in low-level visual representations. Thus, invariant neural representations dynamically evolve in a temporal order reflective of their underlying computational complexity.

Dissociable intrinsic functional networks support noun-object and verb-action processing.

PubMed

Yang, Huichao; Lin, Qixiang; Han, Zaizhu; Li, Hongyu; Song, Luping; Chen, Lingjuan; He, Yong; Bi, Yanchao

2017-12-01

The processing mechanism of verbs-actions and nouns-objects is a central topic of language research, with robust evidence for behavioral dissociation. The neural basis for these two major word and/or conceptual classes, however, remains controversial. Two experiments were conducted to study this question from the network perspective. Experiment 1 found that nodes of the same class, obtained through task-evoked brain imaging meta-analyses, were more strongly connected with each other than nodes of different classes during resting-state, forming segregated network modules. Experiment 2 examined the behavioral relevance of these intrinsic networks using data from 88 brain-damaged patients, finding that across patients the relative strength of functional connectivity of the two networks significantly correlated with the noun-object vs. verb-action relative behavioral performances. In summary, we found that verbs-actions and nouns-objects are supported by separable intrinsic functional networks and that the integrity of such networks accounts for the relative noun-object- and verb-action-selective deficits. Copyright © 2017 Elsevier Inc. All rights reserved.

Large-scale network dysfunction in Major Depressive Disorder: Meta-analysis of resting-state functional connectivity

PubMed Central

Kaiser, Roselinde H.; Andrews-Hanna, Jessica R.; Wager, Tor D.; Pizzagalli, Diego A.

2015-01-01

IMPORTANCE Major depressive disorder (MDD) has been linked to imbalanced communication among large-scale brain networks, as reflected by abnormal resting-state functional connectivity (rsFC). However, given variable methods and results across studies, identifying consistent patterns of network dysfunction in MDD has been elusive. OBJECTIVE To investigate network dysfunction in MDD through the first meta-analysis of rsFC studies. DATA SOURCES Seed-based voxel-wise rsFC studies comparing MDD with healthy individuals (published before June 30, 2014) were retrieved from electronic databases (PubMed, Web-of-Science, EMBASE), and authors contacted for additional data. STUDY SELECTION Twenty-seven datasets from 25 publications (556 MDD adults/teens; 518 controls) were included in the meta-analysis. DATA EXTRACTION AND SYNTHESIS Coordinates of seed regions-of-interest and between-group effects were extracted. Seeds were categorized into “seed-networks” by their location within a priori functional networks. Multilevel kernel density analysis of between-group effects identified brain systems in which MDD was associated with hyperconnectivity (increased positive, or reduced negative, connectivity) or hypoconnectivity (increased negative, or reduced positive, connectivity) with each seed-network. RESULTS MDD was characterized by hypoconnectivity within the frontoparietal network (FN), a set of regions involved in cognitive control of attention and emotion regulation, and hypoconnectivity between frontoparietal systems and parietal regions of the dorsal attention network (DAN) involved in attending to the external environment. MDD was also associated with hyperconnectivity within the default network (DN), a network believed to support internally-oriented and self-referential thought, and hyperconnectivity between FN control systems and regions of DN. Finally, MDD groups exhibited hypoconnectivity between neural systems involved in processing emotion or salience and midline cortical regions that may mediate top-down regulation of such functions. CONCLUSIONS AND RELEVANCE Reduced connectivity within frontoparietal control systems, and imbalanced connectivity between control systems and networks involved in internal- or external-attention, may reflect depressive biases towards internal thoughts at the cost of engaging with the external world. Meanwhile, altered connectivity between neural systems involved in cognitive control and those that support salience or emotion processing may relate to deficits regulating mood. These findings provide an empirical foundation for a neurocognitive model in which network dysfunction underlies core cognitive and affective abnormalities in depression. PMID:25785575

An Object-Oriented Network-Centric Software Architecture for Physical Computing

NASA Astrophysics Data System (ADS)

Palmer, Richard

1997-08-01

Recent developments in object-oriented computer languages and infrastructure such as the Internet, Web browsers, and the like provide an opportunity to define a more productive computational environment for scientific programming that is based more closely on the underlying mathematics describing physics than traditional programming languages such as FORTRAN or C++. In this talk I describe an object-oriented software architecture for representing physical problems that includes classes for such common mathematical objects as geometry, boundary conditions, partial differential and integral equations, discretization and numerical solution methods, etc. In practice, a scientific program written using this architecture looks remarkably like the mathematics used to understand the problem, is typically an order of magnitude smaller than traditional FORTRAN or C++ codes, and hence easier to understand, debug, describe, etc. All objects in this architecture are ``network-enabled,'' which means that components of a software solution to a physical problem can be transparently loaded from anywhere on the Internet or other global network. The architecture is expressed as an ``API,'' or application programmers interface specification, with reference embeddings in Java, Python, and C++. A C++ class library for an early version of this API has been implemented for machines ranging from PC's to the IBM SP2, meaning that phidentical codes run on all architectures.

Regional shape-based feature space for segmenting biomedical images using neural networks

NASA Astrophysics Data System (ADS)

Sundaramoorthy, Gopal; Hoford, John D.; Hoffman, Eric A.

1993-07-01

In biomedical images, structure of interest, particularly the soft tissue structures, such as the heart, airways, bronchial and arterial trees often have grey-scale and textural characteristics similar to other structures in the image, making it difficult to segment them using only gray- scale and texture information. However, these objects can be visually recognized by their unique shapes and sizes. In this paper we discuss, what we believe to be, a novel, simple scheme for extracting features based on regional shapes. To test the effectiveness of these features for image segmentation (classification), we use an artificial neural network and a statistical cluster analysis technique. The proposed shape-based feature extraction algorithm computes regional shape vectors (RSVs) for all pixels that meet a certain threshold criteria. The distance from each such pixel to a boundary is computed in 8 directions (or in 26 directions for a 3-D image). Together, these 8 (or 26) values represent the pixel's (or voxel's) RSV. All RSVs from an image are used to train a multi-layered perceptron neural network which uses these features to 'learn' a suitable classification strategy. To clearly distinguish the desired object from other objects within an image, several examples from inside and outside the desired object are used for training. Several examples are presented to illustrate the strengths and weaknesses of our algorithm. Both synthetic and actual biomedical images are considered. Future extensions to this algorithm are also discussed.

Dissociable Decoding of Spatial Attention and Working Memory from EEG Oscillations and Sustained Potentials.

PubMed

Bae, Gi-Yeul; Luck, Steven J

2018-01-10

In human scalp EEG recordings, both sustained potentials and alpha-band oscillations are present during the delay period of working memory tasks and may therefore reflect the representation of information in working memory. However, these signals may instead reflect support mechanisms rather than the actual contents of memory. In particular, alpha-band oscillations have been tightly tied to spatial attention and may not reflect location-independent memory representations per se. To determine how sustained and oscillating EEG signals are related to attention and working memory, we attempted to decode which of 16 orientations was being held in working memory by human observers (both women and men). We found that sustained EEG activity could be used to decode the remembered orientation of a stimulus, even when the orientation of the stimulus varied independently of its location. Alpha-band oscillations also carried clear information about the location of the stimulus, but they provided little or no information about orientation independently of location. Thus, sustained potentials contain information about the object properties being maintained in working memory, consistent with previous evidence of a tight link between these potentials and working memory capacity. In contrast, alpha-band oscillations primarily carry location information, consistent with their link to spatial attention. SIGNIFICANCE STATEMENT Working memory plays a key role in cognition, and working memory is impaired in several neurological and psychiatric disorders. Previous research has suggested that human scalp EEG recordings contain signals that reflect the neural representation of information in working memory. However, to conclude that a neural signal actually represents the object being remembered, it is necessary to show that the signal contains fine-grained information about that object. Here, we show that sustained voltages in human EEG recordings contain fine-grained information about the orientation of an object being held in memory, consistent with a memory storage signal. Copyright © 2018 the authors 0270-6474/18/380409-14$15.00/0.

Stereo-vision-based cooperative-vehicle positioning using OCC and neural networks

NASA Astrophysics Data System (ADS)

Ifthekhar, Md. Shareef; Saha, Nirzhar; Jang, Yeong Min

2015-10-01

Vehicle positioning has been subjected to extensive research regarding driving safety measures and assistance as well as autonomous navigation. The most common positioning technique used in automotive positioning is the global positioning system (GPS). However, GPS is not reliably accurate because of signal blockage caused by high-rise buildings. In addition, GPS is error prone when a vehicle is inside a tunnel. Moreover, GPS and other radio-frequency-based approaches cannot provide orientation information or the position of neighboring vehicles. In this study, we propose a cooperative-vehicle positioning (CVP) technique by using the newly developed optical camera communications (OCC). The OCC technique utilizes image sensors and cameras to receive and decode light-modulated information from light-emitting diodes (LEDs). A vehicle equipped with an OCC transceiver can receive positioning and other information such as speed, lane change, driver's condition, etc., through optical wireless links of neighboring vehicles. Thus, the target vehicle position that is too far away to establish an OCC link can be determined by a computer-vision-based technique combined with the cooperation of neighboring vehicles. In addition, we have devised a back-propagation (BP) neural-network learning method for positioning and range estimation for CVP. The proposed neural-network-based technique can estimate target vehicle position from only two image points of target vehicles using stereo vision. For this, we use rear LEDs on target vehicles as image points. We show from simulation results that our neural-network-based method achieves better accuracy than that of the computer-vision method.

Intelligent control of robotic arm/hand systems for the NASA EVA retriever using neural networks

NASA Technical Reports Server (NTRS)

Mclauchlan, Robert A.

1989-01-01

Adaptive/general learning algorithms using varying neural network models are considered for the intelligent control of robotic arm plus dextrous hand/manipulator systems. Results are summarized and discussed for the use of the Barto/Sutton/Anderson neuronlike, unsupervised learning controller as applied to the stabilization of an inverted pendulum on a cart system. Recommendations are made for the application of the controller and a kinematic analysis for trajectory planning to simple object retrieval (chase/approach and capture/grasp) scenarios in two dimensions.

Securing Digital Images Integrity using Artificial Neural Networks

NASA Astrophysics Data System (ADS)

Hajji, Tarik; Itahriouan, Zakaria; Ouazzani Jamil, Mohammed

2018-05-01

Digital image signature is a technique used to protect the image integrity. The application of this technique can serve several areas of imaging applied to smart cities. The objective of this work is to propose two methods to protect digital image integrity. We present a description of two approaches using artificial neural networks (ANN) to digitally sign an image. The first one is “Direct Signature without learning” and the second is “Direct Signature with learning”. This paper presents the theory of proposed approaches and an experimental study to test their effectiveness.

Low Temperature Performance of High-Speed Neural Network Circuits

NASA Technical Reports Server (NTRS)

Duong, T.; Tran, M.; Daud, T.; Thakoor, A.

1995-01-01

Artificial neural networks, derived from their biological counterparts, offer a new and enabling computing paradigm specially suitable for such tasks as image and signal processing with feature classification/object recognition, global optimization, and adaptive control. When implemented in fully parallel electronic hardware, it offers orders of magnitude speed advantage. Basic building blocks of the new architecture are the processing elements called neurons implemented as nonlinear operational amplifiers with sigmoidal transfer function, interconnected through weighted connections called synapses implemented using circuitry for weight storage and multiply functions either in an analog, digital, or hybrid scheme.

The cognitive structural approach for image restoration

NASA Astrophysics Data System (ADS)

Mardare, Igor; Perju, Veacheslav; Casasent, David

2008-03-01

It is analyzed the important and actual problem of the defective images of scenes restoration. The proposed approach provides restoration of scenes by a system on the basis of human intelligence phenomena reproduction used for restoration-recognition of images. The cognitive models of the restoration process are elaborated. The models are realized by the intellectual processors constructed on the base of neural networks and associative memory using neural network simulator NNToolbox from MATLAB 7.0. The models provides restoration and semantic designing of images of scenes under defective images of the separate objects.

Ω-Net (Omega-Net): Fully automatic, multi-view cardiac MR detection, orientation, and segmentation with deep neural networks.

PubMed

Vigneault, Davis M; Xie, Weidi; Ho, Carolyn Y; Bluemke, David A; Noble, J Alison

2018-05-22

Pixelwise segmentation of the left ventricular (LV) myocardium and the four cardiac chambers in 2-D steady state free precession (SSFP) cine sequences is an essential preprocessing step for a wide range of analyses. Variability in contrast, appearance, orientation, and placement of the heart between patients, clinical views, scanners, and protocols makes fully automatic semantic segmentation a notoriously difficult problem. Here, we present Ω-Net (Omega-Net): A novel convolutional neural network (CNN) architecture for simultaneous localization, transformation into a canonical orientation, and semantic segmentation. First, an initial segmentation is performed on the input image; second, the features learned during this initial segmentation are used to predict the parameters needed to transform the input image into a canonical orientation; and third, a final segmentation is performed on the transformed image. In this work, Ω-Nets of varying depths were trained to detect five foreground classes in any of three clinical views (short axis, SA; four-chamber, 4C; two-chamber, 2C), without prior knowledge of the view being segmented. This constitutes a substantially more challenging problem compared with prior work. The architecture was trained using three-fold cross-validation on a cohort of patients with hypertrophic cardiomyopathy (HCM, N=42) and healthy control subjects (N=21). Network performance, as measured by weighted foreground intersection-over-union (IoU), was substantially improved for the best-performing Ω-Net compared with U-Net segmentation without localization or orientation (0.858 vs 0.834). In addition, to be comparable with other works, Ω-Net was retrained from scratch using five-fold cross-validation on the publicly available 2017 MICCAI Automated Cardiac Diagnosis Challenge (ACDC) dataset. The Ω-Net outperformed the state-of-the-art method in segmentation of the LV and RV bloodpools, and performed slightly worse in segmentation of the LV myocardium. We conclude that this architecture represents a substantive advancement over prior approaches, with implications for biomedical image segmentation more generally. Published by Elsevier B.V.

Optimization of matrix tablets controlled drug release using Elman dynamic neural networks and decision trees.

PubMed

Petrović, Jelena; Ibrić, Svetlana; Betz, Gabriele; Đurić, Zorica

2012-05-30

The main objective of the study was to develop artificial intelligence methods for optimization of drug release from matrix tablets regardless of the matrix type. Static and dynamic artificial neural networks of the same topology were developed to model dissolution profiles of different matrix tablets types (hydrophilic/lipid) using formulation composition, compression force used for tableting and tablets porosity and tensile strength as input data. Potential application of decision trees in discovering knowledge from experimental data was also investigated. Polyethylene oxide polymer and glyceryl palmitostearate were used as matrix forming materials for hydrophilic and lipid matrix tablets, respectively whereas selected model drugs were diclofenac sodium and caffeine. Matrix tablets were prepared by direct compression method and tested for in vitro dissolution profiles. Optimization of static and dynamic neural networks used for modeling of drug release was performed using Monte Carlo simulations or genetic algorithms optimizer. Decision trees were constructed following discretization of data. Calculated difference (f(1)) and similarity (f(2)) factors for predicted and experimentally obtained dissolution profiles of test matrix tablets formulations indicate that Elman dynamic neural networks as well as decision trees are capable of accurate predictions of both hydrophilic and lipid matrix tablets dissolution profiles. Elman neural networks were compared to most frequently used static network, Multi-layered perceptron, and superiority of Elman networks have been demonstrated. Developed methods allow simple, yet very precise way of drug release predictions for both hydrophilic and lipid matrix tablets having controlled drug release. Copyright © 2012 Elsevier B.V. All rights reserved.

Frontoparietal regions may become hypoactive after intermittent theta burst stimulation over the contralateral homologous cortex in humans.

PubMed

He, Xiaofei; Lan, Yue; Xu, Guangqing; Mao, Yurong; Chen, Zhenghong; Huang, Dongfeng; Pei, Zhong

2013-12-01

Brain injury to the dorsal frontoparietal networks, including the posterior parietal cortex (PPC) and dorsolateral prefrontal cortex (DLPFC), commonly cause spatial neglect. However, the interaction of these different regions in spatial attention is unclear. The aim of the present study was to investigate whether hyperexcitable neural networks can cause an abnormal interhemispheric inhibition. The Attention Network Test was used to test subjects following intermittent theta burst stimulation (iTBS) to the left or right frontoparietal networks. During the Attention Network Test task, all subjects tolerated each conditioning iTBS without any obvious iTBS-related side effects. Subjects receiving real-right-PPC iTBS showed significant enhancement in both alerting and orienting efficiency compared with those receiving either sham-right-PPC iTBS or real-left-PPC iTBS. Moreover, subjects exposed to the real-right-DLPFC iTBS exhibited significant improvement in both alerting and executive control efficiency, compared with those exposed to either the sham-right-DLPFC or real-left-DLPFC conditioning. Interestingly, compared with subjects exposed to the sham-left-PPC stimuli, subjects exposed to the real-left-PPC iTBS had a significant deficit in the orienting index. The present study indicates that iTBS over the contralateral homologous cortex may induce the hypoactivity of the right PPC through interhemispheric competition in spatial orienting attention.

Development of Tool Representations in the Dorsal and Ventral Visual Object Processing Pathways.

PubMed

Kersey, Alyssa J; Clark, Tyia S; Lussier, Courtney A; Mahon, Bradford Z; Cantlon, Jessica F

2016-07-01

Tools represent a special class of objects, because they are processed across both the dorsal and ventral visual object processing pathways. Three core regions are known to be involved in tool processing: the left posterior middle temporal gyrus, the medial fusiform gyrus (bilaterally), and the left inferior parietal lobule. A critical and relatively unexplored issue concerns whether, in development, tool preferences emerge at the same time and to a similar degree across all regions of the tool-processing network. To test this issue, we used functional magnetic resonance imaging to measure the neural amplitude, peak location, and the dispersion of tool-related neural responses in the youngest sample of children tested to date in this domain (ages 4-8 years). We show that children recruit overlapping regions of the adult tool-processing network and also exhibit similar patterns of co-activation across the network to adults. The amplitude and co-activation data show that the core components of the tool-processing network are established by age 4. Our findings on the distributions of peak location and dispersion of activation indicate that the tool network undergoes refinement between ages 4 and 8 years. © The Author 2015. Published by Oxford University Press. All rights reserved. For Permissions, please e-mail: journals.permissions@oup.com.

Application of an object-oriented programming paradigm in three-dimensional computer modeling of mechanically active gastrointestinal tissues.

PubMed

Rashev, P Z; Mintchev, M P; Bowes, K L

2000-09-01

The aim of this study was to develop a novel three-dimensional (3-D) object-oriented modeling approach incorporating knowledge of the anatomy, electrophysiology, and mechanics of externally stimulated excitable gastrointestinal (GI) tissues and emphasizing the "stimulus-response" principle of extracting the modeling parameters. The modeling method used clusters of class hierarchies representing GI tissues from three perspectives: 1) anatomical; 2) electrophysiological; and 3) mechanical. We elaborated on the first four phases of the object-oriented system development life-cycle: 1) analysis; 2) design; 3) implementation; and 4) testing. Generalized cylinders were used for the implementation of 3-D tissue objects modeling the cecum, the descending colon, and the colonic circular smooth muscle tissue. The model was tested using external neural electrical tissue excitation of the descending colon with virtual implanted electrodes and the stimulating current density distributions over the modeled surfaces were calculated. Finally, the tissue deformations invoked by electrical stimulation were estimated and represented by a mesh-surface visualization technique.

Polarized skylight navigation in insects: model and electrophysiology of e-vector coding by neurons in the central complex.

PubMed

Sakura, Midori; Lambrinos, Dimitrios; Labhart, Thomas

2008-02-01

Many insects exploit skylight polarization for visual compass orientation or course control. As found in crickets, the peripheral visual system (optic lobe) contains three types of polarization-sensitive neurons (POL neurons), which are tuned to different ( approximately 60 degrees diverging) e-vector orientations. Thus each e-vector orientation elicits a specific combination of activities among the POL neurons coding any e-vector orientation by just three neural signals. In this study, we hypothesize that in the presumed orientation center of the brain (central complex) e-vector orientation is population-coded by a set of "compass neurons." Using computer modeling, we present a neural network model transforming the signal triplet provided by the POL neurons to compass neuron activities coding e-vector orientation by a population code. Using intracellular electrophysiology and cell marking, we present evidence that neurons with the response profile of the presumed compass neurons do indeed exist in the insect brain: each of these compass neuron-like (CNL) cells is activated by a specific e-vector orientation only and otherwise remains silent. Morphologically, CNL cells are tangential neurons extending from the lateral accessory lobe to the lower division of the central body. Surpassing the modeled compass neurons in performance, CNL cells are insensitive to the degree of polarization of the stimulus between 99% and at least down to 18% polarization and thus largely disregard variations of skylight polarization due to changing solar elevations or atmospheric conditions. This suggests that the polarization vision system includes a gain control circuit keeping the output activity at a constant level.

Haptically Guided Grasping. fMRI Shows Right-Hemisphere Parietal Stimulus Encoding, and Bilateral Dorso-Ventral Parietal Gradients of Object- and Action-Related Processing during Grasp Execution

PubMed Central

Marangon, Mattia; Kubiak, Agnieszka; Króliczak, Gregory

2016-01-01

The neural bases of haptically-guided grasp planning and execution are largely unknown, especially for stimuli having no visual representations. Therefore, we used functional magnetic resonance imaging (fMRI) to monitor brain activity during haptic exploration of novel 3D complex objects, subsequent grasp planning, and the execution of the pre-planned grasps. Haptic object exploration, involving extraction of shape, orientation, and length of the to-be-grasped targets, was associated with the fronto-parietal, temporo-occipital, and insular cortex activity. Yet, only the anterior divisions of the posterior parietal cortex (PPC) of the right hemisphere were significantly more engaged in exploration of complex objects (vs. simple control disks). None of these regions were re-recruited during the planning phase. Even more surprisingly, the left-hemisphere intraparietal, temporal, and occipital areas that were significantly invoked for grasp planning did not show sensitivity to object features. Finally, grasp execution, involving the re-recruitment of the critical right-hemisphere PPC clusters, was also significantly associated with two kinds of bilateral parieto-frontal processes. The first represents transformations of grasp-relevant target features and is linked to the dorso-dorsal (lateral and medial) parieto-frontal networks. The second monitors grasp kinematics and belongs to the ventro-dorsal networks. Indeed, signal modulations associated with these distinct functions follow dorso-ventral gradients, with left aIPS showing significant sensitivity to both target features and the characteristics of the required grasp. Thus, our results from the haptic domain are consistent with the notion that the parietal processing for action guidance reflects primarily transformations from object-related to effector-related coding, and these mechanisms are rather independent of sensory input modality. PMID:26779002

Haptically Guided Grasping. fMRI Shows Right-Hemisphere Parietal Stimulus Encoding, and Bilateral Dorso-Ventral Parietal Gradients of Object- and Action-Related Processing during Grasp Execution.

PubMed

Marangon, Mattia; Kubiak, Agnieszka; Króliczak, Gregory

2015-01-01

The neural bases of haptically-guided grasp planning and execution are largely unknown, especially for stimuli having no visual representations. Therefore, we used functional magnetic resonance imaging (fMRI) to monitor brain activity during haptic exploration of novel 3D complex objects, subsequent grasp planning, and the execution of the pre-planned grasps. Haptic object exploration, involving extraction of shape, orientation, and length of the to-be-grasped targets, was associated with the fronto-parietal, temporo-occipital, and insular cortex activity. Yet, only the anterior divisions of the posterior parietal cortex (PPC) of the right hemisphere were significantly more engaged in exploration of complex objects (vs. simple control disks). None of these regions were re-recruited during the planning phase. Even more surprisingly, the left-hemisphere intraparietal, temporal, and occipital areas that were significantly invoked for grasp planning did not show sensitivity to object features. Finally, grasp execution, involving the re-recruitment of the critical right-hemisphere PPC clusters, was also significantly associated with two kinds of bilateral parieto-frontal processes. The first represents transformations of grasp-relevant target features and is linked to the dorso-dorsal (lateral and medial) parieto-frontal networks. The second monitors grasp kinematics and belongs to the ventro-dorsal networks. Indeed, signal modulations associated with these distinct functions follow dorso-ventral gradients, with left aIPS showing significant sensitivity to both target features and the characteristics of the required grasp. Thus, our results from the haptic domain are consistent with the notion that the parietal processing for action guidance reflects primarily transformations from object-related to effector-related coding, and these mechanisms are rather independent of sensory input modality.

Component Pin Recognition Using Algorithms Based on Machine Learning

NASA Astrophysics Data System (ADS)

Xiao, Yang; Hu, Hong; Liu, Ze; Xu, Jiangchang

2018-04-01

The purpose of machine vision for a plug-in machine is to improve the machine’s stability and accuracy, and recognition of the component pin is an important part of the vision. This paper focuses on component pin recognition using three different techniques. The first technique involves traditional image processing using the core algorithm for binary large object (BLOB) analysis. The second technique uses the histogram of oriented gradients (HOG), to experimentally compare the effect of the support vector machine (SVM) and the adaptive boosting machine (AdaBoost) learning meta-algorithm classifiers. The third technique is the use of an in-depth learning method known as convolution neural network (CNN), which involves identifying the pin by comparing a sample to its training. The main purpose of the research presented in this paper is to increase the knowledge of learning methods used in the plug-in machine industry in order to achieve better results.

Preliminary research on eddy current bobbin quantitative test for heat exchange tube in nuclear power plant

NASA Astrophysics Data System (ADS)

Qi, Pan; Shao, Wenbin; Liao, Shusheng

2016-02-01

For quantitative defects detection research on heat transfer tube in nuclear power plants (NPP), two parts of work are carried out based on the crack as the main research objects. (1) Production optimization of calibration tube. Firstly, ASME, RSEM and homemade crack calibration tubes are applied to quantitatively analyze the defects depth on other designed crack test tubes, and then the judgment with quantitative results under crack calibration tube with more accuracy is given. Base on that, weight analysis of influence factors for crack depth quantitative test such as crack orientation, length, volume and so on can be undertaken, which will optimize manufacture technology of calibration tubes. (2) Quantitative optimization of crack depth. Neural network model with multi-calibration curve adopted to optimize natural crack test depth generated in in-service tubes shows preliminary ability to improve quantitative accuracy.

Personalized recommendation via an improved NBI algorithm and user influence model in a Microblog network

NASA Astrophysics Data System (ADS)

Lian, Jie; Liu, Yun; Zhang, Zhen-jiang; Gui, Chang-ni

2013-10-01

Bipartite network based recommendations have attracted extensive attentions in recent years. Differing from traditional object-oriented recommendations, the recommendation in a Microblog network has two crucial differences. One is high authority users or one’s special friends usually play a very active role in tweet-oriented recommendation. The other is that the object in a Microblog network corresponds to a set of tweets on same topic instead of an actual and single entity, e.g. goods or movies in traditional networks. Thus repeat recommendations of the tweets in one’s collected topics are indispensable. Therefore, this paper improves network based inference (NBI) algorithm by original link matrix and link weight on resource allocation processes. This paper finally proposes the Microblog recommendation model based on the factors of improved network based inference and user influence model. Adjusting the weights of these two factors could generate the best recommendation results in algorithm accuracy and recommendation personalization.

SISSY: An example of a multi-threaded, networked, object-oriented databased application

DOE Office of Scientific and Technical Information (OSTI.GOV)

Scipioni, B.; Liu, D.; Song, T.

1993-05-01

The Systems Integration Support SYstem (SISSY) is presented and its capabilities and techniques are discussed. It is fully automated data collection and analysis system supporting the SSCL`s systems analysis activities as they relate to the Physics Detector and Simulation Facility (PDSF). SISSY itself is a paradigm of effective computing on the PDSF. It uses home-grown code (C++), network programming (RPC, SNMP), relational (SYBASE) and object-oriented (ObjectStore) DBMSs, UNIX operating system services (IRIX threads, cron, system utilities, shells scripts, etc.), and third party software applications (NetCentral Station, Wingz, DataLink) all of which act together as a single application to monitor andmore » analyze the PDSF.« less

Determining root correspondence between previously and newly detected objects

DOEpatents

Paglieroni, David W.; Beer, N Reginald

2014-06-17

A system that applies attribute and topology based change detection to networks of objects that were detected on previous scans of a structure, roadway, or area of interest. The attributes capture properties or characteristics of the previously detected objects, such as location, time of detection, size, elongation, orientation, etc. The topology of the network of previously detected objects is maintained in a constellation database that stores attributes of previously detected objects and implicitly captures the geometrical structure of the network. A change detection system detects change by comparing the attributes and topology of new objects detected on the latest scan to the constellation database of previously detected objects.

Surface immobilized antibody orientation determined using ToF-SIMS and multivariate analysis.

PubMed

Welch, Nicholas G; Madiona, Robert M T; Payten, Thomas B; Easton, Christopher D; Pontes-Braz, Luisa; Brack, Narelle; Scoble, Judith A; Muir, Benjamin W; Pigram, Paul J

2017-06-01

Antibody orientation at solid phase interfaces plays a critical role in the sensitive detection of biomolecules during immunoassays. Correctly oriented antibodies with solution-facing antigen binding regions have improved antigen capture as compared to their randomly oriented counterparts. Direct characterization of oriented proteins with surface analysis methods still remains a challenge however surface sensitive techniques such as Time-of-Flight Secondary Ion Mass Spectrometry (ToF-SIMS) provide information-rich data that can be used to probe antibody orientation. Diethylene glycol dimethyl ether plasma polymers (DGpp) functionalized with chromium (DGpp+Cr) have improved immunoassay performance that is indicative of preferential antibody orientation. Herein, ToF-SIMS data from proteolytic fragments of anti-EGFR antibody bound to DGpp and DGpp+Cr are used to construct artificial neural network (ANN) and principal component analysis (PCA) models indicative of correctly oriented systems. Whole antibody samples (IgG) test against each of the models indicated preferential antibody orientation on DGpp+Cr. Cross-reference between ANN and PCA models yield 20 mass fragments associated with F(ab') 2 region representing correct orientation, and 23 mass fragments associated with the Fc region representing incorrect orientation. Mass fragments were then compared to amino acid fragments and amino acid composition in F(ab') 2 and Fc regions. A ratio of the sum of the ToF-SIMS ion intensities from the F(ab') 2 fragments to the Fc fragments demonstrated a 50% increase in intensity for IgG on DGpp+Cr as compared to DGpp. The systematic data analysis methodology employed herein offers a new approach for the investigation of antibody orientation applicable to a range of substrates. Controlled orientation of antibodies at solid phases is critical for maximizing antigen detection in biosensors and immunoassays. Surface-sensitive techniques (such as ToF-SIMS), capable of direct characterization of surface immobilized and oriented antibodies, are under-utilized in current practice. Selection of a small number of mass fragments for analysis, typically pertaining to amino acids, is commonplace in literature, leaving the majority of the information-rich spectra unanalyzed. The novelty of this work is the utilization of a comprehensive, unbiased mass fragment list and the employment of principal component analysis (PCA) and artificial neural network (ANN) models in a unique methodology to prove antibody orientation. This methodology is of significant and broad interest to the scientific community as it is applicable to a range of substrates and allows for direct, label-free characterization of surface bound proteins. Copyright © 2017 Acta Materialia Inc. All rights reserved.

Adaptive neural network motion control for aircraft under uncertainty conditions

NASA Astrophysics Data System (ADS)

Efremov, A. V.; Tiaglik, M. S.; Tiumentsev, Yu V.

2018-02-01

We need to provide motion control of modern and advanced aircraft under diverse uncertainty conditions. This problem can be solved by using adaptive control laws. We carry out an analysis of the capabilities of these laws for such adaptive systems as MRAC (Model Reference Adaptive Control) and MPC (Model Predictive Control). In the case of a nonlinear control object, the most efficient solution to the adaptive control problem is the use of neural network technologies. These technologies are suitable for the development of both a control object model and a control law for the object. The approximate nature of the ANN model was taken into account by introducing additional compensating feedback into the control system. The capabilities of adaptive control laws under uncertainty in the source data are considered. We also conduct simulations to assess the contribution of adaptivity to the behavior of the system.

Distant Speech Recognition Using a Microphone Array Network

NASA Astrophysics Data System (ADS)

Nakano, Alberto Yoshihiro; Nakagawa, Seiichi; Yamamoto, Kazumasa

In this work, spatial information consisting of the position and orientation angle of an acoustic source is estimated by an artificial neural network (ANN). The estimated position of a speaker in an enclosed space is used to refine the estimated time delays for a delay-and-sum beamformer, thus enhancing the output signal. On the other hand, the orientation angle is used to restrict the lexicon used in the recognition phase, assuming that the speaker faces a particular direction while speaking. To compensate the effect of the transmission channel inside a short frame analysis window, a new cepstral mean normalization (CMN) method based on a Gaussian mixture model (GMM) is investigated and shows better performance than the conventional CMN for short utterances. The performance of the proposed method is evaluated through Japanese digit/command recognition experiments.

An object recognition method based on fuzzy theory and BP networks

NASA Astrophysics Data System (ADS)

Wu, Chuan; Zhu, Ming; Yang, Dong

2006-01-01

It is difficult to choose eigenvectors when neural network recognizes object. It is possible that the different object eigenvectors is similar or the same object eigenvectors is different under scaling, shifting, rotation if eigenvectors can not be chosen appropriately. In order to solve this problem, the image is edged, the membership function is reconstructed and a new threshold segmentation method based on fuzzy theory is proposed to get the binary image. Moment invariant of binary image is extracted and normalized. Some time moment invariant is too small to calculate effectively so logarithm of moment invariant is taken as input eigenvectors of BP network. The experimental results demonstrate that the proposed approach could recognize the object effectively, correctly and quickly.

Real-time Adaptive Control Using Neural Generalized Predictive Control

NASA Technical Reports Server (NTRS)

Haley, Pam; Soloway, Don; Gold, Brian

1999-01-01

The objective of this paper is to demonstrate the feasibility of a Nonlinear Generalized Predictive Control algorithm by showing real-time adaptive control on a plant with relatively fast time-constants. Generalized Predictive Control has classically been used in process control where linear control laws were formulated for plants with relatively slow time-constants. The plant of interest for this paper is a magnetic levitation device that is nonlinear and open-loop unstable. In this application, the reference model of the plant is a neural network that has an embedded nominal linear model in the network weights. The control based on the linear model provides initial stability at the beginning of network training. In using a neural network the control laws are nonlinear and online adaptation of the model is possible to capture unmodeled or time-varying dynamics. Newton-Raphson is the minimization algorithm. Newton-Raphson requires the calculation of the Hessian, but even with this computational expense the low iteration rate make this a viable algorithm for real-time control.

Regional application of multi-layer artificial neural networks in 3-D ionosphere tomography

NASA Astrophysics Data System (ADS)

Ghaffari Razin, Mir Reza; Voosoghi, Behzad

2016-08-01

Tomography is a very cost-effective method to study physical properties of the ionosphere. In this paper, residual minimization training neural network (RMTNN) is used in voxel-based tomography to reconstruct of 3-D ionosphere electron density with high spatial resolution. For numerical experiments, observations collected at 37 GPS stations from Iranian permanent GPS network (IPGN) are used. A smoothed TEC approach was used for absolute STEC recovery. To improve the vertical resolution, empirical orthogonal functions (EOFs) obtained from international reference ionosphere 2012 (IRI-2012) used as object function in training neural network. Ionosonde observations is used for validate reliability of the proposed method. Minimum relative error for RMTNN is 1.64% and maximum relative error is 15.61%. Also root mean square error (RMSE) of 0.17 × 1011 (electrons/m3) is computed for RMTNN which is less than RMSE of IRI2012. The results show that RMTNN has higher accuracy and compiles speed than other ionosphere reconstruction methods.

DeepID-Net: Deformable Deep Convolutional Neural Networks for Object Detection.

PubMed

Ouyang, Wanli; Zeng, Xingyu; Wang, Xiaogang; Qiu, Shi; Luo, Ping; Tian, Yonglong; Li, Hongsheng; Yang, Shuo; Wang, Zhe; Li, Hongyang; Loy, Chen Change; Wang, Kun; Yan, Junjie; Tang, Xiaoou

2016-07-07

In this paper, we propose deformable deep convolutional neural networks for generic object detection. This new deep learning object detection framework has innovations in multiple aspects. In the proposed new deep architecture, a new deformation constrained pooling (def-pooling) layer models the deformation of object parts with geometric constraint and penalty. A new pre-training strategy is proposed to learn feature representations more suitable for the object detection task and with good generalization capability. By changing the net structures, training strategies, adding and removing some key components in the detection pipeline, a set of models with large diversity are obtained, which significantly improves the effectiveness of model averaging. The proposed approach improves the mean averaged precision obtained by RCNN [16], which was the state-of-the-art, from 31% to 50.3% on the ILSVRC2014 detection test set. It also outperforms the winner of ILSVRC2014, GoogLeNet, by 6.1%. Detailed component-wise analysis is also provided through extensive experimental evaluation, which provides a global view for people to understand the deep learning object detection pipeline.

Mechanisms of Innovation Diffusion under Information Abundance and Information Scarcity--On the Contribution of Social Networks in Group vs. Individual Extension Approaches in Semi-Arid Kenya

ERIC Educational Resources Information Center

Darr, Dietrich; Pretzsch, Jurgen

2008-01-01

Purpose: The objective of this paper is to assess the effectiveness of innovation diffusion under group-oriented and individual-oriented extension. Current theoretical notions of innovation diffusion in social networks shall be briefly reviewed, and the concepts of "search" and "innovation" vis-a-vis "transfer" and…

Cellular neural network-based hybrid approach toward automatic image registration

NASA Astrophysics Data System (ADS)

Arun, Pattathal VijayaKumar; Katiyar, Sunil Kumar

2013-01-01

Image registration is a key component of various image processing operations that involve the analysis of different image data sets. Automatic image registration domains have witnessed the application of many intelligent methodologies over the past decade; however, inability to properly model object shape as well as contextual information has limited the attainable accuracy. A framework for accurate feature shape modeling and adaptive resampling using advanced techniques such as vector machines, cellular neural network (CNN), scale invariant feature transform (SIFT), coreset, and cellular automata is proposed. CNN has been found to be effective in improving feature matching as well as resampling stages of registration and complexity of the approach has been considerably reduced using coreset optimization. The salient features of this work are cellular neural network approach-based SIFT feature point optimization, adaptive resampling, and intelligent object modelling. Developed methodology has been compared with contemporary methods using different statistical measures. Investigations over various satellite images revealed that considerable success was achieved with the approach. This system has dynamically used spectral and spatial information for representing contextual knowledge using CNN-prolog approach. This methodology is also illustrated to be effective in providing intelligent interpretation and adaptive resampling.

A Real-Time Method to Estimate Speed of Object Based on Object Detection and Optical Flow Calculation

NASA Astrophysics Data System (ADS)

Liu, Kaizhan; Ye, Yunming; Li, Xutao; Li, Yan

2018-04-01

In recent years Convolutional Neural Network (CNN) has been widely used in computer vision field and makes great progress in lots of contents like object detection and classification. Even so, combining Convolutional Neural Network, which means making multiple CNN frameworks working synchronously and sharing their output information, could figure out useful message that each of them cannot provide singly. Here we introduce a method to real-time estimate speed of object by combining two CNN: YOLOv2 and FlowNet. In every frame, YOLOv2 provides object size; object location and object type while FlowNet providing the optical flow of whole image. On one hand, object size and object location help to select out the object part of optical flow image thus calculating out the average optical flow of every object. On the other hand, object type and object size help to figure out the relationship between optical flow and true speed by means of optics theory and priori knowledge. Therefore, with these two key information, speed of object can be estimated. This method manages to estimate multiple objects at real-time speed by only using a normal camera even in moving status, whose error is acceptable in most application fields like manless driving or robot vision.

"Geo-statistics methods and neural networks in geophysical applications: A case study"

NASA Astrophysics Data System (ADS)

Rodriguez Sandoval, R.; Urrutia Fucugauchi, J.; Ramirez Cruz, L. C.

2008-12-01

The study is focus in the Ebano-Panuco basin of northeastern Mexico, which is being explored for hydrocarbon reservoirs. These reservoirs are in limestones and there is interest in determining porosity and permeability in the carbonate sequences. The porosity maps presented in this study are estimated from application of multiattribute and neural networks techniques, which combine geophysics logs and 3-D seismic data by means of statistical relationships. The multiattribute analysis is a process to predict a volume of any underground petrophysical measurement from well-log and seismic data. The data consist of a series of target logs from wells which tie a 3-D seismic volume. The target logs are neutron porosity logs. From the 3-D seismic volume a series of sample attributes is calculated. The objective of this study is to derive a set of attributes and the target log values. The selected set is determined by a process of forward stepwise regression. The analysis can be linear or nonlinear. In the linear mode the method consists of a series of weights derived by least-square minimization. In the nonlinear mode, a neural network is trained using the select attributes as inputs. In this case we used a probabilistic neural network PNN. The method is applied to a real data set from PEMEX. For better reservoir characterization the porosity distribution was estimated using both techniques. The case shown a continues improvement in the prediction of the porosity from the multiattribute to the neural network analysis. The improvement is in the training and the validation, which are important indicators of the reliability of the results. The neural network showed an improvement in resolution over the multiattribute analysis. The final maps provide more realistic results of the porosity distribution.

Real-time classification of vehicles by type within infrared imagery

NASA Astrophysics Data System (ADS)

Kundegorski, Mikolaj E.; Akçay, Samet; Payen de La Garanderie, Grégoire; Breckon, Toby P.

2016-10-01

Real-time classification of vehicles into sub-category types poses a significant challenge within infra-red imagery due to the high levels of intra-class variation in thermal vehicle signatures caused by aspects of design, current operating duration and ambient thermal conditions. Despite these challenges, infra-red sensing offers significant generalized target object detection advantages in terms of all-weather operation and invariance to visual camouflage techniques. This work investigates the accuracy of a number of real-time object classification approaches for this task within the wider context of an existing initial object detection and tracking framework. Specifically we evaluate the use of traditional feature-driven bag of visual words and histogram of oriented gradient classification approaches against modern convolutional neural network architectures. Furthermore, we use classical photogrammetry, within the context of current target detection and classification techniques, as a means of approximating 3D target position within the scene based on this vehicle type classification. Based on photogrammetric estimation of target position, we then illustrate the use of regular Kalman filter based tracking operating on actual 3D vehicle trajectories. Results are presented using a conventional thermal-band infra-red (IR) sensor arrangement where targets are tracked over a range of evaluation scenarios.

Coordinating complex problem-solving among distributed intelligent agents

NASA Technical Reports Server (NTRS)

Adler, Richard M.

1992-01-01

A process-oriented control model is described for distributed problem solving. The model coordinates the transfer and manipulation of information across independent networked applications, both intelligent and conventional. The model was implemented using SOCIAL, a set of object-oriented tools for distributing computing. Complex sequences of distributed tasks are specified in terms of high level scripts. Scripts are executed by SOCIAL objects called Manager Agents, which realize an intelligent coordination model that routes individual tasks to suitable server applications across the network. These tools are illustrated in a prototype distributed system for decision support of ground operations for NASA's Space Shuttle fleet.

An fMRI Study of the Neural Systems Involved in Visually Cued Auditory Top-Down Spatial and Temporal Attention

PubMed Central

Li, Chunlin; Chen, Kewei; Han, Hongbin; Chui, Dehua; Wu, Jinglong

2012-01-01

Top-down attention to spatial and temporal cues has been thoroughly studied in the visual domain. However, because the neural systems that are important for auditory top-down temporal attention (i.e., attention based on time interval cues) remain undefined, the differences in brain activity between directed attention to auditory spatial location (compared with time intervals) are unclear. Using fMRI (magnetic resonance imaging), we measured the activations caused by cue-target paradigms by inducing the visual cueing of attention to an auditory target within a spatial or temporal domain. Imaging results showed that the dorsal frontoparietal network (dFPN), which consists of the bilateral intraparietal sulcus and the frontal eye field, responded to spatial orienting of attention, but activity was absent in the bilateral frontal eye field (FEF) during temporal orienting of attention. Furthermore, the fMRI results indicated that activity in the right ventrolateral prefrontal cortex (VLPFC) was significantly stronger during spatial orienting of attention than during temporal orienting of attention, while the DLPFC showed no significant differences between the two processes. We conclude that the bilateral dFPN and the right VLPFC contribute to auditory spatial orienting of attention. Furthermore, specific activations related to temporal cognition were confirmed within the superior occipital gyrus, tegmentum, motor area, thalamus and putamen. PMID:23166800

Comparative Study of Neural Network Frameworks for the Next Generation of Adaptive Optics Systems.

PubMed

González-Gutiérrez, Carlos; Santos, Jesús Daniel; Martínez-Zarzuela, Mario; Basden, Alistair G; Osborn, James; Díaz-Pernas, Francisco Javier; De Cos Juez, Francisco Javier

2017-06-02

Many of the next generation of adaptive optics systems on large and extremely large telescopes require tomographic techniques in order to correct for atmospheric turbulence over a large field of view. Multi-object adaptive optics is one such technique. In this paper, different implementations of a tomographic reconstructor based on a machine learning architecture named "CARMEN" are presented. Basic concepts of adaptive optics are introduced first, with a short explanation of three different control systems used on real telescopes and the sensors utilised. The operation of the reconstructor, along with the three neural network frameworks used, and the developed CUDA code are detailed. Changes to the size of the reconstructor influence the training and execution time of the neural network. The native CUDA code turns out to be the best choice for all the systems, although some of the other frameworks offer good performance under certain circumstances.

Alexnet Feature Extraction and Multi-Kernel Learning for Objectoriented Classification

NASA Astrophysics Data System (ADS)

Ding, L.; Li, H.; Hu, C.; Zhang, W.; Wang, S.

2018-04-01

In view of the fact that the deep convolutional neural network has stronger ability of feature learning and feature expression, an exploratory research is done on feature extraction and classification for high resolution remote sensing images. Taking the Google image with 0.3 meter spatial resolution in Ludian area of Yunnan Province as an example, the image segmentation object was taken as the basic unit, and the pre-trained AlexNet deep convolution neural network model was used for feature extraction. And the spectral features, AlexNet features and GLCM texture features are combined with multi-kernel learning and SVM classifier, finally the classification results were compared and analyzed. The results show that the deep convolution neural network can extract more accurate remote sensing image features, and significantly improve the overall accuracy of classification, and provide a reference value for earthquake disaster investigation and remote sensing disaster evaluation.

Review of Medical Image Classification using the Adaptive Neuro-Fuzzy Inference System

PubMed Central

Hosseini, Monireh Sheikh; Zekri, Maryam

2012-01-01

Image classification is an issue that utilizes image processing, pattern recognition and classification methods. Automatic medical image classification is a progressive area in image classification, and it is expected to be more developed in the future. Because of this fact, automatic diagnosis can assist pathologists by providing second opinions and reducing their workload. This paper reviews the application of the adaptive neuro-fuzzy inference system (ANFIS) as a classifier in medical image classification during the past 16 years. ANFIS is a fuzzy inference system (FIS) implemented in the framework of an adaptive fuzzy neural network. It combines the explicit knowledge representation of an FIS with the learning power of artificial neural networks. The objective of ANFIS is to integrate the best features of fuzzy systems and neural networks. A brief comparison with other classifiers, main advantages and drawbacks of this classifier are investigated. PMID:23493054

Optimization of a Multi-Stage ATR System for Small Target Identification

NASA Technical Reports Server (NTRS)

Lin, Tsung-Han; Lu, Thomas; Braun, Henry; Edens, Western; Zhang, Yuhan; Chao, Tien- Hsin; Assad, Christopher; Huntsberger, Terrance

2010-01-01

An Automated Target Recognition system (ATR) was developed to locate and target small object in images and videos. The data is preprocessed and sent to a grayscale optical correlator (GOC) filter to identify possible regionsof- interest (ROIs). Next, features are extracted from ROIs based on Principal Component Analysis (PCA) and sent to neural network (NN) to be classified. The features are analyzed by the NN classifier indicating if each ROI contains the desired target or not. The ATR system was found useful in identifying small boats in open sea. However, due to "noisy background," such as weather conditions, background buildings, or water wakes, some false targets are mis-classified. Feedforward backpropagation and Radial Basis neural networks are optimized for generalization of representative features to reduce false-alarm rate. The neural networks are compared for their performance in classification accuracy, classifying time, and training time.

Modeling and simulation of permanent magnet synchronous motor based on neural network control strategy

NASA Astrophysics Data System (ADS)

Luo, Bingyang; Chi, Shangjie; Fang, Man; Li, Mengchao

2017-03-01

Permanent magnet synchronous motor is used widely in industry, the performance requirements wouldn't be met by adopting traditional PID control in some of the occasions with high requirements. In this paper, a hybrid control strategy - nonlinear neural network PID and traditional PID parallel control are adopted. The high stability and reliability of traditional PID was combined with the strong adaptive ability and robustness of neural network. The permanent magnet synchronous motor will get better control performance when switch different working modes according to different controlled object conditions. As the results showed, the speed response adopting the composite control strategy in this paper was faster than the single control strategy. And in the case of sudden disturbance, the recovery time adopting the composite control strategy designed in this paper was shorter, the recovery ability and the robustness were stronger.

Comparative Study of Neural Network Frameworks for the Next Generation of Adaptive Optics Systems

PubMed Central

González-Gutiérrez, Carlos; Santos, Jesús Daniel; Martínez-Zarzuela, Mario; Basden, Alistair G.; Osborn, James; Díaz-Pernas, Francisco Javier; De Cos Juez, Francisco Javier

2017-01-01

Many of the next generation of adaptive optics systems on large and extremely large telescopes require tomographic techniques in order to correct for atmospheric turbulence over a large field of view. Multi-object adaptive optics is one such technique. In this paper, different implementations of a tomographic reconstructor based on a machine learning architecture named “CARMEN” are presented. Basic concepts of adaptive optics are introduced first, with a short explanation of three different control systems used on real telescopes and the sensors utilised. The operation of the reconstructor, along with the three neural network frameworks used, and the developed CUDA code are detailed. Changes to the size of the reconstructor influence the training and execution time of the neural network. The native CUDA code turns out to be the best choice for all the systems, although some of the other frameworks offer good performance under certain circumstances. PMID:28574426

Deep Neural Networks for Speech Separation With Application to Robust Speech Recognition

DTIC Science & Technology

acoustic -phonetic features. The second objective is integration of spectrotemporal context for improved separation performance. Conditional random fields...will be used to encode contextual constraints. The third objective is to achieve robust ASR in the DNN framework through integrated acoustic modeling

Gender Recognition from Human-Body Images Using Visible-Light and Thermal Camera Videos Based on a Convolutional Neural Network for Image Feature Extraction

PubMed Central

Nguyen, Dat Tien; Kim, Ki Wan; Hong, Hyung Gil; Koo, Ja Hyung; Kim, Min Cheol; Park, Kang Ryoung

2017-01-01

Extracting powerful image features plays an important role in computer vision systems. Many methods have previously been proposed to extract image features for various computer vision applications, such as the scale-invariant feature transform (SIFT), speed-up robust feature (SURF), local binary patterns (LBP), histogram of oriented gradients (HOG), and weighted HOG. Recently, the convolutional neural network (CNN) method for image feature extraction and classification in computer vision has been used in various applications. In this research, we propose a new gender recognition method for recognizing males and females in observation scenes of surveillance systems based on feature extraction from visible-light and thermal camera videos through CNN. Experimental results confirm the superiority of our proposed method over state-of-the-art recognition methods for the gender recognition problem using human body images. PMID:28335510

Sensorless FOC Performance Improved with On-Line Speed and Rotor Resistance Estimator Based on an Artificial Neural Network for an Induction Motor Drive

PubMed Central

Gutierrez-Villalobos, Jose M.; Rodriguez-Resendiz, Juvenal; Rivas-Araiza, Edgar A.; Martínez-Hernández, Moisés A.

2015-01-01

Three-phase induction motor drive requires high accuracy in high performance processes in industrial applications. Field oriented control, which is one of the most employed control schemes for induction motors, bases its function on the electrical parameter estimation coming from the motor. These parameters make an electrical machine driver work improperly, since these electrical parameter values change at low speeds, temperature changes, and especially with load and duty changes. The focus of this paper is the real-time and on-line electrical parameters with a CMAC-ADALINE block added in the standard FOC scheme to improve the IM driver performance and endure the driver and the induction motor lifetime. Two kinds of neural network structures are used; one to estimate rotor speed and the other one to estimate rotor resistance of an induction motor. PMID:26131677

Sensorless FOC Performance Improved with On-Line Speed and Rotor Resistance Estimator Based on an Artificial Neural Network for an Induction Motor Drive.

PubMed

Gutierrez-Villalobos, Jose M; Rodriguez-Resendiz, Juvenal; Rivas-Araiza, Edgar A; Martínez-Hernández, Moisés A

2015-06-29

Three-phase induction motor drive requires high accuracy in high performance processes in industrial applications. Field oriented control, which is one of the most employed control schemes for induction motors, bases its function on the electrical parameter estimation coming from the motor. These parameters make an electrical machine driver work improperly, since these electrical parameter values change at low speeds, temperature changes, and especially with load and duty changes. The focus of this paper is the real-time and on-line electrical parameters with a CMAC-ADALINE block added in the standard FOC scheme to improve the IM driver performance and endure the driver and the induction motor lifetime. Two kinds of neural network structures are used; one to estimate rotor speed and the other one to estimate rotor resistance of an induction motor.

Gender Recognition from Human-Body Images Using Visible-Light and Thermal Camera Videos Based on a Convolutional Neural Network for Image Feature Extraction.

PubMed

Nguyen, Dat Tien; Kim, Ki Wan; Hong, Hyung Gil; Koo, Ja Hyung; Kim, Min Cheol; Park, Kang Ryoung

2017-03-20

Extracting powerful image features plays an important role in computer vision systems. Many methods have previously been proposed to extract image features for various computer vision applications, such as the scale-invariant feature transform (SIFT), speed-up robust feature (SURF), local binary patterns (LBP), histogram of oriented gradients (HOG), and weighted HOG. Recently, the convolutional neural network (CNN) method for image feature extraction and classification in computer vision has been used in various applications. In this research, we propose a new gender recognition method for recognizing males and females in observation scenes of surveillance systems based on feature extraction from visible-light and thermal camera videos through CNN. Experimental results confirm the superiority of our proposed method over state-of-the-art recognition methods for the gender recognition problem using human body images.

Integrating conflict detection and attentional control mechanisms.

PubMed

Walsh, Bong J; Buonocore, Michael H; Carter, Cameron S; Mangun, George R

2011-09-01

Human behavior involves monitoring and adjusting performance to meet established goals. Performance-monitoring systems that act by detecting conflict in stimulus and response processing have been hypothesized to influence cortical control systems to adjust and improve performance. Here we used fMRI to investigate the neural mechanisms of conflict monitoring and resolution during voluntary spatial attention. We tested the hypothesis that the ACC would be sensitive to conflict during attentional orienting and influence activity in the frontoparietal attentional control network that selectively modulates visual information processing. We found that activity in ACC increased monotonically with increasing attentional conflict. This increased conflict detection activity was correlated with both increased activity in the attentional control network and improved speed and accuracy from one trial to the next. These results establish a long hypothesized interaction between conflict detection systems and neural systems supporting voluntary control of visual attention.

Neural network disturbance observer-based distributed finite-time formation tracking control for multiple unmanned helicopters.

PubMed

Wang, Dandan; Zong, Qun; Tian, Bailing; Shao, Shikai; Zhang, Xiuyun; Zhao, Xinyi

2018-02-01

The distributed finite-time formation tracking control problem for multiple unmanned helicopters is investigated in this paper. The control object is to maintain the positions of follower helicopters in formation with external interferences. The helicopter model is divided into a second order outer-loop subsystem and a second order inner-loop subsystem based on multiple-time scale features. Using radial basis function neural network (RBFNN) technique, we first propose a novel finite-time multivariable neural network disturbance observer (FMNNDO) to estimate the external disturbance and model uncertainty, where the neural network (NN) approximation errors can be dynamically compensated by adaptive law. Next, based on FMNNDO, a distributed finite-time formation tracking controller and a finite-time attitude tracking controller are designed using the nonsingular fast terminal sliding mode (NFTSM) method. In order to estimate the second derivative of the virtual desired attitude signal, a novel finite-time sliding mode integral filter is designed. Finally, Lyapunov analysis and multiple-time scale principle ensure the realization of control goal in finite-time. The effectiveness of the proposed FMNNDO and controllers are then verified by numerical simulations. Copyright © 2017 ISA. Published by Elsevier Ltd. All rights reserved.

Neural network application to aircraft control system design

NASA Technical Reports Server (NTRS)

Troudet, Terry; Garg, Sanjay; Merrill, Walter C.

1991-01-01

The feasibility of using artificial neural networks as control systems for modern, complex aerospace vehicles is investigated via an example aircraft control design study. The problem considered is that of designing a controller for an integrated airframe/propulsion longitudinal dynamics model of a modern fighter aircraft to provide independent control of pitch rate and airspeed responses to pilot command inputs. An explicit model following controller using H infinity control design techniques is first designed to gain insight into the control problem as well as to provide a baseline for evaluation of the neurocontroller. Using the model of the desired dynamics as a command generator, a multilayer feedforward neural network is trained to control the vehicle model within the physical limitations of the actuator dynamics. This is achieved by minimizing an objective function which is a weighted sum of tracking errors and control input commands and rates. To gain insight in the neurocontrol, linearized representations of the nonlinear neurocontroller are analyzed along a commanded trajectory. Linear robustness analysis tools are then applied to the linearized neurocontroller models and to the baseline H infinity based controller. Future areas of research are identified to enhance the practical applicability of neural networks to flight control design.

Neural network application to aircraft control system design

NASA Technical Reports Server (NTRS)

Troudet, Terry; Garg, Sanjay; Merrill, Walter C.

1991-01-01

The feasibility of using artificial neural network as control systems for modern, complex aerospace vehicles is investigated via an example aircraft control design study. The problem considered is that of designing a controller for an integrated airframe/propulsion longitudinal dynamics model of a modern fighter aircraft to provide independent control of pitch rate and airspeed responses to pilot command inputs. An explicit model following controller using H infinity control design techniques is first designed to gain insight into the control problem as well as to provide a baseline for evaluation of the neurocontroller. Using the model of the desired dynamics as a command generator, a multilayer feedforward neural network is trained to control the vehicle model within the physical limitations of the actuator dynamics. This is achieved by minimizing an objective function which is a weighted sum of tracking errors and control input commands and rates. To gain insight in the neurocontrol, linearized representations of the nonlinear neurocontroller are analyzed along a commanded trajectory. Linear robustness analysis tools are then applied to the linearized neurocontroller models and to the baseline H infinity based controller. Future areas of research identified to enhance the practical applicability of neural networks to flight control design.

Deep Learning for Real-Time Capable Object Detection and Localization on Mobile Platforms

NASA Astrophysics Data System (ADS)

Particke, F.; Kolbenschlag, R.; Hiller, M.; Patiño-Studencki, L.; Thielecke, J.

2017-10-01

Industry 4.0 is one of the most formative terms in current times. Subject of research are particularly smart and autonomous mobile platforms, which enormously lighten the workload and optimize production processes. In order to interact with humans, the platforms need an in-depth knowledge of the environment. Hence, it is required to detect a variety of static and non-static objects. Goal of this paper is to propose an accurate and real-time capable object detection and localization approach for the use on mobile platforms. A method is introduced to use the powerful detection capabilities of a neural network for the localization of objects. Therefore, detection information of a neural network is combined with depth information from a RGB-D camera, which is mounted on a mobile platform. As detection network, YOLO Version 2 (YOLOv2) is used on a mobile robot. In order to find the detected object in the depth image, the bounding boxes, predicted by YOLOv2, are mapped to the corresponding regions in the depth image. This provides a powerful and extremely fast approach for establishing a real-time-capable Object Locator. In the evaluation part, the localization approach turns out to be very accurate. Nevertheless, it is dependent on the detected object itself and some additional parameters, which are analysed in this paper.

Improved Classification of Lung Cancer Using Radial Basis Function Neural Network with Affine Transforms of Voss Representation.

PubMed

Adetiba, Emmanuel; Olugbara, Oludayo O

2015-01-01

Lung cancer is one of the diseases responsible for a large number of cancer related death cases worldwide. The recommended standard for screening and early detection of lung cancer is the low dose computed tomography. However, many patients diagnosed die within one year, which makes it essential to find alternative approaches for screening and early detection of lung cancer. We present computational methods that can be implemented in a functional multi-genomic system for classification, screening and early detection of lung cancer victims. Samples of top ten biomarker genes previously reported to have the highest frequency of lung cancer mutations and sequences of normal biomarker genes were respectively collected from the COSMIC and NCBI databases to validate the computational methods. Experiments were performed based on the combinations of Z-curve and tetrahedron affine transforms, Histogram of Oriented Gradient (HOG), Multilayer perceptron and Gaussian Radial Basis Function (RBF) neural networks to obtain an appropriate combination of computational methods to achieve improved classification of lung cancer biomarker genes. Results show that a combination of affine transforms of Voss representation, HOG genomic features and Gaussian RBF neural network perceptibly improves classification accuracy, specificity and sensitivity of lung cancer biomarker genes as well as achieving low mean square error.

A medical cost estimation with fuzzy neural network of acute hepatitis patients in emergency room.

PubMed

Kuo, R J; Cheng, W C; Lien, W C; Yang, T J

2015-10-01

Taiwan is an area where chronic hepatitis is endemic. Liver cancer is so common that it has been ranked first among cancer mortality rates since the early 1980s in Taiwan. Besides, liver cirrhosis and chronic liver diseases are the sixth or seventh in the causes of death. Therefore, as shown by the active research on hepatitis, it is not only a health threat, but also a huge medical cost for the government. The estimated total number of hepatitis B carriers in the general population aged more than 20 years old is 3,067,307. Thus, a case record review was conducted from all patients with diagnosis of acute hepatitis admitted to the Emergency Department (ED) of a well-known teaching-oriented hospital in Taipei. The cost of medical resource utilization is defined as the total medical fee. In this study, a fuzzy neural network is employed to develop the cost forecasting model. A total of 110 patients met the inclusion criteria. The computational results indicate that the FNN model can provide more accurate forecasts than the support vector regression (SVR) or artificial neural network (ANN). In addition, unlike SVR and ANN, FNN can also provide fuzzy IF-THEN rules for interpretation. Copyright © 2015 Elsevier Ireland Ltd. All rights reserved.

Aerodynamic Design Using Neural Networks

NASA Technical Reports Server (NTRS)

Rai, Man Mohan; Madavan, Nateri K.

2003-01-01

The design of aerodynamic components of aircraft, such as wings or engines, involves a process of obtaining the most optimal component shape that can deliver the desired level of component performance, subject to various constraints, e.g., total weight or cost, that the component must satisfy. Aerodynamic design can thus be formulated as an optimization problem that involves the minimization of an objective function subject to constraints. A new aerodynamic design optimization procedure based on neural networks and response surface methodology (RSM) incorporates the advantages of both traditional RSM and neural networks. The procedure uses a strategy, denoted parameter-based partitioning of the design space, to construct a sequence of response surfaces based on both neural networks and polynomial fits to traverse the design space in search of the optimal solution. Some desirable characteristics of the new design optimization procedure include the ability to handle a variety of design objectives, easily impose constraints, and incorporate design guidelines and rules of thumb. It provides an infrastructure for variable fidelity analysis and reduces the cost of computation by using less-expensive, lower fidelity simulations in the early stages of the design evolution. The initial or starting design can be far from optimal. The procedure is easy and economical to use in large-dimensional design space and can be used to perform design tradeoff studies rapidly. Designs involving multiple disciplines can also be optimized. Some practical applications of the design procedure that have demonstrated some of its capabilities include the inverse design of an optimal turbine airfoil starting from a generic shape and the redesign of transonic turbines to improve their unsteady aerodynamic characteristics.

End-to-end deep neural network for optical inversion in quantitative photoacoustic imaging.

PubMed

Cai, Chuangjian; Deng, Kexin; Ma, Cheng; Luo, Jianwen

2018-06-15

An end-to-end deep neural network, ResU-net, is developed for quantitative photoacoustic imaging. A residual learning framework is used to facilitate optimization and to gain better accuracy from considerably increased network depth. The contracting and expanding paths enable ResU-net to extract comprehensive context information from multispectral initial pressure images and, subsequently, to infer a quantitative image of chromophore concentration or oxygen saturation (sO 2 ). According to our numerical experiments, the estimations of sO 2 and indocyanine green concentration are accurate and robust against variations in both optical property and object geometry. An extremely short reconstruction time of 22 ms is achieved.

Use of artificial neural networks on optical track width measurements.

PubMed

Smith, Richard J; See, Chung W; Somekh, Mike G; Yacoot, Andrew

2007-08-01

We have demonstrated recently that, by using an ultrastable optical interferometer together with artificial neural networks (ANNs), track widths down to 60 nm can be measured with a 0.3 NA objective lens. We investigate the effective conditions for training ANNs. Experimental results will be used to show the characteristics of the training samples and the data format of the ANN inputs required to produce suitably trained ANNs. Results obtained with networks measuring double tracks, and classifying different structures, will be presented to illustrate the capability of the technique. We include a discussion on expansion of the application areas of the system, allowing it to be used as a general purpose instrument.

Use of artificial neural networks on optical track width measurements

NASA Astrophysics Data System (ADS)

Smith, Richard J.; See, Chung W.; Somekh, Mike G.; Yacoot, Andrew

2007-08-01

We have demonstrated recently that, by using an ultrastable optical interferometer together with artificial neural networks (ANNs), track widths down to 60 nm can be measured with a 0.3 NA objective lens. We investigate the effective conditions for training ANNs. Experimental results will be used to show the characteristics of the training samples and the data format of the ANN inputs required to produce suitably trained ANNs. Results obtained with networks measuring double tracks, and classifying different structures, will be presented to illustrate the capability of the technique. We include a discussion on expansion of the application areas of the system, allowing it to be used as a general purpose instrument.

A Balanced Comparison of Object Invariances in Monkey IT Neurons

PubMed Central

2017-01-01

Abstract Our ability to recognize objects across variations in size, position, or rotation is based on invariant object representations in higher visual cortex. However, we know little about how these invariances are related. Are some invariances harder than others? Do some invariances arise faster than others? These comparisons can be made only upon equating image changes across transformations. Here, we targeted invariant neural representations in the monkey inferotemporal (IT) cortex using object images with balanced changes in size, position, and rotation. Across the recorded population, IT neurons generalized across size and position both stronger and faster than to rotations in the image plane as well as in depth. We obtained a similar ordering of invariances in deep neural networks but not in low-level visual representations. Thus, invariant neural representations dynamically evolve in a temporal order reflective of their underlying computational complexity. PMID:28413827

Progressively expanded neural network for automatic material identification in hyperspectral imagery

NASA Astrophysics Data System (ADS)

Paheding, Sidike

The science of hyperspectral remote sensing focuses on the exploitation of the spectral signatures of various materials to enhance capabilities including object detection, recognition, and material characterization. Hyperspectral imagery (HSI) has been extensively used for object detection and identification applications since it provides plenty of spectral information to uniquely identify materials by their reflectance spectra. HSI-based object detection algorithms can be generally classified into stochastic and deterministic approaches. Deterministic approaches are comparatively simple to apply since it is usually based on direct spectral similarity such as spectral angles or spectral correlation. In contrast, stochastic algorithms require statistical modeling and estimation for target class and non-target class. Over the decades, many single class object detection methods have been proposed in the literature, however, deterministic multiclass object detection in HSI has not been explored. In this work, we propose a deterministic multiclass object detection scheme, named class-associative spectral fringe-adjusted joint transform correlation. Human brain is capable of simultaneously processing high volumes of multi-modal data received every second of the day. In contrast, a machine sees input data simply as random binary numbers. Although machines are computationally efficient, they are inferior when comes to data abstraction and interpretation. Thus, mimicking the learning strength of human brain has been current trend in artificial intelligence. In this work, we present a biological inspired neural network, named progressively expanded neural network (PEN Net), based on nonlinear transformation of input neurons to a feature space for better pattern differentiation. In PEN Net, discrete fixed excitations are disassembled and scattered in the feature space as a nonlinear line. Each disassembled element on the line corresponds to a pattern with similar features. Unlike the conventional neural network where hidden neurons need to be iteratively adjusted to achieve better accuracy, our proposed PEN Net does not require hidden neurons tuning which achieves better computational efficiency, and it has also shown superior performance in HSI classification tasks compared to the state-of-the-arts. Spectral-spatial features based HSI classification framework has shown stronger strength compared to spectral-only based methods. In our lastly proposed technique, PEN Net is incorporated with multiscale spatial features (i.e., multiscale complete local binary pattern) to perform a spectral-spatial classification of HSI. Several experiments demonstrate excellent performance of our proposed technique compared to the more recent developed approaches.

Single neural code for blur in subjects with different interocular optical blur orientation

PubMed Central

Radhakrishnan, Aiswaryah; Sawides, Lucie; Dorronsoro, Carlos; Peli, Eli; Marcos, Susana

2015-01-01

The ability of the visual system to compensate for differences in blur orientation between eyes is not well understood. We measured the orientation of the internal blur code in both eyes of the same subject monocularly by presenting pairs of images blurred with real ocular point spread functions (PSFs) of similar blur magnitude but varying in orientations. Subjects assigned a level of confidence to their selection of the best perceived image in each pair. Using a classification-images–inspired paradigm and applying a reverse correlation technique, a classification map was obtained from the weighted averages of the PSFs, representing the internal blur code. Positive and negative neural PSFs were obtained from the classification map, representing the neural blur for best and worse perceived blur, respectively. The neural PSF was found to be highly correlated in both eyes, even for eyes with different ocular PSF orientations (rPos = 0.95; rNeg = 0.99; p < 0.001). We found that in subjects with similar and with different ocular PSF orientations between eyes, the orientation of the positive neural PSF was closer to the orientation of the ocular PSF of the eye with the better optical quality (average difference was ∼10°), while the orientation of the positive and negative neural PSFs tended to be orthogonal. These results suggest a single internal code for blur with orientation driven by the orientation of the optical blur of the eye with better optical quality. PMID:26114678

A case of complex regional pain syndrome with agnosia for object orientation.

PubMed

Robinson, Gail; Cohen, Helen; Goebel, Andreas

2011-07-01

This systematic investigation of the neurocognitive correlates of complex regional pain syndrome (CRPS) in a single case also reports agnosia for object orientation in the context of persistent CRPS. We report a patient (JW) with severe long-standing CRPS who had no difficulty identifying and naming line drawings of objects presented in 1 of 4 cardinal orientations. In contrast, he was extremely poor at reorienting these objects into the correct upright orientation and in judging whether an object was upright or not. Moreover, JW made orientation errors when copying drawings of objects, and he also showed features of mirror reversal in writing single words and reading single letters. The findings are discussed in relation to accounts of visual processing. Agnosia for object orientation is the term for impaired knowledge of an object's orientation despite good recognition and naming of the same misoriented object. This defect has previously only been reported in patients with major structural brain lesions. The neuroanatomical correlates are discussed. The patient had no structural brain lesion, raising the possibility that nonstructural reorganisation of cortical networks may be responsible for his deficits. Other patients with CRPS may have related neurocognitive defects. Crown Copyright © 2011. Published by Elsevier B.V. All rights reserved.

An Investigation of the Application of Artificial Neural Networks to Adaptive Optics Imaging Systems

DTIC Science & Technology

1991-12-01

neural network and the feedforward neural network studied is the single layer perceptron artificial neural network . The recurrent artificial neural network input...features are the wavefront sensor slope outputs and neighboring actuator feedback commands. The feedforward artificial neural network input

Novel maximum-margin training algorithms for supervised neural networks.

PubMed

Ludwig, Oswaldo; Nunes, Urbano

2010-06-01

This paper proposes three novel training methods, two of them based on the backpropagation approach and a third one based on information theory for multilayer perceptron (MLP) binary classifiers. Both backpropagation methods are based on the maximal-margin (MM) principle. The first one, based on the gradient descent with adaptive learning rate algorithm (GDX) and named maximum-margin GDX (MMGDX), directly increases the margin of the MLP output-layer hyperplane. The proposed method jointly optimizes both MLP layers in a single process, backpropagating the gradient of an MM-based objective function, through the output and hidden layers, in order to create a hidden-layer space that enables a higher margin for the output-layer hyperplane, avoiding the testing of many arbitrary kernels, as occurs in case of support vector machine (SVM) training. The proposed MM-based objective function aims to stretch out the margin to its limit. An objective function based on Lp-norm is also proposed in order to take into account the idea of support vectors, however, overcoming the complexity involved in solving a constrained optimization problem, usually in SVM training. In fact, all the training methods proposed in this paper have time and space complexities O(N) while usual SVM training methods have time complexity O(N (3)) and space complexity O(N (2)) , where N is the training-data-set size. The second approach, named minimization of interclass interference (MICI), has an objective function inspired on the Fisher discriminant analysis. Such algorithm aims to create an MLP hidden output where the patterns have a desirable statistical distribution. In both training methods, the maximum area under ROC curve (AUC) is applied as stop criterion. The third approach offers a robust training framework able to take the best of each proposed training method. The main idea is to compose a neural model by using neurons extracted from three other neural networks, each one previously trained by MICI, MMGDX, and Levenberg-Marquard (LM), respectively. The resulting neural network was named assembled neural network (ASNN). Benchmark data sets of real-world problems have been used in experiments that enable a comparison with other state-of-the-art classifiers. The results provide evidence of the effectiveness of our methods regarding accuracy, AUC, and balanced error rate.

Functional neural substrates of posterior cortical atrophy patients.

PubMed

Shames, H; Raz, N; Levin, Netta

2015-07-01

Posterior cortical atrophy (PCA) is a neurodegenerative syndrome in which the most pronounced pathologic involvement is in the occipito-parietal visual regions. Herein, we aimed to better define the cortical reflection of this unique syndrome using a thorough battery of behavioral and functional MRI (fMRI) tests. Eight PCA patients underwent extensive testing to map their visual deficits. Assessments included visual functions associated with lower and higher components of the cortical hierarchy, as well as dorsal- and ventral-related cortical functions. fMRI was performed on five patients to examine the neuronal substrate of their visual functions. The PCA patient cohort exhibited stereopsis, saccadic eye movements and higher dorsal stream-related functional impairments, including simultant perception, image orientation, figure-from-ground segregation, closure and spatial orientation. In accordance with the behavioral findings, fMRI revealed intact activation in the ventral visual regions of face and object perception while more dorsal aspects of perception, including motion and gestalt perception, revealed impaired patterns of activity. In most of the patients, there was a lack of activity in the word form area, which is known to be linked to reading disorders. Finally, there was evidence of reduced cortical representation of the peripheral visual field, corresponding to the behaviorally assessed peripheral visual deficit. The findings are discussed in the context of networks extending from parietal regions, which mediate navigationally related processing, visually guided actions, eye movement control and working memory, suggesting that damage to these networks might explain the wide range of deficits in PCA patients.

Decoding of finger trajectory from ECoG using deep learning

NASA Astrophysics Data System (ADS)

Xie, Ziqian; Schwartz, Odelia; Prasad, Abhishek

2018-06-01

Objective. Conventional decoding pipeline for brain-machine interfaces (BMIs) consists of chained different stages of feature extraction, time-frequency analysis and statistical learning models. Each of these stages uses a different algorithm trained in a sequential manner, which makes it difficult to make the whole system adaptive. The goal was to create an adaptive online system with a single objective function and a single learning algorithm so that the whole system can be trained in parallel to increase the decoding performance. Here, we used deep neural networks consisting of convolutional neural networks (CNN) and a special kind of recurrent neural network (RNN) called long short term memory (LSTM) to address these needs. Approach. We used electrocorticography (ECoG) data collected by Kubanek et al. The task consisted of individual finger flexions upon a visual cue. Our model combined a hierarchical feature extractor CNN and a RNN that was able to process sequential data and recognize temporal dynamics in the neural data. CNN was used as the feature extractor and LSTM was used as the regression algorithm to capture the temporal dynamics of the signal. Main results. We predicted the finger trajectory using ECoG signals and compared results for the least angle regression (LARS), CNN-LSTM, random forest, LSTM model (LSTM_HC, for using hard-coded features) and a decoding pipeline consisting of band-pass filtering, energy extraction, feature selection and linear regression. The results showed that the deep learning models performed better than the commonly used linear model. The deep learning models not only gave smoother and more realistic trajectories but also learned the transition between movement and rest state. Significance. This study demonstrated a decoding network for BMI that involved a convolutional and recurrent neural network model. It integrated the feature extraction pipeline into the convolution and pooling layer and used LSTM layer to capture the state transitions. The discussed network eliminated the need to separately train the model at each step in the decoding pipeline. The whole system can be jointly optimized using stochastic gradient descent and is capable of online learning.

Generalized Hough Transform for Object Classification in the Maritime Domain

DTIC Science & Technology

2015-12-01

and memory storage problems of the GHT in this work . Neural networks have been used to provide excellent solutions to real-world problems in many...1 A. THESIS OBJECTIVE ...............................................................................1 B. RELATED WORK ...SIGNIFICANT CONTRIBUTIONS ......................................................47  B.  RECOMMENDATIONS FOR FUTURE WORK ................................48

SortNet: learning to rank by a neural preference function.

PubMed

Rigutini, Leonardo; Papini, Tiziano; Maggini, Marco; Scarselli, Franco

2011-09-01

Relevance ranking consists in sorting a set of objects with respect to a given criterion. However, in personalized retrieval systems, the relevance criteria may usually vary among different users and may not be predefined. In this case, ranking algorithms that adapt their behavior from users' feedbacks must be devised. Two main approaches are proposed in the literature for learning to rank: the use of a scoring function, learned by examples, that evaluates a feature-based representation of each object yielding an absolute relevance score, a pairwise approach, where a preference function is learned to determine the object that has to be ranked first in a given pair. In this paper, we present a preference learning method for learning to rank. A neural network, the comparative neural network (CmpNN), is trained from examples to approximate the comparison function for a pair of objects. The CmpNN adopts a particular architecture designed to implement the symmetries naturally present in a preference function. The learned preference function can be embedded as the comparator into a classical sorting algorithm to provide a global ranking of a set of objects. To improve the ranking performances, an active-learning procedure is devised, that aims at selecting the most informative patterns in the training set. The proposed algorithm is evaluated on the LETOR dataset showing promising performances in comparison with other state-of-the-art algorithms.

Advanced Aeroservoelastic Testing and Data Analysis (Les Essais Aeroservoelastiques et l’Analyse des Donnees).

DTIC Science & Technology

1995-11-01

network - based AFS concepts. Neural networks can addition of vanes in each engine exhaust for thrust provide...parameter estimation programs 19-11 8.6 Neural Network Based Methods unknown parameters of the postulated state space model Artificial neural network ...Forward Neural Network the network that the applicability of the recurrent neural and ii) Recurrent Neural Network [117-119]. network to

The effect of music-induced mood on attentional networks.

PubMed

Jiang, Jun; Scolaro, Ashley J; Bailey, Kira; Chen, Antao

2011-06-01

Attention network theory suggests that there are three separate neural networks that execute the discrete functions of alerting, orienting, and executive attention. Previous research on the influence of mood on attention has shown subtle and inconsistent results. The attention network theory may aid in clarifying the influence of mood on attention. The present study investigated the influence of mood on attentional networks in a normal population. Participants performed the Attention Network Test (ANT), which provides functional measures of alerting, orienting, and executive attention. Positive or negative mood was induced by listening to music with a positive or negative valence, respectively; neutral mood was induced by reading a collection of basic facts about China. The results revealed that negative mood led to a significantly higher alerting efficiency relative to other moods, while there were no significant mood effects on orienting or executive attention efficiency. According to the algorithm underlying the ANT, the higher alerting efficiency in the negative mood condition can be attributed to relatively greater benefits of cueing effects. The findings are discussed in the context of the noradrenergic system and of evolutionary significance. Specifically, the increase in the alerting function during negative mood states may be due to the modulation effect of negative mood on the noradrenergic system, and/or to the survival benefit resulting from an increase in automatic vigilance towards negative information. The current results suggest that as the influence of negative mood on attention appears to specifically consist in an enhanced alerting function, it may not be found in studies where the three attentional networks are not dissociated.

The hierarchical brain network for face recognition.

PubMed

Zhen, Zonglei; Fang, Huizhen; Liu, Jia

2013-01-01

Numerous functional magnetic resonance imaging (fMRI) studies have identified multiple cortical regions that are involved in face processing in the human brain. However, few studies have characterized the face-processing network as a functioning whole. In this study, we used fMRI to identify face-selective regions in the entire brain and then explore the hierarchical structure of the face-processing network by analyzing functional connectivity among these regions. We identified twenty-five regions mainly in the occipital, temporal and frontal cortex that showed a reliable response selective to faces (versus objects) across participants and across scan sessions. Furthermore, these regions were clustered into three relatively independent sub-networks in a face-recognition task on the basis of the strength of functional connectivity among them. The functionality of the sub-networks likely corresponds to the recognition of individual identity, retrieval of semantic knowledge and representation of emotional information. Interestingly, when the task was switched to object recognition from face recognition, the functional connectivity between the inferior occipital gyrus and the rest of the face-selective regions were significantly reduced, suggesting that this region may serve as an entry node in the face-processing network. In sum, our study provides empirical evidence for cognitive and neural models of face recognition and helps elucidate the neural mechanisms underlying face recognition at the network level.

Multiple components of surround modulation in primary visual cortex: multiple neural circuits with multiple functions?

PubMed Central

Nurminen, Lauri; Angelucci, Alessandra

2014-01-01

The responses of neurons in primary visual cortex (V1) to stimulation of their receptive field (RF) are modulated by stimuli in the RF surround. This modulation is suppressive when the stimuli in the RF and surround are of similar orientation, but less suppressive or facilitatory when they are cross-oriented. Similarly, in human vision surround stimuli selectively suppress the perceived contrast of a central stimulus. Although the properties of surround modulation have been thoroughly characterized in many species, cortical areas and sensory modalities, its role in perception remains unknown. Here we argue that surround modulation in V1 consists of multiple components having different spatio-temporal and tuning properties, generated by different neural circuits and serving different visual functions. One component arises from LGN afferents, is fast, untuned for orientation, and spatially restricted to the surround region nearest to the RF (the near-surround); its function is to normalize V1 cell responses to local contrast. Intra-V1 horizontal connections contribute a slower, narrowly orientation-tuned component to near-surround modulation, whose function is to increase the coding efficiency of natural images in manner that leads to the extraction of object boundaries. The third component is generated by topdown feedback connections to V1, is fast, broadly orientation-tuned, and extends into the far-surround; its function is to enhance the salience of behaviorally relevant visual features. Far- and near-surround modulation, thus, act as parallel mechanisms: the former quickly detects and guides saccades/attention to salient visual scene locations, the latter segments object boundaries in the scene. PMID:25204770

Early multisensory interactions affect the competition among multiple visual objects.

PubMed

Van der Burg, Erik; Talsma, Durk; Olivers, Christian N L; Hickey, Clayton; Theeuwes, Jan

2011-04-01

In dynamic cluttered environments, audition and vision may benefit from each other in determining what deserves further attention and what does not. We investigated the underlying neural mechanisms responsible for attentional guidance by audiovisual stimuli in such an environment. Event-related potentials (ERPs) were measured during visual search through dynamic displays consisting of line elements that randomly changed orientation. Search accuracy improved when a target orientation change was synchronized with an auditory signal as compared to when the auditory signal was absent or synchronized with a distractor orientation change. The ERP data show that behavioral benefits were related to an early multisensory interaction over left parieto-occipital cortex (50-60 ms post-stimulus onset), which was followed by an early positive modulation (80-100 ms) over occipital and temporal areas contralateral to the audiovisual event, an enhanced N2pc (210-250 ms), and a contralateral negative slow wave (CNSW). The early multisensory interaction was correlated with behavioral search benefits, indicating that participants with a strong multisensory interaction benefited the most from the synchronized auditory signal. We suggest that an auditory signal enhances the neural response to a synchronized visual event, which increases the chances of selection in a multiple object environment. Copyright © 2010 Elsevier Inc. All rights reserved.

An Artificial Immune System-Inspired Multiobjective Evolutionary Algorithm with Application to the Detection of Distributed Computer Network Intrusions

DTIC Science & Technology

2007-03-01

Intelligence AIS Artificial Immune System ANN Artificial Neural Networks API Application Programming Interface BFS Breadth-First Search BIS Biological...problem domain is too large for only one algorithm’s application . It ranges from network - based sniffer systems, responsible for Enterprise-wide coverage...options to network administrators in choosing detectors to employ in future ID applications . Objectives Our hypothesis validity is based on a set

Dissociation of neural mechanisms underlying orientation processing in humans

PubMed Central

Ling, Sam; Pearson, Joel; Blake, Randolph

2009-01-01

Summary Orientation selectivity is a fundamental, emergent property of neurons in early visual cortex, and discovery of that property [1, 2] dramatically shaped how we conceptualize visual processing [3–6]. However, much remains unknown about the neural substrates of these basic building blocks of perception, and what is known primarily stems from animal physiology studies. To probe the neural concomitants of orientation processing in humans, we employed repetitive transcranial magnetic stimulation (rTMS) to attenuate neural responses evoked by stimuli presented within a local region of the visual field. Previous physiological studies have shown that rTMS can significantly suppress the neuronal spiking activity, hemodynamic responses, and local field potentials within a focused cortical region [7, 8]. By suppressing neural activity with rTMS, we were able to dissociate components of the neural circuitry underlying two distinct aspects of orientation processing: selectivity and contextual effects. Orientation selectivity gauged by masking was unchanged by rTMS, whereas an otherwise robust orientation repulsion illusion was weakened following rTMS. This dissociation implies that orientation processing relies on distinct mechanisms, only one of which was impacted by rTMS. These results are consistent with models positing that orientation selectivity is largely governed by the patterns of convergence of thalamic afferents onto cortical neurons, with intracortical activity then shaping population responses contained within those orientation-selective cortical neurons. PMID:19682905

Neural networks for aircraft control

NASA Technical Reports Server (NTRS)

Linse, Dennis

1990-01-01

Current research in Artificial Neural Networks indicates that networks offer some potential advantages in adaptation and fault tolerance. This research is directed at determining the possible applicability of neural networks to aircraft control. The first application will be to aircraft trim. Neural network node characteristics, network topology and operation, neural network learning and example histories using neighboring optimal control with a neural net are discussed.

Gravity influences the visual representation of object tilt in parietal cortex.

PubMed

Rosenberg, Ari; Angelaki, Dora E

2014-10-22

Sensory systems encode the environment in egocentric (e.g., eye, head, or body) reference frames, creating inherently unstable representations that shift and rotate as we move. However, it is widely speculated that the brain transforms these signals into an allocentric, gravity-centered representation of the world that is stable and independent of the observer's spatial pose. Where and how this representation may be achieved is currently unknown. Here we demonstrate that a subpopulation of neurons in the macaque caudal intraparietal area (CIP) visually encodes object tilt in nonegocentric coordinates defined relative to the gravitational vector. Neuronal responses to the tilt of a visually presented planar surface were measured with the monkey in different spatial orientations (upright and rolled left/right ear down) and then compared. This revealed a continuum of representations in which planar tilt was encoded in a gravity-centered reference frame in approximately one-tenth of the comparisons, intermediate reference frames ranging between gravity-centered and egocentric in approximately two-tenths of the comparisons, and in an egocentric reference frame in less than half of the comparisons. Altogether, almost half of the comparisons revealed a shift in the preferred tilt and/or a gain change consistent with encoding object orientation in nonegocentric coordinates. Through neural network modeling, we further show that a purely gravity-centered representation of object tilt can be achieved directly from the population activity of CIP-like units. These results suggest that area CIP may play a key role in creating a stable, allocentric representation of the environment defined relative to an "earth-vertical" direction. Copyright © 2014 the authors 0270-6474/14/3414170-11$15.00/0.

Attribute and topology based change detection in a constellation of previously detected objects

DOEpatents

Paglieroni, David W.; Beer, Reginald N.

2016-01-19

A system that applies attribute and topology based change detection to networks of objects that were detected on previous scans of a structure, roadway, or area of interest. The attributes capture properties or characteristics of the previously detected objects, such as location, time of detection, size, elongation, orientation, etc. The topology of the network of previously detected objects is maintained in a constellation database that stores attributes of previously detected objects and implicitly captures the geometrical structure of the network. A change detection system detects change by comparing the attributes and topology of new objects detected on the latest scan to the constellation database of previously detected objects.

Fuzzy Adaptive Control for Intelligent Autonomous Space Exploration Problems

NASA Technical Reports Server (NTRS)

Esogbue, Augustine O.

1998-01-01

The principal objective of the research reported here is the re-design, analysis and optimization of our newly developed neural network fuzzy adaptive controller model for complex processes capable of learning fuzzy control rules using process data and improving its control through on-line adaption. The learned improvement is according to a performance objective function that provides evaluative feedback; this performance objective is broadly defined to meet long-range goals over time. Although fuzzy control had proven effective for complex, nonlinear, imprecisely-defined processes for which standard models and controls are either inefficient, impractical or cannot be derived, the state of the art prior to our work showed that procedures for deriving fuzzy control, however, were mostly ad hoc heuristics. The learning ability of neural networks was exploited to systematically derive fuzzy control and permit on-line adaption and in the process optimize control. The operation of neural networks integrates very naturally with fuzzy logic. The neural networks which were designed and tested using simulation software and simulated data, followed by realistic industrial data were reconfigured for application on several platforms as well as for the employment of improved algorithms. The statistical procedures of the learning process were investigated and evaluated with standard statistical procedures (such as ANOVA, graphical analysis of residuals, etc.). The computational advantage of dynamic programming-like methods of optimal control was used to permit on-line fuzzy adaptive control. Tests for the consistency, completeness and interaction of the control rules were applied. Comparisons to other methods and controllers were made so as to identify the major advantages of the resulting controller model. Several specific modifications and extensions were made to the original controller. Additional modifications and explorations have been proposed for further study. Some of these are in progress in our laboratory while others await additional support. All of these enhancements will improve the attractiveness of the controller as an effective tool for the on line control of an array of complex process environments.

Pattern recognition invariant under changes of scale and orientation

NASA Astrophysics Data System (ADS)

Arsenault, Henri H.; Parent, Sebastien; Moisan, Sylvain

1997-08-01

We have used a modified method proposed by neiberg and Casasent to successfully classify five kinds of military vehicles. The method uses a wedge filter to achieve scale invariance, and lines in a multi-dimensional feature space correspond to each target with out-of-plane orientations over 360 degrees around a vertical axis. The images were not binarized, but were filtered in a preprocessing step to reduce aliasing. The feature vectors were normalized and orthogonalized by means of a neural network. Out-of-plane rotations of 360 degrees and scale changes of a factor of four were considered. Error-free classification was achieved.

Solving inversion problems with neural networks

NASA Technical Reports Server (NTRS)

Kamgar-Parsi, Behzad; Gualtieri, J. A.

1990-01-01

A class of inverse problems in remote sensing can be characterized by Q = F(x), where F is a nonlinear and noninvertible (or hard to invert) operator, and the objective is to infer the unknowns, x, from the observed quantities, Q. Since the number of observations is usually greater than the number of unknowns, these problems are formulated as optimization problems, which can be solved by a variety of techniques. The feasibility of neural networks for solving such problems is presently investigated. As an example, the problem of finding the atmospheric ozone profile from measured ultraviolet radiances is studied.

Diagnostic analysis of liver B ultrasonic texture features based on LM neural network

NASA Astrophysics Data System (ADS)

Chi, Qingyun; Hua, Hu; Liu, Menglin; Jiang, Xiuying

2017-03-01

In this study, B ultrasound images of 124 benign and malignant patients were randomly selected as the study objects. The B ultrasound images of the liver were treated by enhanced de-noising. By constructing the gray level co-occurrence matrix which reflects the information of each angle, Principal Component Analysis of 22 texture features were extracted and combined with LM neural network for diagnosis and classification. Experimental results show that this method is a rapid and effective diagnostic method for liver imaging, which provides a quantitative basis for clinical diagnosis of liver diseases.

A bio-inspired system for spatio-temporal recognition in static and video imagery

NASA Astrophysics Data System (ADS)

Khosla, Deepak; Moore, Christopher K.; Chelian, Suhas

2007-04-01

This paper presents a bio-inspired method for spatio-temporal recognition in static and video imagery. It builds upon and extends our previous work on a bio-inspired Visual Attention and object Recognition System (VARS). The VARS approach locates and recognizes objects in a single frame. This work presents two extensions of VARS. The first extension is a Scene Recognition Engine (SCE) that learns to recognize spatial relationships between objects that compose a particular scene category in static imagery. This could be used for recognizing the category of a scene, e.g., office vs. kitchen scene. The second extension is the Event Recognition Engine (ERE) that recognizes spatio-temporal sequences or events in sequences. This extension uses a working memory model to recognize events and behaviors in video imagery by maintaining and recognizing ordered spatio-temporal sequences. The working memory model is based on an ARTSTORE1 neural network that combines an ART-based neural network with a cascade of sustained temporal order recurrent (STORE)1 neural networks. A series of Default ARTMAP classifiers ascribes event labels to these sequences. Our preliminary studies have shown that this extension is robust to variations in an object's motion profile. We evaluated the performance of the SCE and ERE on real datasets. The SCE module was tested on a visual scene classification task using the LabelMe2 dataset. The ERE was tested on real world video footage of vehicles and pedestrians in a street scene. Our system is able to recognize the events in this footage involving vehicles and pedestrians.

Classification of boreal forest by satellite and inventory data using neural network approach

NASA Astrophysics Data System (ADS)

Romanov, A. A.

2012-12-01

The main objective of this research was to develop methodology for boreal (Siberian Taiga) land cover classification in a high accuracy level. The study area covers the territories of Central Siberian several parts along the Yenisei River (60-62 degrees North Latitude): the right bank includes mixed forest and dark taiga, the left - pine forests; so were taken as a high heterogeneity and statistically equal surfaces concerning spectral characteristics. Two main types of data were used: time series of middle spatial resolution satellite images (Landsat 5, 7 and SPOT4) and inventory datasets from the nature fieldworks (used for training samples sets preparation). Method of collecting field datasets included a short botany description (type/species of vegetation, density, compactness of the crowns, individual height and max/min diameters representative of each type, surface altitude of the plot), at the same time the geometric characteristic of each training sample unit corresponded to the spatial resolution of satellite images and geo-referenced (prepared datasets both of the preliminary processing and verification). The network of test plots was planned as irregular and determined by the landscape oriented approach. The main focus of the thematic data processing has been allocated for the use of neural networks (fuzzy logic inc.); therefore, the results of field studies have been converting input parameter of type / species of vegetation cover of each unit and the degree of variability. Proposed approach involves the processing of time series separately for each image mainly for the verification: shooting parameters taken into consideration (time, albedo) and thus expected to assess the quality of mapping. So the input variables for the networks were sensor bands, surface altitude, solar angels and land surface temperature (for a few experiments); also given attention to the formation of the formula class on the basis of statistical pre-processing of results of field research (prevalence type). Besides some statistical methods of supervised classification has been used (minimal distance, maximum likelihood, Mahalanobis). During the study received various types of neural classifiers suitable for the mapping, and even for the high heterogenic areas neural network approach has shown better results in precision despite the validity of the assumption of Gaussian distribution (Table). Experimentally chosen optimum network structure consisting of three layers of ten neuron in each, but it should be clarified that such configuration requires larges computational resources in comparison the statistical methods presented above; necessary to increase the number of iteration in network learning process for RMS errors minimization. It should also be emphasized that the key issues of accuracy estimation of the classification results is lack of completeness of the training sets, this is especially true with summer image processing of mixed forest. However seems that proposed methodology can be used also for measure local dynamic of boreal land surface by the type of vegetation.Comparison of classification accuracyt;

Time Series Neural Network Model for Part-of-Speech Tagging Indonesian Language

NASA Astrophysics Data System (ADS)

Tanadi, Theo

2018-03-01

Part-of-speech tagging (POS tagging) is an important part in natural language processing. Many methods have been used to do this task, including neural network. This paper models a neural network that attempts to do POS tagging. A time series neural network is modelled to solve the problems that a basic neural network faces when attempting to do POS tagging. In order to enable the neural network to have text data input, the text data will get clustered first using Brown Clustering, resulting a binary dictionary that the neural network can use. To further the accuracy of the neural network, other features such as the POS tag, suffix, and affix of previous words would also be fed to the neural network.

Comparing visual representations across human fMRI and computational vision

PubMed Central

Leeds, Daniel D.; Seibert, Darren A.; Pyles, John A.; Tarr, Michael J.

2013-01-01

Feedforward visual object perception recruits a cortical network that is assumed to be hierarchical, progressing from basic visual features to complete object representations. However, the nature of the intermediate features related to this transformation remains poorly understood. Here, we explore how well different computer vision recognition models account for neural object encoding across the human cortical visual pathway as measured using fMRI. These neural data, collected during the viewing of 60 images of real-world objects, were analyzed with a searchlight procedure as in Kriegeskorte, Goebel, and Bandettini (2006): Within each searchlight sphere, the obtained patterns of neural activity for all 60 objects were compared to model responses for each computer recognition algorithm using representational dissimilarity analysis (Kriegeskorte et al., 2008). Although each of the computer vision methods significantly accounted for some of the neural data, among the different models, the scale invariant feature transform (Lowe, 2004), encoding local visual properties gathered from “interest points,” was best able to accurately and consistently account for stimulus representations within the ventral pathway. More generally, when present, significance was observed in regions of the ventral-temporal cortex associated with intermediate-level object perception. Differences in model effectiveness and the neural location of significant matches may be attributable to the fact that each model implements a different featural basis for representing objects (e.g., more holistic or more parts-based). Overall, we conclude that well-known computer vision recognition systems may serve as viable proxies for theories of intermediate visual object representation. PMID:24273227

A design philosophy for multi-layer neural networks with applications to robot control

NASA Technical Reports Server (NTRS)

Vadiee, Nader; Jamshidi, MO

1989-01-01

A system is proposed which receives input information from many sensors that may have diverse scaling, dimension, and data representations. The proposed system tolerates sensory information with faults. The proposed self-adaptive processing technique has great promise in integrating the techniques of artificial intelligence and neural networks in an attempt to build a more intelligent computing environment. The proposed architecture can provide a detailed decision tree based on the input information, information stored in a long-term memory, and the adapted rule-based knowledge. A mathematical model for analysis will be obtained to validate the cited hypotheses. An extensive software program will be developed to simulate a typical example of pattern recognition problem. It is shown that the proposed model displays attention, expectation, spatio-temporal, and predictory behavior which are specific to the human brain. The anticipated results of this research project are: (1) creation of a new dynamic neural network structure, and (2) applications to and comparison with conventional multi-layer neural network structures. The anticipated benefits from this research are vast. The model can be used in a neuro-computer architecture as a building block which can perform complicated, nonlinear, time-varying mapping from a multitude of input excitory classes to an output or decision environment. It can be used for coordinating different sensory inputs and past experience of a dynamic system and actuating signals. The commercial applications of this project can be the creation of a special-purpose neuro-computer hardware which can be used in spatio-temporal pattern recognitions in such areas as air defense systems, e.g., target tracking, and recognition. Potential robotics-related applications are trajectory planning, inverse dynamics computations, hierarchical control, task-oriented control, and collision avoidance.

Identification of Correlated GRACE Monthly Harmonic Coefficients Using Pattern Recognition and Neural Networks

NASA Astrophysics Data System (ADS)

Piretzidis, D.; Sra, G.; Sideris, M. G.

2016-12-01

This study explores new methods for identifying correlation errors in harmonic coefficients derived from monthly solutions of the Gravity Recovery and Climate Experiment (GRACE) satellite mission using pattern recognition and neural network algorithms. These correlation errors are evidenced in the differences between monthly solutions and can be suppressed using a de-correlation filter. In all studies so far, the implementation of the de-correlation filter starts from a specific minimum order (i.e., 11 for RL04 and 38 for RL05) until the maximum order of the monthly solution examined. This implementation method has two disadvantages, namely, the omission of filtering correlated coefficients of order less than the minimum order and the filtering of uncorrelated coefficients of order higher than the minimum order. In the first case, the filtered solution is not completely free of correlated errors, whereas the second case results in a monthly solution that suffers from loss of geophysical signal. In the present study, a new method of implementing the de-correlation filter is suggested, by identifying and filtering only the coefficients that show indications of high correlation. Several numerical and geometric properties of the harmonic coefficient series of all orders are examined. Extreme cases of both correlated and uncorrelated coefficients are selected, and their corresponding properties are used to train a two-layer feed-forward neural network. The objective of the neural network is to identify and quantify the correlation by providing the probability of an order of coefficients to be correlated. Results show good performance of the neural network, both in the validation stage of the training procedure and in the subsequent use of the trained network to classify independent coefficients. The neural network is also capable of identifying correlated coefficients even when a small number of training samples and neurons are used (e.g.,100 and 10, respectively).

Computational Account of Spontaneous Activity as a Signature of Predictive Coding

PubMed Central

Koren, Veronika

2017-01-01

Spontaneous activity is commonly observed in a variety of cortical states. Experimental evidence suggested that neural assemblies undergo slow oscillations with Up ad Down states even when the network is isolated from the rest of the brain. Here we show that these spontaneous events can be generated by the recurrent connections within the network and understood as signatures of neural circuits that are correcting their internal representation. A noiseless spiking neural network can represent its input signals most accurately when excitatory and inhibitory currents are as strong and as tightly balanced as possible. However, in the presence of realistic neural noise and synaptic delays, this may result in prohibitively large spike counts. An optimal working regime can be found by considering terms that control firing rates in the objective function from which the network is derived and then minimizing simultaneously the coding error and the cost of neural activity. In biological terms, this is equivalent to tuning neural thresholds and after-spike hyperpolarization. In suboptimal working regimes, we observe spontaneous activity even in the absence of feed-forward inputs. In an all-to-all randomly connected network, the entire population is involved in Up states. In spatially organized networks with local connectivity, Up states spread through local connections between neurons of similar selectivity and take the form of a traveling wave. Up states are observed for a wide range of parameters and have similar statistical properties in both active and quiescent state. In the optimal working regime, Up states are vanishing, leaving place to asynchronous activity, suggesting that this working regime is a signature of maximally efficient coding. Although they result in a massive increase in the firing activity, the read-out of spontaneous Up states is in fact orthogonal to the stimulus representation, therefore interfering minimally with the network function. PMID:28114353

Integration of object-oriented knowledge representation with the CLIPS rule based system

NASA Technical Reports Server (NTRS)

Logie, David S.; Kamil, Hasan

1990-01-01

The paper describes a portion of the work aimed at developing an integrated, knowledge based environment for the development of engineering-oriented applications. An Object Representation Language (ORL) was implemented in C++ which is used to build and modify an object-oriented knowledge base. The ORL was designed in such a way so as to be easily integrated with other representation schemes that could effectively reason with the object base. Specifically, the integration of the ORL with the rule based system C Language Production Systems (CLIPS), developed at the NASA Johnson Space Center, will be discussed. The object-oriented knowledge representation provides a natural means of representing problem data as a collection of related objects. Objects are comprised of descriptive properties and interrelationships. The object-oriented model promotes efficient handling of the problem data by allowing knowledge to be encapsulated in objects. Data is inherited through an object network via the relationship links. Together, the two schemes complement each other in that the object-oriented approach efficiently handles problem data while the rule based knowledge is used to simulate the reasoning process. Alone, the object based knowledge is little more than an object-oriented data storage scheme; however, the CLIPS inference engine adds the mechanism to directly and automatically reason with that knowledge. In this hybrid scheme, the expert system dynamically queries for data and can modify the object base with complete access to all the functionality of the ORL from rules.

An investigation of the neural substrates of mind wandering induced by viewing traditional Chinese landscape paintings.

PubMed

Wang, Tingting; Mo, Lei; Vartanian, Oshin; Cant, Jonathan S; Cupchik, Gerald

2014-01-01

The present study was conducted to investigate whether the calming effect induced by viewing traditional Chinese landscape paintings would make disengagement from that mental state more difficult, as measured by performance on a cognitive control task. In Experiment 1 we examined the subjective experience of viewing traditional Chinese landscape paintings vs. realistic oil landscape paintings in a behavioral study. Our results confirmed that, as predicted, traditional Chinese landscape paintings induce greater levels of relaxation and mind wandering and lower levels of object-oriented absorption and recognition, compared to realistic oil landscape paintings. In Experiment 2 we used functional Magnetic Resonance Imaging to explore the behavioral and neural effects of viewing traditional Chinese landscape paintings on a task requiring cognitive control (i.e., the flanker task)-administered immediately following exposure to paintings. Contrary to our prediction, the behavioral data demonstrated that compared to realistic oil landscape paintings, exposure to traditional Chinese landscape paintings had no effect on performance on the flanker task. However, the neural data demonstrated an interaction effect such that there was greater activation in the inferior parietal cortex and the superior frontal gyrus on incongruent compared with congruent flanker trials when participants switched from viewing traditional Chinese landscape paintings to the flanker task than when they switched from realistic oil landscape paintings. These results suggest that switching from traditional Chinese landscape paintings placed greater demands on the brain's attention and working memory networks during the flanker task than did switching from realistic oil landscape paintings.

Java and its future in biomedical computing.

PubMed Central

Rodgers, R P

1996-01-01

Java, a new object-oriented computing language related to C++, is receiving considerable attention due to its use in creating network-sharable, platform-independent software modules (known as "applets") that can be used with the World Wide Web. The Web has rapidly become the most commonly used information-retrieval tool associated with the global computer network known as the Internet, and Java has the potential to further accelerate the Web's application to medical problems. Java's potentially wide acceptance due to its Web association and its own technical merits also suggests that it may become a popular language for non-Web-based, object-oriented computing. PMID:8880677

Integration trumps selection in object recognition.

PubMed

Saarela, Toni P; Landy, Michael S

2015-03-30

Finding and recognizing objects is a fundamental task of vision. Objects can be defined by several "cues" (color, luminance, texture, etc.), and humans can integrate sensory cues to improve detection and recognition [1-3]. Cortical mechanisms fuse information from multiple cues [4], and shape-selective neural mechanisms can display cue invariance by responding to a given shape independent of the visual cue defining it [5-8]. Selective attention, in contrast, improves recognition by isolating a subset of the visual information [9]. Humans can select single features (red or vertical) within a perceptual dimension (color or orientation), giving faster and more accurate responses to items having the attended feature [10, 11]. Attention elevates neural responses and sharpens neural tuning to the attended feature, as shown by studies in psychophysics and modeling [11, 12], imaging [13-16], and single-cell and neural population recordings [17, 18]. Besides single features, attention can select whole objects [19-21]. Objects are among the suggested "units" of attention because attention to a single feature of an object causes the selection of all of its features [19-21]. Here, we pit integration against attentional selection in object recognition. We find, first, that humans can integrate information near optimally from several perceptual dimensions (color, texture, luminance) to improve recognition. They cannot, however, isolate a single dimension even when the other dimensions provide task-irrelevant, potentially conflicting information. For object recognition, it appears that there is mandatory integration of information from multiple dimensions of visual experience. The advantage afforded by this integration, however, comes at the expense of attentional selection. Copyright © 2015 Elsevier Ltd. All rights reserved.

Integration trumps selection in object recognition

PubMed Central

Saarela, Toni P.; Landy, Michael S.

2015-01-01

Summary Finding and recognizing objects is a fundamental task of vision. Objects can be defined by several “cues” (color, luminance, texture etc.), and humans can integrate sensory cues to improve detection and recognition [1–3]. Cortical mechanisms fuse information from multiple cues [4], and shape-selective neural mechanisms can display cue-invariance by responding to a given shape independent of the visual cue defining it [5–8]. Selective attention, in contrast, improves recognition by isolating a subset of the visual information [9]. Humans can select single features (red or vertical) within a perceptual dimension (color or orientation), giving faster and more accurate responses to items having the attended feature [10,11]. Attention elevates neural responses and sharpens neural tuning to the attended feature, as shown by studies in psychophysics and modeling [11,12], imaging [13–16], and single-cell and neural population recordings [17,18]. Besides single features, attention can select whole objects [19–21]. Objects are among the suggested “units” of attention because attention to a single feature of an object causes the selection of all of its features [19–21]. Here, we pit integration against attentional selection in object recognition. We find, first, that humans can integrate information near-optimally from several perceptual dimensions (color, texture, luminance) to improve recognition. They cannot, however, isolate a single dimension even when the other dimensions provide task-irrelevant, potentially conflicting information. For object recognition, it appears that there is mandatory integration of information from multiple dimensions of visual experience. The advantage afforded by this integration, however, comes at the expense of attentional selection. PMID:25802154

SSBRP User Operations Facility (UOF) Overview and Development Strategy

NASA Technical Reports Server (NTRS)

Picinich, Lou; Stone, Thom; Sun, Charles; Windrem, May; Givens, John J. (Technical Monitor)

1995-01-01

This paper will present the Space Station Biological Research Project (SSBRP) User Operations Facility (UOF) architecture and development strategy. A major element of the UOF at NASA Ames Research Center, the Communication and Data System (CDS) will be the primary focus of the discussions. CDS operational, telescience, security, and development objectives will be discussed along with CDS implementation strategy. The implementation strategy discussions will include: Object Oriented Analysis & Design, System & Software Prototyping, and Technology Utilization. A CDS design overview that includes: CDS Context Diagram, CDS Architecture, Object Models, Use Cases, and User Interfaces will also be presented. CDS development brings together "cutting edge" technologies and techniques such as: object oriented development, network security, multimedia networking, web-based data distribution, JAVA, and graphical user interfaces. Use of these "cutting edge" technologies and techniques translates directly to lower development and operations costs.

Object segmentation and recovery via neural oscillators implementing the similarity and prior knowledge gestalt rules.

PubMed

Ursino, Mauro; Magosso, Elisa; La Cara, Giuseppe-Emiliano; Cuppini, Cristiano

2006-09-01

Object recognition requires the solution of the binding and segmentation problems, i.e., grouping different features to achieve a coherent representation. Synchronization of neural activity in the gamma-band, associated with gestalt perception, has often been proposed as a putative mechanism to solve these problems, not only as to low-level processing, but also in higher cortical functions. In the present work, a network of Wilson-Cowan oscillators is used to segment simultaneous objects, and recover an object from partial or corrupted information, by implementing two gestalt rules: similarity and prior knowledge. The network consists of H different areas, each devoted to representation of a particular feature of the object, according to a topological organization. The similarity law is realized via lateral intra-area connections, arranged as a "Mexican-hat". Prior knowledge is realized via inter-area connections, which link properties belonging to a previously memorized object. A global inhibitor allows segmentation of several objects avoiding interference. Simulation results, performed using three simultaneous input objects, show that the network is able to detect an object even in difficult conditions (i.e., when some features are absent or shifted with respect to the original one). Moreover, the trade-off between sensitivity (capacity to detect true positives) and specificity (capacity to reject false positives) can be controlled acting on the extension of lateral synapses (i.e., on the level of accepted similarity). Finally, the network can also deal with correlated objects, i.e., objects which have some common features. Simulations performed using a different number of objects (2, 3, 4 or 5) suggest that the network is able to segment and recall up to four objects, but the oscillation frequency must increase, the lower the number of objects simultaneously present. The model, although quite simpler compared with neurophysiology, may represent a theoretical framework for the analysis of the relationships between object representation, memory, learning, and gamma-band activity. In particular, it extends previous studies on autoassociative memory since it exploits not only oscillatory dynamics, but also a topological organization of features.

Neural Mechanisms of Episodic Retrieval Support Divergent Creative Thinking.

PubMed

Madore, Kevin P; Thakral, Preston P; Beaty, Roger E; Addis, Donna Rose; Schacter, Daniel L

2017-11-17

Prior research has indicated that brain regions and networks that support semantic memory, top-down and bottom-up attention, and cognitive control are all involved in divergent creative thinking. Kernels of evidence suggest that neural processes supporting episodic memory-the retrieval of particular elements of prior experiences-may also be involved in divergent thinking, but such processes have typically been characterized as not very relevant for, or even a hindrance to, creative output. In the present study, we combine functional magnetic resonance imaging with an experimental manipulation to test formally, for the first time, episodic memory's involvement in divergent thinking. Following a manipulation that facilitates detailed episodic retrieval, we observed greater neural activity in the hippocampus and stronger connectivity between a core brain network linked to episodic processing and a frontoparietal brain network linked to cognitive control during divergent thinking relative to an object association control task that requires little divergent thinking. Stronger coupling following the retrieval manipulation extended to a subsequent resting-state scan. Neural effects of the episodic manipulation were consistent with behavioral effects of enhanced idea production on divergent thinking but not object association. The results indicate that conceptual frameworks should accommodate the idea that episodic retrieval can function as a component process of creative idea generation, and highlight how the brain flexibly utilizes the retrieval of episodic details for tasks beyond simple remembering. © The Author 2017. Published by Oxford University Press. All rights reserved. For Permissions, please e-mail: journals.permissions@oup.com.

Cascaded Segmentation-Detection Networks for Word-Level Text Spotting.

PubMed

Qin, Siyang; Manduchi, Roberto

2017-11-01

We introduce an algorithm for word-level text spotting that is able to accurately and reliably determine the bounding regions of individual words of text "in the wild". Our system is formed by the cascade of two convolutional neural networks. The first network is fully convolutional and is in charge of detecting areas containing text. This results in a very reliable but possibly inaccurate segmentation of the input image. The second network (inspired by the popular YOLO architecture) analyzes each segment produced in the first stage, and predicts oriented rectangular regions containing individual words. No post-processing (e.g. text line grouping) is necessary. With execution time of 450 ms for a 1000 × 560 image on a Titan X GPU, our system achieves good performance on the ICDAR 2013, 2015 benchmarks [2], [1].

Lateral Information Processing by Spiking Neurons: A Theoretical Model of the Neural Correlate of Consciousness

PubMed Central

Ebner, Marc; Hameroff, Stuart

2011-01-01

Cognitive brain functions, for example, sensory perception, motor control and learning, are understood as computation by axonal-dendritic chemical synapses in networks of integrate-and-fire neurons. Cognitive brain functions may occur either consciously or nonconsciously (on “autopilot”). Conscious cognition is marked by gamma synchrony EEG, mediated largely by dendritic-dendritic gap junctions, sideways connections in input/integration layers. Gap-junction-connected neurons define a sub-network within a larger neural network. A theoretical model (the “conscious pilot”) suggests that as gap junctions open and close, a gamma-synchronized subnetwork, or zone moves through the brain as an executive agent, converting nonconscious “auto-pilot” cognition to consciousness, and enhancing computation by coherent processing and collective integration. In this study we implemented sideways “gap junctions” in a single-layer artificial neural network to perform figure/ground separation. The set of neurons connected through gap junctions form a reconfigurable resistive grid or sub-network zone. In the model, outgoing spikes are temporally integrated and spatially averaged using the fixed resistive grid set up by neurons of similar function which are connected through gap-junctions. This spatial average, essentially a feedback signal from the neuron's output, determines whether particular gap junctions between neurons will open or close. Neurons connected through open gap junctions synchronize their output spikes. We have tested our gap-junction-defined sub-network in a one-layer neural network on artificial retinal inputs using real-world images. Our system is able to perform figure/ground separation where the laterally connected sub-network of neurons represents a perceived object. Even though we only show results for visual stimuli, our approach should generalize to other modalities. The system demonstrates a moving sub-network zone of synchrony, within which the contents of perception are represented and contained. This mobile zone can be viewed as a model of the neural correlate of consciousness in the brain. PMID:22046178

Lateral information processing by spiking neurons: a theoretical model of the neural correlate of consciousness.

PubMed

Ebner, Marc; Hameroff, Stuart

2011-01-01

Cognitive brain functions, for example, sensory perception, motor control and learning, are understood as computation by axonal-dendritic chemical synapses in networks of integrate-and-fire neurons. Cognitive brain functions may occur either consciously or nonconsciously (on "autopilot"). Conscious cognition is marked by gamma synchrony EEG, mediated largely by dendritic-dendritic gap junctions, sideways connections in input/integration layers. Gap-junction-connected neurons define a sub-network within a larger neural network. A theoretical model (the "conscious pilot") suggests that as gap junctions open and close, a gamma-synchronized subnetwork, or zone moves through the brain as an executive agent, converting nonconscious "auto-pilot" cognition to consciousness, and enhancing computation by coherent processing and collective integration. In this study we implemented sideways "gap junctions" in a single-layer artificial neural network to perform figure/ground separation. The set of neurons connected through gap junctions form a reconfigurable resistive grid or sub-network zone. In the model, outgoing spikes are temporally integrated and spatially averaged using the fixed resistive grid set up by neurons of similar function which are connected through gap-junctions. This spatial average, essentially a feedback signal from the neuron's output, determines whether particular gap junctions between neurons will open or close. Neurons connected through open gap junctions synchronize their output spikes. We have tested our gap-junction-defined sub-network in a one-layer neural network on artificial retinal inputs using real-world images. Our system is able to perform figure/ground separation where the laterally connected sub-network of neurons represents a perceived object. Even though we only show results for visual stimuli, our approach should generalize to other modalities. The system demonstrates a moving sub-network zone of synchrony, within which the contents of perception are represented and contained. This mobile zone can be viewed as a model of the neural correlate of consciousness in the brain.

Optical track width measurements below 100 nm using artificial neural networks

NASA Astrophysics Data System (ADS)

Smith, R. J.; See, C. W.; Somekh, M. G.; Yacoot, A.; Choi, E.

2005-12-01

This paper discusses the feasibility of using artificial neural networks (ANNs), together with a high precision scanning optical profiler, to measure very fine track widths that are considerably below the conventional diffraction limit of a conventional optical microscope. The ANN is trained using optical profiles obtained from tracks of known widths, the network is then assessed by applying it to test profiles. The optical profiler is an ultra-stable common path scanning interferometer, which provides extremely precise surface measurements. Preliminary results, obtained with a 0.3 NA objective lens and a laser wavelength of 633 nm, show that the system is capable of measuring a 50 nm track width, with a standard deviation less than 4 nm.

Neural dynamics for landmark orientation and angular path integration

PubMed Central

Seelig, Johannes D.; Jayaraman, Vivek

2015-01-01

Summary Many animals navigate using a combination of visual landmarks and path integration. In mammalian brains, head direction cells integrate these two streams of information by representing an animal's heading relative to landmarks, yet maintaining their directional tuning in darkness based on self-motion cues. Here we use two-photon calcium imaging in head-fixed flies walking on a ball in a virtual reality arena to demonstrate that landmark-based orientation and angular path integration are combined in the population responses of neurons whose dendrites tile the ellipsoid body — a toroidal structure in the center of the fly brain. The population encodes the fly's azimuth relative to its environment, tracking visual landmarks when available and relying on self-motion cues in darkness. When both visual and self-motion cues are absent, a representation of the animal's orientation is maintained in this network through persistent activity — a potential substrate for short-term memory. Several features of the population dynamics of these neurons and their circular anatomical arrangement are suggestive of ring attractors — network structures proposed to support the function of navigational brain circuits. PMID:25971509

Selection of neural network structure for system error correction of electro-optical tracker system with horizontal gimbal

NASA Astrophysics Data System (ADS)

Liu, Xing-fa; Cen, Ming

2007-12-01

Neural Network system error correction method is more precise than lest square system error correction method and spheric harmonics function system error correction method. The accuracy of neural network system error correction method is mainly related to the frame of Neural Network. Analysis and simulation prove that both BP neural network system error correction method and RBF neural network system error correction method have high correction accuracy; it is better to use RBF Network system error correction method than BP Network system error correction method for little studying stylebook considering training rate and neural network scale.

Deep convolutional neural network training enrichment using multi-view object-based analysis of Unmanned Aerial systems imagery for wetlands classification

NASA Astrophysics Data System (ADS)

Liu, Tao; Abd-Elrahman, Amr

2018-05-01

Deep convolutional neural network (DCNN) requires massive training datasets to trigger its image classification power, while collecting training samples for remote sensing application is usually an expensive process. When DCNN is simply implemented with traditional object-based image analysis (OBIA) for classification of Unmanned Aerial systems (UAS) orthoimage, its power may be undermined if the number training samples is relatively small. This research aims to develop a novel OBIA classification approach that can take advantage of DCNN by enriching the training dataset automatically using multi-view data. Specifically, this study introduces a Multi-View Object-based classification using Deep convolutional neural network (MODe) method to process UAS images for land cover classification. MODe conducts the classification on multi-view UAS images instead of directly on the orthoimage, and gets the final results via a voting procedure. 10-fold cross validation results show the mean overall classification accuracy increasing substantially from 65.32%, when DCNN was applied on the orthoimage to 82.08% achieved when MODe was implemented. This study also compared the performances of the support vector machine (SVM) and random forest (RF) classifiers with DCNN under traditional OBIA and the proposed multi-view OBIA frameworks. The results indicate that the advantage of DCNN over traditional classifiers in terms of accuracy is more obvious when these classifiers were applied with the proposed multi-view OBIA framework than when these classifiers were applied within the traditional OBIA framework.

A Definitive Work on Factors Impacting the Arming of Unmanned Vehicles

DTIC Science & Technology

2005-05-01

making software, which can then adjust the system to compensate for unusual activity. Behavioral models that better predict how applications, networks ... network structure of nodes and arcs. The arcs describe relations between nodes, and nodes represent objects, concepts, or events. It uses the arc...tackling things that occur outside the known problem domain. There are some newer, natural-based approaches. One deals with neural networks . There is no

A novel recurrent neural network with finite-time convergence for linear programming.

PubMed

Liu, Qingshan; Cao, Jinde; Chen, Guanrong

2010-11-01

In this letter, a novel recurrent neural network based on the gradient method is proposed for solving linear programming problems. Finite-time convergence of the proposed neural network is proved by using the Lyapunov method. Compared with the existing neural networks for linear programming, the proposed neural network is globally convergent to exact optimal solutions in finite time, which is remarkable and rare in the literature of neural networks for optimization. Some numerical examples are given to show the effectiveness and excellent performance of the new recurrent neural network.

Introducing ab initio based neural networks for transition-rate prediction in kinetic Monte Carlo simulations

NASA Astrophysics Data System (ADS)

Messina, Luca; Castin, Nicolas; Domain, Christophe; Olsson, Pär

2017-02-01

The quality of kinetic Monte Carlo (KMC) simulations of microstructure evolution in alloys relies on the parametrization of point-defect migration rates, which are complex functions of the local chemical composition and can be calculated accurately with ab initio methods. However, constructing reliable models that ensure the best possible transfer of physical information from ab initio to KMC is a challenging task. This work presents an innovative approach, where the transition rates are predicted by artificial neural networks trained on a database of 2000 migration barriers, obtained with density functional theory (DFT) in place of interatomic potentials. The method is tested on copper precipitation in thermally aged iron alloys, by means of a hybrid atomistic-object KMC model. For the object part of the model, the stability and mobility properties of copper-vacancy clusters are analyzed by means of independent atomistic KMC simulations, driven by the same neural networks. The cluster diffusion coefficients and mean free paths are found to increase with size, confirming the dominant role of coarsening of medium- and large-sized clusters in the precipitation kinetics. The evolution under thermal aging is in better agreement with experiments with respect to a previous interatomic-potential model, especially concerning the experiment time scales. However, the model underestimates the solubility of copper in iron due to the excessively high solution energy predicted by the chosen DFT method. Nevertheless, this work proves the capability of neural networks to transfer complex ab initio physical properties to higher-scale models, and facilitates the extension to systems with increasing chemical complexity, setting the ground for reliable microstructure evolution simulations in a wide range of alloys and applications.

Objects Classification by Learning-Based Visual Saliency Model and Convolutional Neural Network.

PubMed

Li, Na; Zhao, Xinbo; Yang, Yongjia; Zou, Xiaochun

2016-01-01

Humans can easily classify different kinds of objects whereas it is quite difficult for computers. As a hot and difficult problem, objects classification has been receiving extensive interests with broad prospects. Inspired by neuroscience, deep learning concept is proposed. Convolutional neural network (CNN) as one of the methods of deep learning can be used to solve classification problem. But most of deep learning methods, including CNN, all ignore the human visual information processing mechanism when a person is classifying objects. Therefore, in this paper, inspiring the completed processing that humans classify different kinds of objects, we bring forth a new classification method which combines visual attention model and CNN. Firstly, we use the visual attention model to simulate the processing of human visual selection mechanism. Secondly, we use CNN to simulate the processing of how humans select features and extract the local features of those selected areas. Finally, not only does our classification method depend on those local features, but also it adds the human semantic features to classify objects. Our classification method has apparently advantages in biology. Experimental results demonstrated that our method made the efficiency of classification improve significantly.

Defense Small Business Innovation Research Program (SBIR). Volume 1. Army Abstracts of Phase 1 Awards 1990

DTIC Science & Technology

1990-01-01

RABRO DR E HAUPPAUGE, NY 11788 Program Manager: SULLIVAN S CHEN Contract #: Title: CORRELATION OF SOLDER JOINT MEASUREMENTS TO PROCESS VARIABLES FOR...ADDITION, THE SR& E NEURAL NETWORK WILL BE USED TO PERFORM SHAPE MATCHING BECAUSE IT IS NOT ORIENTATION INVARIANT. SINCE OUR TARGET DETECTOR IS A PIXEL...DEVELOPMENT METHODS AND TOOLS ARE NEEDED WHICH BOTH REDUCE DEVELOPMENT COSTS AND FACILITATE COMMUNICATION BETWEEN DEVELOPERS AND MAINTAINERS THROUGHOUT

Automobile gross emitter screening with remote sensing data using objective-oriented neural network.

PubMed

Chen, Ho-Wen; Yang, Hsi-Hsien; Wang, Yu-Sheng

2009-11-01

One of the costs of Taiwan's massive economic development has been severe air pollution problems in many parts of the island. Since vehicle emissions are the major source of air pollution in most of Taiwan's urban areas, Taiwan's government has implemented policies to rectify the degrading air quality, especially in areas with high population density. To reduce vehicle pollution emissions an on-road remote sensing and monitoring system is used to check the exhaust emissions from gasoline engine automobiles. By identifying individual vehicles with excessive emissions for follow-up inspection and testing, air quality in the urban environment is expected to improve greatly. Because remote sensing is capable of measuring a large number of moving vehicles in a short period, it has been considered as an assessment technique in place of the stationary emission-sampling techniques. However, inherent measurement uncertainty of remote sensing instrumentation, compounded by the indeterminacy of monitoring site selection, plus the vagaries of weather, causes large errors in pollution discrimination and limits the application of the remote sensing. Many governments are still waiting for a novel data analysis methodology to clamp down on heavily emitting vehicles by using remote sensing data. This paper proposes an artificial neural network (ANN), with vehicle attributes embedded, that can be trained by genetic algorithm (GA) based on different strategies to predict vehicle emission violation. Results show that the accuracy of predicting emission violation is as high as 92%. False determinations tend to occur for vehicles aged 7-13 years, peaking at 10 years of age.

Modular, Hierarchical Learning By Artificial Neural Networks

NASA Technical Reports Server (NTRS)

Baldi, Pierre F.; Toomarian, Nikzad

1996-01-01

Modular and hierarchical approach to supervised learning by artificial neural networks leads to neural networks more structured than neural networks in which all neurons fully interconnected. These networks utilize general feedforward flow of information and sparse recurrent connections to achieve dynamical effects. The modular organization, sparsity of modular units and connections, and fact that learning is much more circumscribed are all attractive features for designing neural-network hardware. Learning streamlined by imitating some aspects of biological neural networks.

Clinical Outcome Prediction in Aneurysmal Subarachnoid Hemorrhage Using Bayesian Neural Networks with Fuzzy Logic Inferences

PubMed Central

Lo, Benjamin W. Y.; Macdonald, R. Loch; Baker, Andrew; Levine, Mitchell A. H.

2013-01-01

Objective. The novel clinical prediction approach of Bayesian neural networks with fuzzy logic inferences is created and applied to derive prognostic decision rules in cerebral aneurysmal subarachnoid hemorrhage (aSAH). Methods. The approach of Bayesian neural networks with fuzzy logic inferences was applied to data from five trials of Tirilazad for aneurysmal subarachnoid hemorrhage (3551 patients). Results. Bayesian meta-analyses of observational studies on aSAH prognostic factors gave generalizable posterior distributions of population mean log odd ratios (ORs). Similar trends were noted in Bayesian and linear regression ORs. Significant outcome predictors include normal motor response, cerebral infarction, history of myocardial infarction, cerebral edema, history of diabetes mellitus, fever on day 8, prior subarachnoid hemorrhage, admission angiographic vasospasm, neurological grade, intraventricular hemorrhage, ruptured aneurysm size, history of hypertension, vasospasm day, age and mean arterial pressure. Heteroscedasticity was present in the nontransformed dataset. Artificial neural networks found nonlinear relationships with 11 hidden variables in 1 layer, using the multilayer perceptron model. Fuzzy logic decision rules (centroid defuzzification technique) denoted cut-off points for poor prognosis at greater than 2.5 clusters. Discussion. This aSAH prognostic system makes use of existing knowledge, recognizes unknown areas, incorporates one's clinical reasoning, and compensates for uncertainty in prognostication. PMID:23690884

Neural Correlates of Sound Localization in Complex Acoustic Environments

PubMed Central

Zündorf, Ida C.; Lewald, Jörg; Karnath, Hans-Otto

2013-01-01

Listening to and understanding people in a “cocktail-party situation” is a remarkable feature of the human auditory system. Here we investigated the neural correlates of the ability to localize a particular sound among others in an acoustically cluttered environment with healthy subjects. In a sound localization task, five different natural sounds were presented from five virtual spatial locations during functional magnetic resonance imaging (fMRI). Activity related to auditory stream segregation was revealed in posterior superior temporal gyrus bilaterally, anterior insula, supplementary motor area, and frontoparietal network. Moreover, the results indicated critical roles of left planum temporale in extracting the sound of interest among acoustical distracters and the precuneus in orienting spatial attention to the target sound. We hypothesized that the left-sided lateralization of the planum temporale activation is related to the higher specialization of the left hemisphere for analysis of spectrotemporal sound features. Furthermore, the precuneus − a brain area known to be involved in the computation of spatial coordinates across diverse frames of reference for reaching to objects − seems to be also a crucial area for accurately determining locations of auditory targets in an acoustically complex scene of multiple sound sources. The precuneus thus may not only be involved in visuo-motor processes, but may also subserve related functions in the auditory modality. PMID:23691185

Characterization of pulse amplitude and pulse rate modulation for a human vestibular implant during acute electrical stimulation

NASA Astrophysics Data System (ADS)

Nguyen, T. A. K.; DiGiovanna, J.; Cavuscens, S.; Ranieri, M.; Guinand, N.; van de Berg, R.; Carpaneto, J.; Kingma, H.; Guyot, J.-P.; Micera, S.; Perez Fornos, A.

2016-08-01

Objective. The vestibular system provides essential information about balance and spatial orientation via the brain to other sensory and motor systems. Bilateral vestibular loss significantly reduces quality of life, but vestibular implants (VIs) have demonstrated potential to restore lost function. However, optimal electrical stimulation strategies have not yet been identified in patients. In this study, we compared the two most common strategies, pulse amplitude modulation (PAM) and pulse rate modulation (PRM), in patients. Approach. Four subjects with a modified cochlear implant including electrodes targeting the peripheral vestibular nerve branches were tested. Charge-equivalent PAM and PRM were applied after adaptation to baseline stimulation. Vestibulo-ocular reflex eye movement responses were recorded to evaluate stimulation efficacy during acute clinical testing sessions. Main results. PAM evoked larger amplitude eye movement responses than PRM. Eye movement response axes for lateral canal stimulation were marginally better aligned with PRM than with PAM. A neural network model was developed for the tested stimulation strategies to provide insights on possible neural mechanisms. This model suggested that PAM would consistently cause a larger ensemble firing rate of neurons and thus larger responses than PRM. Significance. Due to the larger magnitude of eye movement responses, our findings strongly suggest PAM as the preferred strategy for initial VI modulation.

Color encoding in biologically-inspired convolutional neural networks.

PubMed

Rafegas, Ivet; Vanrell, Maria

2018-05-11

Convolutional Neural Networks have been proposed as suitable frameworks to model biological vision. Some of these artificial networks showed representational properties that rival primate performances in object recognition. In this paper we explore how color is encoded in a trained artificial network. It is performed by estimating a color selectivity index for each neuron, which allows us to describe the neuron activity to a color input stimuli. The index allows us to classify whether they are color selective or not and if they are of a single or double color. We have determined that all five convolutional layers of the network have a large number of color selective neurons. Color opponency clearly emerges in the first layer, presenting 4 main axes (Black-White, Red-Cyan, Blue-Yellow and Magenta-Green), but this is reduced and rotated as we go deeper into the network. In layer 2 we find a denser hue sampling of color neurons and opponency is reduced almost to one new main axis, the Bluish-Orangish coinciding with the dataset bias. In layers 3, 4 and 5 color neurons are similar amongst themselves, presenting different type of neurons that detect specific colored objects (e.g., orangish faces), specific surrounds (e.g., blue sky) or specific colored or contrasted object-surround configurations (e.g. blue blob in a green surround). Overall, our work concludes that color and shape representation are successively entangled through all the layers of the studied network, revealing certain parallelisms with the reported evidences in primate brains that can provide useful insight into intermediate hierarchical spatio-chromatic representations. Copyright © 2018 Elsevier Ltd. All rights reserved.