Command and Control of Teams of Autonomous Units

DTIC Science & Technology

2012-06-01

done by a hybrid genetic algorithm (GA) particle swarm optimization ( PSO ) algorithm called PIDGION-alternate. This training algorithm is an ANN ...human controller will recognize the behaviors as being safe and correct. As the HyperNEAT approach produces Artificial Neural Nets ( ANN ), we can...optimization technique that generates efficient ANN controls from simple environmental feedback. FALCONET has been tested showing that it can produce

Control of Wind Tunnel Operations Using Neural Net Interpretation of Flow Visualization Records

NASA Technical Reports Server (NTRS)

Buggele, Alvin E.; Decker, Arthur J.

1994-01-01

Neural net control of operations in a small subsonic/transonic/supersonic wind tunnel at Lewis Research Center is discussed. The tunnel and the layout for neural net control or control by other parallel processing techniques are described. The tunnel is an affordable, multiuser platform for testing instrumentation and components, as well as parallel processing and control strategies. Neural nets have already been tested on archival schlieren and holographic visualizations from this tunnel as well as recent supersonic and transonic shadowgraph. This paper discusses the performance of neural nets for interpreting shadowgraph images in connection with a recent exercise for tuning the tunnel in a subsonic/transonic cascade mode of operation. That mode was operated for performing wake surveys in connection with NASA's Advanced Subsonic Technology (AST) noise reduction program. The shadowgraph was presented to the neural nets as 60 by 60 pixel arrays. The outputs were tunnel parameters such as valve settings or tunnel state identifiers for selected tunnel operating points, conditions, or states. The neural nets were very sensitive, perhaps too sensitive, to shadowgraph pattern detail. However, the nets exhibited good immunity to variations in brightness, to noise, and to changes in contrast. The nets are fast enough so that ten or more can be combined per control operation to interpret flow visualization data, point sensor data, and model calculations. The pattern sensitivity of the nets will be utilized and tested to control wind tunnel operations at Mach 2.0 based on shock wave patterns.

Using fuzzy logic to integrate neural networks and knowledge-based systems

NASA Technical Reports Server (NTRS)

Yen, John

1991-01-01

Outlined here is a novel hybrid architecture that uses fuzzy logic to integrate neural networks and knowledge-based systems. The author's approach offers important synergistic benefits to neural nets, approximate reasoning, and symbolic processing. Fuzzy inference rules extend symbolic systems with approximate reasoning capabilities, which are used for integrating and interpreting the outputs of neural networks. The symbolic system captures meta-level information about neural networks and defines its interaction with neural networks through a set of control tasks. Fuzzy action rules provide a robust mechanism for recognizing the situations in which neural networks require certain control actions. The neural nets, on the other hand, offer flexible classification and adaptive learning capabilities, which are crucial for dynamic and noisy environments. By combining neural nets and symbolic systems at their system levels through the use of fuzzy logic, the author's approach alleviates current difficulties in reconciling differences between low-level data processing mechanisms of neural nets and artificial intelligence systems.

Flexible body control using neural networks

NASA Technical Reports Server (NTRS)

Mccullough, Claire L.

1992-01-01

Progress is reported on the control of Control Structures Interaction suitcase demonstrator (a flexible structure) using neural networks and fuzzy logic. It is concluded that while control by neural nets alone (i.e., allowing the net to design a controller with no human intervention) has yielded less than optimal results, the neural net trained to emulate the existing fuzzy logic controller does produce acceptible system responses for the initial conditions examined. Also, a neural net was found to be very successful in performing the emulation step necessary for the anticipatory fuzzy controller for the CSI suitcase demonstrator. The fuzzy neural hybrid, which exhibits good robustness and noise rejection properties, shows promise as a controller for practical flexible systems, and should be further evaluated.

LavaNet—Neural network development environment in a general mine planning package

NASA Astrophysics Data System (ADS)

Kapageridis, Ioannis Konstantinou; Triantafyllou, A. G.

2011-04-01

LavaNet is a series of scripts written in Perl that gives access to a neural network simulation environment inside a general mine planning package. A well known and a very popular neural network development environment, the Stuttgart Neural Network Simulator, is used as the base for the development of neural networks. LavaNet runs inside VULCAN™—a complete mine planning package with advanced database, modelling and visualisation capabilities. LavaNet is taking advantage of VULCAN's Perl based scripting environment, Lava, to bring all the benefits of neural network development and application to geologists, mining engineers and other users of the specific mine planning package. LavaNet enables easy development of neural network training data sets using information from any of the data and model structures available, such as block models and drillhole databases. Neural networks can be trained inside VULCAN™ and the results be used to generate new models that can be visualised in 3D. Direct comparison of developed neural network models with conventional and geostatistical techniques is now possible within the same mine planning software package. LavaNet supports Radial Basis Function networks, Multi-Layer Perceptrons and Self-Organised Maps.

Optoelectronic analogs of self-programming neural nets - Architecture and methodologies for implementing fast stochastic learning by simulated annealing

NASA Technical Reports Server (NTRS)

Farhat, Nabil H.

1987-01-01

Self-organization and learning is a distinctive feature of neural nets and processors that sets them apart from conventional approaches to signal processing. It leads to self-programmability which alleviates the problem of programming complexity in artificial neural nets. In this paper architectures for partitioning an optoelectronic analog of a neural net into distinct layers with prescribed interconnectivity pattern to enable stochastic learning by simulated annealing in the context of a Boltzmann machine are presented. Stochastic learning is of interest because of its relevance to the role of noise in biological neural nets. Practical considerations and methodologies for appreciably accelerating stochastic learning in such a multilayered net are described. These include the use of parallel optical computing of the global energy of the net, the use of fast nonvolatile programmable spatial light modulators to realize fast plasticity, optical generation of random number arrays, and an adaptive noisy thresholding scheme that also makes stochastic learning more biologically plausible. The findings reported predict optoelectronic chips that can be used in the realization of optical learning machines.

The silicon synapse or, neural net computing.

PubMed

Frenger, P

1989-01-01

Recent developments have rekindled interest in the electronic neural network, a form of parallel computer architecture loosely based on the nervous system of living creatures. This paper describes the elements of neural net computers, reviews the historical milestones in their development, and lists the advantages and disadvantages of their use. Methods for software simulation of neural network systems on existing computers, as well as creation of hardware analogues, are given. The most successful applications of these techniques, involving emulation of biological system responses, are presented. The author's experiences with neural net systems are discussed.

A neural net based architecture for the segmentation of mixed gray-level and binary pictures

NASA Technical Reports Server (NTRS)

Tabatabai, Ali; Troudet, Terry P.

1991-01-01

A neural-net-based architecture is proposed to perform segmentation in real time for mixed gray-level and binary pictures. In this approach, the composite picture is divided into 16 x 16 pixel blocks, which are identified as character blocks or image blocks on the basis of a dichotomy measure computed by an adaptive 16 x 16 neural net. For compression purposes, each image block is further divided into 4 x 4 subblocks; a one-bit nonparametric quantizer is used to encode 16 x 16 character and 4 x 4 image blocks; and the binary map and quantizer levels are obtained through a neural net segmentor over each block. The efficiency of the neural segmentation in terms of computational speed, data compression, and quality of the compressed picture is demonstrated. The effect of weight quantization is also discussed. VLSI implementations of such adaptive neural nets in CMOS technology are described and simulated in real time for a maximum block size of 256 pixels.

Neural network and letter recognition

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

Lee, Hue Yeon.

Neural net architectures and learning algorithms that recognize hand written 36 alphanumeric characters are studied. The thin line input patterns written in 32 x 32 binary array are used. The system is comprised of two major components, viz. a preprocessing unit and a Recognition unit. The preprocessing unit in turn consists of three layers of neurons; the U-layer, the V-layer, and the C-layer. The functions of the U-layer is to extract local features by template matching. The correlation between the detected local features are considered. Through correlating neurons in a plane with their neighboring neurons, the V-layer would thicken themore » on-cells or lines that are groups of on-cells of the previous layer. These two correlations would yield some deformation tolerance and some of the rotational tolerance of the system. The C-layer then compresses data through the Gabor transform. Pattern dependent choice of center and wavelengths of Gabor filters is the cause of shift and scale tolerance of the system. Three different learning schemes had been investigated in the recognition unit, namely; the error back propagation learning with hidden units, a simple perceptron learning, and a competitive learning. Their performances were analyzed and compared. Since sometimes the network fails to distinguish between two letters that are inherently similar, additional ambiguity resolving neural nets are introduced on top of the above main neural net. The two dimensional Fourier transform is used as the preprocessing and the perceptron is used as the recognition unit of the ambiguity resolver. One hundred different person's handwriting sets are collected. Some of these are used as the training sets and the remainders are used as the test sets.« less

Neural-Net Processed Characteristic Patterns for Measurement of Structural Integrity of Pressure Cycled Components

NASA Technical Reports Server (NTRS)

Decker, A. J.

2001-01-01

A neural-net inspection process has been combined with a bootstrap training procedure and electronic holography to detect changes or damage in a pressure-cycled International Space Station cold plate to be used for cooling instrumentation. The cold plate was excited to vibrate in a normal mode at low amplitude, and the neural net was trained by example to flag small changes in the mode shape. The NDE (nondestructive-evaluation) technique is straightforward but in its infancy; its applications are ad-hoc and uncalibrated. Nevertheless previous research has shown that the neural net can detect displacement changes to better than 1/100 the maximum displacement amplitude. Development efforts that support the NDE technique are mentioned briefly, followed by descriptions of electronic holography and neural-net processing. The bootstrap training procedure and its application to detection of damage in a pressure-cycled cold plate are discussed. Suggestions for calibrating and quantifying the NDE procedure are presented.

Overcoming rule-based rigidity and connectionist limitations through massively-parallel case-based reasoning

NASA Technical Reports Server (NTRS)

Barnden, John; Srinivas, Kankanahalli

1990-01-01

Symbol manipulation as used in traditional Artificial Intelligence has been criticized by neural net researchers for being excessively inflexible and sequential. On the other hand, the application of neural net techniques to the types of high-level cognitive processing studied in traditional artificial intelligence presents major problems as well. A promising way out of this impasse is to build neural net models that accomplish massively parallel case-based reasoning. Case-based reasoning, which has received much attention recently, is essentially the same as analogy-based reasoning, and avoids many of the problems leveled at traditional artificial intelligence. Further problems are avoided by doing many strands of case-based reasoning in parallel, and by implementing the whole system as a neural net. In addition, such a system provides an approach to some aspects of the problems of noise, uncertainty and novelty in reasoning systems. The current neural net system (Conposit), which performs standard rule-based reasoning, is being modified into a massively parallel case-based reasoning version.

Perception for Outdoor Navigation

DTIC Science & Technology

1990-11-01

without lane marktings. Our perception modules use a variety of techniques for video processing (clusering theory, symbolic feature detection, neural nets...on gravel and dirt roads, as expected. The most difficult case involved a dirt road in a forest, which was mainly distinguishable in the video images...in that estimate. u bIsrshigl Neural Nets. Under separate funding, we have driven the Naviab using neural nets to track the road in video iages. We ame

Optimal and Adaptive Control of Flow in a Thermal Convection Loop

NASA Astrophysics Data System (ADS)

Yuen, Po Ki; Bau, Haim

1998-11-01

In theory and experiment, we use nonlinear and linear optimal and adaptive controllers to suppress the naturally occurring chaotic convection in a thermal convection loop. The thermal convection loop is a simple experimental analog of the Lorenz equations, and it provides a convenient platform for testing and comparing the performance of various control strategies in a fluid mechanical setting. The performance of the optimal and adaptive controllers is compared with that of a previously developed simple feedback controller (Singer, J., Wang, Y., & Bau, H., H., 1991, Physical Review Letters, 66,123-1125.)(Wang, Y., Singer, J., & Bau, H., H., 1992, J. Fluid Mechanics, 237, 479-498.), a nonlinear controller with a cubic nonlinearity(Yuen, P., & Bau, H., H., 1996, J. Fluid Mechanics, 317, 91-109.), and a neural net controller(Yuen, P., & Bau, H., H., 1998, Neural Networks, 11, 557 - 569, 1998.). It is demonstrated that an adaptive controller can perform successfully even when the system's model is not known.

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.

Feature to prototype transition in neural networks

NASA Astrophysics Data System (ADS)

Krotov, Dmitry; Hopfield, John

Models of associative memory with higher order (higher than quadratic) interactions, and their relationship to neural networks used in deep learning are discussed. Associative memory is conventionally described by recurrent neural networks with dynamical convergence to stable points. Deep learning typically uses feedforward neural nets without dynamics. However, a simple duality relates these two different views when applied to problems of pattern classification. From the perspective of associative memory such models deserve attention because they make it possible to store a much larger number of memories, compared to the quadratic case. In the dual description, these models correspond to feedforward neural networks with one hidden layer and unusual activation functions transmitting the activities of the visible neurons to the hidden layer. These activation functions are rectified polynomials of a higher degree rather than the rectified linear functions used in deep learning. The network learns representations of the data in terms of features for rectified linear functions, but as the power in the activation function is increased there is a gradual shift to a prototype-based representation, the two extreme regimes of pattern recognition known in cognitive psychology. Simons Center for Systems Biology.

Examples of Current and Future Uses of Neural-Net Image Processing for Aerospace Applications

NASA Technical Reports Server (NTRS)

Decker, Arthur J.

2004-01-01

Feed forward artificial neural networks are very convenient for performing correlated interpolation of pairs of complex noisy data sets as well as detecting small changes in image data. Image-to-image, image-to-variable and image-to-index applications have been tested at Glenn. Early demonstration applications are summarized including image-directed alignment of optics, tomography, flow-visualization control of wind-tunnel operations and structural-model-trained neural networks. A practical application is reviewed that employs neural-net detection of structural damage from interference fringe patterns. Both sensor-based and optics-only calibration procedures are available for this technique. These accomplishments have generated the knowledge necessary to suggest some other applications for NASA and Government programs. A tomography application is discussed to support Glenn's Icing Research tomography effort. The self-regularizing capability of a neural net is shown to predict the expected performance of the tomography geometry and to augment fast data processing. Other potential applications involve the quantum technologies. It may be possible to use a neural net as an image-to-image controller of an optical tweezers being used for diagnostics of isolated nano structures. The image-to-image transformation properties also offer the potential for simulating quantum computing. Computer resources are detailed for implementing the black box calibration features of the neural nets.

NETS

NASA Technical Reports Server (NTRS)

Baffes, Paul T.

1993-01-01

NETS development tool provides environment for simulation and development of neural networks - computer programs that "learn" from experience. Written in ANSI standard C, program allows user to generate C code for implementation of neural network.

Neural network technologies

NASA Technical Reports Server (NTRS)

Villarreal, James A.

1991-01-01

A whole new arena of computer technologies is now beginning to form. Still in its infancy, neural network technology is a biologically inspired methodology which draws on nature's own cognitive processes. The Software Technology Branch has provided a software tool, Neural Execution and Training System (NETS), to industry, government, and academia to facilitate and expedite the use of this technology. NETS is written in the C programming language and can be executed on a variety of machines. Once a network has been debugged, NETS can produce a C source code which implements the network. This code can then be incorporated into other software systems. Described here are various software projects currently under development with NETS and the anticipated future enhancements to NETS and the technology.

Optimization of Training Sets for Neural-Net Processing of Characteristic Patterns from Vibrating Solids

NASA Technical Reports Server (NTRS)

Decker, Arthur J.

2001-01-01

Artificial neural networks have been used for a number of years to process holography-generated characteristic patterns of vibrating structures. This technology depends critically on the selection and the conditioning of the training sets. A scaling operation called folding is discussed for conditioning training sets optimally for training feed-forward neural networks to process characteristic fringe patterns. Folding allows feed-forward nets to be trained easily to detect damage-induced vibration-displacement-distribution changes as small as 10 nm. A specific application to aerospace of neural-net processing of characteristic patterns is presented to motivate the conditioning and optimization effort.

A real time neural net estimator of fatigue life

NASA Technical Reports Server (NTRS)

Troudet, T.; Merrill, W.

1990-01-01

A neural net architecture is proposed to estimate, in real-time, the fatigue life of mechanical components, as part of the Intelligent Control System for Reusable Rocket Engines. Arbitrary component loading values were used as input to train a two hidden-layer feedforward neural net to estimate component fatigue damage. The ability of the net to learn, based on a local strain approach, the mapping between load sequence and fatigue damage has been demonstrated for a uniaxial specimen. Because of its demonstrated performance, the neural computation may be extended to complex cases where the loads are biaxial or triaxial, and the geometry of the component is complex (e.g., turbopump blades). The generality of the approach is such that load/damage mappings can be directly extracted from experimental data without requiring any knowledge of the stress/strain profile of the component. In addition, the parallel network architecture allows real-time life calculations even for high frequency vibrations. Owing to its distributed nature, the neural implementation will be robust and reliable, enabling its use in hostile environments such as rocket engines. This neural net estimator of fatigue life is seen as the enabling technology to achieve component life prognosis, and therefore would be an important part of life extending control for reusable rocket engines.

ER fluid applications to vibration control devices and an adaptive neural-net controller

NASA Astrophysics Data System (ADS)

Morishita, Shin; Ura, Tamaki

1993-07-01

Four applications of electrorheological (ER) fluid to vibration control actuators and an adaptive neural-net control system suitable for the controller of ER actuators are described: a shock absorber system for automobiles, a squeeze film damper bearing for rotational machines, a dynamic damper for multidegree-of-freedom structures, and a vibration isolator. An adaptive neural-net control system composed of a forward model network for structural identification and a controller network is introduced for the control system of these ER actuators. As an example study of intelligent vibration control systems, an experiment was performed in which the ER dynamic damper was attached to a beam structure and controlled by the present neural-net controller so that the vibration in several modes of the beam was reduced with a single dynamic damper.

Neural net applied to anthropological material: a methodical study on the human nasal skeleton.

PubMed

Prescher, Andreas; Meyers, Anne; Gerf von Keyserlingk, Diedrich

2005-07-01

A new information processing method, an artificial neural net, was applied to characterise the variability of anthropological features of the human nasal skeleton. The aim was to find different types of nasal skeletons. A neural net with 15*15 nodes was trained by 17 standard anthropological parameters taken from 184 skulls of the Aachen collection. The trained neural net delivers its classification in a two-dimensional map. Different types of noses were locally separated within the map. Rare and frequent types may be distinguished after one passage of the complete collection through the net. Statistical descriptive analysis, hierarchical cluster analysis, and discriminant analysis were applied to the same data set. These parallel applications allowed comparison of the new approach to the more traditional ones. In general the classification by the neural net is in correspondence with cluster analysis and discriminant analysis. However, it goes beyond these classifications because of the possibility of differentiating the types in multi-dimensional dependencies. Furthermore, places in the map are kept blank for intermediate forms, which may be theoretically expected, but were not included in the training set. In conclusion, the application of a neural network is a suitable method for investigating large collections of biological material. The gained classification may be helpful in anatomy and anthropology as well as in forensic medicine. It may be used to characterise the peculiarity of a whole set as well as to find particular cases within the set.

Brain without mind: Computer simulation of neural networks with modifiable neuronal interactions

NASA Astrophysics Data System (ADS)

Clark, John W.; Rafelski, Johann; Winston, Jeffrey V.

1985-07-01

Aspects of brain function are examined in terms of a nonlinear dynamical system of highly interconnected neuron-like binary decision elements. The model neurons operate synchronously in discrete time, according to deterministic or probabilistic equations of motion. Plasticity of the nervous system, which underlies such cognitive collective phenomena as adaptive development, learning, and memory, is represented by temporal modification of interneuronal connection strengths depending on momentary or recent neural activity. A formal basis is presented for the construction of local plasticity algorithms, or connection-modification routines, spanning a large class. To build an intuitive understanding of the behavior of discrete-time network models, extensive computer simulations have been carried out (a) for nets with fixed, quasirandom connectivity and (b) for nets with connections that evolve under one or another choice of plasticity algorithm. From the former experiments, insights are gained concerning the spontaneous emergence of order in the form of cyclic modes of neuronal activity. In the course of the latter experiments, a simple plasticity routine (“brainwashing,” or “anti-learning”) was identified which, applied to nets with initially quasirandom connectivity, creates model networks which provide more felicitous starting points for computer experiments on the engramming of content-addressable memories and on learning more generally. The potential relevance of this algorithm to developmental neurobiology and to sleep states is discussed. The model considered is at the same time a synthesis of earlier synchronous neural-network models and an elaboration upon them; accordingly, the present article offers both a focused review of the dynamical properties of such systems and a selection of new findings derived from computer simulation.

A comparison of polynomial approximations and artificial neural nets as response surfaces

NASA Technical Reports Server (NTRS)

Carpenter, William C.; Barthelemy, Jean-Francois M.

1992-01-01

Artificial neural nets and polynomial approximations were used to develop response surfaces for several test problems. Based on the number of functional evaluations required to build the approximations and the number of undetermined parameters associated with the approximations, the performance of the two types of approximations was found to be comparable. A rule of thumb is developed for determining the number of nodes to be used on a hidden layer of an artificial neural net, and the number of designs needed to train an approximation is discussed.

Usage of the back-propagation method for alphabet recognition

NASA Astrophysics Data System (ADS)

Shaila Sree, R. N.; Eswaran, Kumar; Sundararajan, N.

1999-03-01

Artificial Neural Networks play a pivotal role in the branch of Artificial Intelligence. They can be trained efficiently for a variety of tasks using different methods, of which the Back Propagation method is one among them. The paper studies the choosing of various design parameters of a neural network for the Back Propagation method. The study shows that when these parameters are properly assigned, the training task of the net is greatly simplified. The character recognition problem has been chosen as a test case for this study. A sample space of different handwritten characters of the English alphabet was gathered. A Neural net is finally designed taking many the design aspects into consideration and trained for different styles of writing. Experimental results are reported and discussed. It has been found that an appropriate choice of the design parameters of the neural net for the Back Propagation method reduces the training time and improves the performance of the net.

A neural net approach to space vehicle guidance

NASA Technical Reports Server (NTRS)

Caglayan, Alper K.; Allen, Scott M.

1990-01-01

The space vehicle guidance problem is formulated using a neural network approach, and the appropriate neural net architecture for modeling optimum guidance trajectories is investigated. In particular, an investigation is made of the incorporation of prior knowledge about the characteristics of the optimal guidance solution into the neural network architecture. The online classification performance of the developed network is demonstrated using a synthesized network trained with a database of optimum guidance trajectories. Such a neural-network-based guidance approach can readily adapt to environment uncertainties such as those encountered by an AOTV during atmospheric maneuvers.

Neural Network for Image-to-Image Control of Optical Tweezers

NASA Technical Reports Server (NTRS)

Decker, Arthur J.; Anderson, Robert C.; Weiland, Kenneth E.; Wrbanek, Susan Y.

2004-01-01

A method is discussed for using neural networks to control optical tweezers. Neural-net outputs are combined with scaling and tiling to generate 480 by 480-pixel control patterns for a spatial light modulator (SLM). The SLM can be combined in various ways with a microscope to create movable tweezers traps with controllable profiles. The neural nets are intended to respond to scattered light from carbon and silicon carbide nanotube sensors. The nanotube sensors are to be held by the traps for manipulation and calibration. Scaling and tiling allow the 100 by 100-pixel maximum resolution of the neural-net software to be applied in stages to exploit the full 480 by 480-pixel resolution of the SLM. One of these stages is intended to create sensitive null detectors for detecting variations in the scattered light from the nanotube sensors.

Introduction to Neural Networks.

DTIC Science & Technology

1992-03-01

parallel processing of information that can greatly reduce the time required to perform operations which are needed in pattern recognition. Neural network, Artificial neural network , Neural net, ANN.

Neural-net Processed Electronic Holography for Rotating Machines

NASA Technical Reports Server (NTRS)

Decker, Arthur J.

2003-01-01

This report presents the results of an R&D effort to apply neural-net processed electronic holography to NDE of rotors. Electronic holography was used to generate characteristic patterns or mode shapes of vibrating rotors and rotor components. Artificial neural networks were trained to identify damage-induced changes in the characteristic patterns. The development and optimization of a neural-net training method were the most significant contributions of this work, and the training method and its optimization are discussed in detail. A second positive result was the assembly and testing of a fiber-optic holocamera. A major disappointment was the inadequacy of the high-speed-holography hardware selected for this effort, but the use of scaled holograms to match the low effective resolution of an image intensifier was one interesting attempt to compensate. This report also discusses in some detail the physics and environmental requirements for rotor electronic holography. The major conclusions were that neural-net and electronic-holography inspections of stationary components in the laboratory and the field are quite practical and worthy of continuing development, but that electronic holography of moving rotors is still an expensive high-risk endeavor.

Neural networks for structural design - An integrated system implementation

NASA Technical Reports Server (NTRS)

Berke, Laszlo; Hafez, Wassim; Pao, Yoh-Han

1992-01-01

The development of powerful automated procedures to aid the creative designer is becoming increasingly critical for complex design tasks. In the work described here Artificial Neural Nets are applied to acquire structural analysis and optimization domain expertise. Based on initial instructions from the user an automated procedure generates random instances of structural analysis and/or optimization 'experiences' that cover a desired domain. It extracts training patterns from the created instances, constructs and trains an appropriate network architecture and checks the accuracy of net predictions. The final product is a trained neural net that can estimate analysis and/or optimization results instantaneously.

Design of neural networks for classification of remotely sensed imagery

NASA Technical Reports Server (NTRS)

Chettri, Samir R.; Cromp, Robert F.; Birmingham, Mark

1992-01-01

Classification accuracies of a backpropagation neural network are discussed and compared with a maximum likelihood classifier (MLC) with multivariate normal class models. We have found that, because of its nonparametric nature, the neural network outperforms the MLC in this area. In addition, we discuss techniques for constructing optimal neural nets on parallel hardware like the MasPar MP-1 currently at GSFC. Other important discussions are centered around training and classification times of the two methods, and sensitivity to the training data. Finally, we discuss future work in the area of classification and neural nets.

Residual Deep Convolutional Neural Network Predicts MGMT Methylation Status.

PubMed

Korfiatis, Panagiotis; Kline, Timothy L; Lachance, Daniel H; Parney, Ian F; Buckner, Jan C; Erickson, Bradley J

2017-10-01

Predicting methylation of the O6-methylguanine methyltransferase (MGMT) gene status utilizing MRI imaging is of high importance since it is a predictor of response and prognosis in brain tumors. In this study, we compare three different residual deep neural network (ResNet) architectures to evaluate their ability in predicting MGMT methylation status without the need for a distinct tumor segmentation step. We found that the ResNet50 (50 layers) architecture was the best performing model, achieving an accuracy of 94.90% (+/- 3.92%) for the test set (classification of a slice as no tumor, methylated MGMT, or non-methylated). ResNet34 (34 layers) achieved 80.72% (+/- 13.61%) while ResNet18 (18 layers) accuracy was 76.75% (+/- 20.67%). ResNet50 performance was statistically significantly better than both ResNet18 and ResNet34 architectures (p < 0.001). We report a method that alleviates the need of extensive preprocessing and acts as a proof of concept that deep neural architectures can be used to predict molecular biomarkers from routine medical images.

Neural net controller for inlet pressure control of rocket engine testing

NASA Technical Reports Server (NTRS)

Trevino, Luis C.

1994-01-01

Many dynamic systems operate in select operating regions, each exhibiting characteristic modes of behavior. It is traditional to employ standard adjustable gain proportional-integral-derivative (PID) loops in such systems where no apriori model information is available. However, for controlling inlet pressure for rocket engine testing, problems in fine tuning, disturbance accommodation, and control gains for new profile operating regions (for research and development) are typically encountered. Because of the capability of capturing I/O peculiarities, using NETS, a back propagation trained neural network is specified. For select operating regions, the neural network controller is simulated to be as robust as the PID controller. For a comparative analysis, the higher order moment neural array (HOMNA) method is used to specify a second neural controller by extracting critical exemplars from the I/O data set. Furthermore, using the critical exemplars from the HOMNA method, a third neural controller is developed using NETS back propagation algorithm. All controllers are benchmarked against each other.

Neural Network Development Tool (NETS)

NASA Technical Reports Server (NTRS)

Baffes, Paul T.

1990-01-01

Artificial neural networks formed from hundreds or thousands of simulated neurons, connected in manner similar to that in human brain. Such network models learning behavior. Using NETS involves translating problem to be solved into input/output pairs, designing network configuration, and training network. Written in C.

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.

Optical neural net for classifying imaging spectrometer data

NASA Technical Reports Server (NTRS)

Barnard, Etienne; Casasent, David P.

1989-01-01

The problem of determining the composition of an unknown input mixture from its measured spectrum, given the spectra of a number of elements, is studied. The Hopfield minimization procedure was used to express the determination of the compositions as a problem suitable for solution by neural nets. A mathematical description of the problem was developed and used as a basis for a neural network solution and an optical implementation.

Neural Net Gains Estimation Based on an Equivalent Model

PubMed Central

Aguilar Cruz, Karen Alicia; Medel Juárez, José de Jesús; Fernández Muñoz, José Luis; Esmeralda Vigueras Velázquez, Midory

2016-01-01

A model of an Equivalent Artificial Neural Net (EANN) describes the gains set, viewed as parameters in a layer, and this consideration is a reproducible process, applicable to a neuron in a neural net (NN). The EANN helps to estimate the NN gains or parameters, so we propose two methods to determine them. The first considers a fuzzy inference combined with the traditional Kalman filter, obtaining the equivalent model and estimating in a fuzzy sense the gains matrix A and the proper gain K into the traditional filter identification. The second develops a direct estimation in state space, describing an EANN using the expected value and the recursive description of the gains estimation. Finally, a comparison of both descriptions is performed; highlighting the analytical method describes the neural net coefficients in a direct form, whereas the other technique requires selecting into the Knowledge Base (KB) the factors based on the functional error and the reference signal built with the past information of the system. PMID:27366146

Neural Net Gains Estimation Based on an Equivalent Model.

PubMed

Aguilar Cruz, Karen Alicia; Medel Juárez, José de Jesús; Fernández Muñoz, José Luis; Esmeralda Vigueras Velázquez, Midory

2016-01-01

A model of an Equivalent Artificial Neural Net (EANN) describes the gains set, viewed as parameters in a layer, and this consideration is a reproducible process, applicable to a neuron in a neural net (NN). The EANN helps to estimate the NN gains or parameters, so we propose two methods to determine them. The first considers a fuzzy inference combined with the traditional Kalman filter, obtaining the equivalent model and estimating in a fuzzy sense the gains matrix A and the proper gain K into the traditional filter identification. The second develops a direct estimation in state space, describing an EANN using the expected value and the recursive description of the gains estimation. Finally, a comparison of both descriptions is performed; highlighting the analytical method describes the neural net coefficients in a direct form, whereas the other technique requires selecting into the Knowledge Base (KB) the factors based on the functional error and the reference signal built with the past information of the system.

Vector control of wind turbine on the basis of the fuzzy selective neural net*

NASA Astrophysics Data System (ADS)

Engel, E. A.; Kovalev, I. V.; Engel, N. E.

2016-04-01

An article describes vector control of wind turbine based on fuzzy selective neural net. Based on the wind turbine system’s state, the fuzzy selective neural net tracks an maximum power point under random perturbations. Numerical simulations are accomplished to clarify the applicability and advantages of the proposed vector wind turbine’s control on the basis of the fuzzy selective neuronet. The simulation results show that the proposed intelligent control of wind turbine achieves real-time control speed and competitive performance, as compared to a classical control model with PID controllers based on traditional maximum torque control strategy.

Variability-induced transition in a net of neural elements: From oscillatory to excitable behavior.

PubMed

Glatt, Erik; Gassel, Martin; Kaiser, Friedemann

2006-06-01

Starting with an oscillatory net of neural elements, increasing variability induces a phase transition to excitability. This transition is explained by a systematic effect of the variability, which stabilizes the formerly unstable, spatially uniform, temporally constant solution of the net. Multiplicative noise may also influence the net in a systematic way and may thus induce a similar transition. Adding noise into the model, the interplay of noise and variability with respect to the reported transition is investigated. Finally, pattern formation in a diffusively coupled net is studied, because excitability implies the ability of pattern formation and information transmission.

Decision net, directed graph, and neural net processing of imaging spectrometer data

NASA Technical Reports Server (NTRS)

Casasent, David; Liu, Shiaw-Dong; Yoneyama, Hideyuki; Barnard, Etienne

1989-01-01

A decision-net solution involving a novel hierarchical classifier and a set of multiple directed graphs, as well as a neural-net solution, are respectively presented for large-class problem and mixture problem treatments of imaging spectrometer data. The clustering method for hierarchical classifier design, when used with multiple directed graphs, yields an efficient decision net. New directed-graph rules for reducing local maxima as well as the number of perturbations required, and the new starting-node rules for extending the reachability and reducing the search time of the graphs, are noted to yield superior results, as indicated by an illustrative 500-class imaging spectrometer problem.

ChemNet: A Transferable and Generalizable Deep Neural Network for Small-Molecule Property Prediction

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

Goh, Garrett B.; Siegel, Charles M.; Vishnu, Abhinav

With access to large datasets, deep neural networks through representation learning have been able to identify patterns from raw data, achieving human-level accuracy in image and speech recognition tasks. However, in chemistry, availability of large standardized and labelled datasets is scarce, and with a multitude of chemical properties of interest, chemical data is inherently small and fragmented. In this work, we explore transfer learning techniques in conjunction with the existing Chemception CNN model, to create a transferable and generalizable deep neural network for small-molecule property prediction. Our latest model, ChemNet learns in a semi-supervised manner from inexpensive labels computed frommore » the ChEMBL database. When fine-tuned to the Tox21, HIV and FreeSolv dataset, which are 3 separate chemical tasks that ChemNet was not originally trained on, we demonstrate that ChemNet exceeds the performance of existing Chemception models, contemporary MLP models that trains on molecular fingerprints, and it matches the performance of the ConvGraph algorithm, the current state-of-the-art. Furthermore, as ChemNet has been pre-trained on a large diverse chemical database, it can be used as a universal “plug-and-play” deep neural network, which accelerates the deployment of deep neural networks for the prediction of novel small-molecule chemical properties.« less

Neural networks for calibration tomography

NASA Technical Reports Server (NTRS)

Decker, Arthur

1993-01-01

Artificial neural networks are suitable for performing pattern-to-pattern calibrations. These calibrations are potentially useful for facilities operations in aeronautics, the control of optical alignment, and the like. Computed tomography is compared with neural net calibration tomography for estimating density from its x-ray transform. X-ray transforms are measured, for example, in diffuse-illumination, holographic interferometry of fluids. Computed tomography and neural net calibration tomography are shown to have comparable performance for a 10 degree viewing cone and 29 interferograms within that cone. The system of tomography discussed is proposed as a relevant test of neural networks and other parallel processors intended for using flow visualization data.

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.

Squeeze-SegNet: a new fast deep convolutional neural network for semantic segmentation

NASA Astrophysics Data System (ADS)

Nanfack, Geraldin; Elhassouny, Azeddine; Oulad Haj Thami, Rachid

2018-04-01

The recent researches in Deep Convolutional Neural Network have focused their attention on improving accuracy that provide significant advances. However, if they were limited to classification tasks, nowadays with contributions from Scientific Communities who are embarking in this field, they have become very useful in higher level tasks such as object detection and pixel-wise semantic segmentation. Thus, brilliant ideas in the field of semantic segmentation with deep learning have completed the state of the art of accuracy, however this architectures become very difficult to apply in embedded systems as is the case for autonomous driving. We present a new Deep fully Convolutional Neural Network for pixel-wise semantic segmentation which we call Squeeze-SegNet. The architecture is based on Encoder-Decoder style. We use a SqueezeNet-like encoder and a decoder formed by our proposed squeeze-decoder module and upsample layer using downsample indices like in SegNet and we add a deconvolution layer to provide final multi-channel feature map. On datasets like Camvid or City-states, our net gets SegNet-level accuracy with less than 10 times fewer parameters than SegNet.

Application of artificial neural networks to the design optimization of aerospace structural components

NASA Technical Reports Server (NTRS)

Berke, Laszlo; Patnaik, Surya N.; Murthy, Pappu L. N.

1993-01-01

The application of artificial neural networks to capture structural design expertise is demonstrated. The principal advantage of a trained neural network is that it requires trivial computational effort to produce an acceptable new design. For the class of problems addressed, the development of a conventional expert system would be extremely difficult. In the present effort, a structural optimization code with multiple nonlinear programming algorithms and an artificial neural network code NETS were used. A set of optimum designs for a ring and two aircraft wings for static and dynamic constraints were generated by using the optimization codes. The optimum design data were processed to obtain input and output pairs, which were used to develop a trained artificial neural network with the code NETS. Optimum designs for new design conditions were predicted by using the trained network. Neural net prediction of optimum designs was found to be satisfactory for most of the output design parameters. However, results from the present study indicate that caution must be exercised to ensure that all design variables are within selected error bounds.

Optimum Design of Aerospace Structural Components Using Neural Networks

NASA Technical Reports Server (NTRS)

Berke, L.; Patnaik, S. N.; Murthy, P. L. N.

1993-01-01

The application of artificial neural networks to capture structural design expertise is demonstrated. The principal advantage of a trained neural network is that it requires a trivial computational effort to produce an acceptable new design. For the class of problems addressed, the development of a conventional expert system would be extremely difficult. In the present effort, a structural optimization code with multiple nonlinear programming algorithms and an artificial neural network code NETS were used. A set of optimum designs for a ring and two aircraft wings for static and dynamic constraints were generated using the optimization codes. The optimum design data were processed to obtain input and output pairs, which were used to develop a trained artificial neural network using the code NETS. Optimum designs for new design conditions were predicted using the trained network. Neural net prediction of optimum designs was found to be satisfactory for the majority of the output design parameters. However, results from the present study indicate that caution must be exercised to ensure that all design variables are within selected error bounds.

Neural Network and Letter Recognition.

NASA Astrophysics Data System (ADS)

Lee, Hue Yeon

Neural net architectures and learning algorithms that recognize hand written 36 alphanumeric characters are studied. The thin line input patterns written in 32 x 32 binary array are used. The system is comprised of two major components, viz. a preprocessing unit and a Recognition unit. The preprocessing unit in turn consists of three layers of neurons; the U-layer, the V-layer, and the C -layer. The functions of the U-layer is to extract local features by template matching. The correlation between the detected local features are considered. Through correlating neurons in a plane with their neighboring neurons, the V-layer would thicken the on-cells or lines that are groups of on-cells of the previous layer. These two correlations would yield some deformation tolerance and some of the rotational tolerance of the system. The C-layer then compresses data through the 'Gabor' transform. Pattern dependent choice of center and wavelengths of 'Gabor' filters is the cause of shift and scale tolerance of the system. Three different learning schemes had been investigated in the recognition unit, namely; the error back propagation learning with hidden units, a simple perceptron learning, and a competitive learning. Their performances were analyzed and compared. Since sometimes the network fails to distinguish between two letters that are inherently similar, additional ambiguity resolving neural nets are introduced on top of the above main neural net. The two dimensional Fourier transform is used as the preprocessing and the perceptron is used as the recognition unit of the ambiguity resolver. One hundred different person's handwriting sets are collected. Some of these are used as the training sets and the remainders are used as the test sets. The correct recognition rate of the system increases with the number of training sets and eventually saturates at a certain value. Similar recognition rates are obtained for the above three different learning algorithms. The minimum error rate, 4.9% is achieved for alphanumeric sets when 50 sets are trained. With the ambiguity resolver, it is reduced to 2.5%. In case that only numeral sets are trained and tested, 2.0% error rate is achieved. When only alphabet sets are considered, the error rate is reduced to 1.1%.

Post interaural neural net-based vowel recognition

NASA Astrophysics Data System (ADS)

Jouny, Ismail I.

2001-10-01

Interaural head related transfer functions are used to process speech signatures prior to neural net based recognition. Data representing the head related transfer function of a dummy has been collected at MIT and made available on the Internet. This data is used to pre-process vowel signatures to mimic the effects of human ear on speech perception. Signatures representing various vowels of the English language are then presented to a multi-layer perceptron trained using the back propagation algorithm for recognition purposes. The focus in this paper is to assess the effects of human interaural system on vowel recognition performance particularly when using a classification system that mimics the human brain such as a neural net.

Comparing and Contrasting Neural Net Solutions to Classical Statistical Solutions.

ERIC Educational Resources Information Center

Van Nelson, C.; Neff, Kathryn J.

Data from two studies in which subjects were classified as successful or unsuccessful were analyzed using neural net technology after being analyzed with a linear regression function. Data were obtained from admission records of 201 students admitted to undergraduate and 285 students admitted to graduate programs. Data included grade point…

Detection of Structural Abnormalities Using Neural Nets

NASA Technical Reports Server (NTRS)

Zak, M.; Maccalla, A.; Daggumati, V.; Gulati, S.; Toomarian, N.

1996-01-01

This paper describes a feed-forward neural net approach for detection of abnormal system behavior based upon sensor data analyses. A new dynamical invariant representing structural parameters of the system is introduced in such a way that any structural abnormalities in the system behavior are detected from the corresponding changes to the invariant.

A hybrid architecture for the implementation of the Athena neural net model

NASA Technical Reports Server (NTRS)

Koutsougeras, C.; Papachristou, C.

1989-01-01

The implementation of an earlier introduced neural net model for pattern classification is considered. Data flow principles are employed in the development of a machine that efficiently implements the model and can be useful for real time classification tasks. Further enhancement with optical computing structures is also considered.

Extra permeability is required to model dynamic oxygen measurements: evidence for functional recruitment?

PubMed Central

Barrett, Matthew JP; Suresh, Vinod

2013-01-01

Neural activation triggers a rapid, focal increase in blood flow and thus oxygen delivery. Local oxygen consumption also increases, although not to the same extent as oxygen delivery. This ‘uncoupling' enables a number of widely-used functional neuroimaging techniques; however, the physiologic mechanisms that govern oxygen transport under these conditions remain unclear. Here, we explore this dynamic process using a new mathematical model. Motivated by experimental observations and previous modeling, we hypothesized that functional recruitment of capillaries has an important role during neural activation. Using conventional mechanisms alone, the model predictions were inconsistent with in vivo measurements of oxygen partial pressure. However, dynamically increasing net capillary permeability, a simple description of functional recruitment, led to predictions consistent with the data. Increasing permeability in all vessel types had the same effect, but two alternative mechanisms were unable to produce predictions consistent with the data. These results are further evidence that conventional models of oxygen transport are not sufficient to predict dynamic experimental data. The data and modeling suggest that it is necessary to include a mechanism that dynamically increases net vascular permeability. While the model cannot distinguish between the different possibilities, we speculate that functional recruitment could have this effect in vivo. PMID:23673433

A new neural net approach to robot 3D perception and visuo-motor coordination

NASA Technical Reports Server (NTRS)

Lee, Sukhan

1992-01-01

A novel neural network approach to robot hand-eye coordination is presented. The approach provides a true sense of visual error servoing, redundant arm configuration control for collision avoidance, and invariant visuo-motor learning under gazing control. A 3-D perception network is introduced to represent the robot internal 3-D metric space in which visual error servoing and arm configuration control are performed. The arm kinematic network performs the bidirectional association between 3-D space arm configurations and joint angles, and enforces the legitimate arm configurations. The arm kinematic net is structured by a radial-based competitive and cooperative network with hierarchical self-organizing learning. The main goal of the present work is to demonstrate that the neural net representation of the robot 3-D perception net serves as an important intermediate functional block connecting robot eyes and arms.

Neural-Network-Development Program

NASA Technical Reports Server (NTRS)

Phillips, Todd A.

1993-01-01

NETS, software tool for development and evaluation of neural networks, provides simulation of neural-network algorithms plus computing environment for development of such algorithms. Uses back-propagation learning method for all of networks it creates. Enables user to customize patterns of connections between layers of network. Also provides features for saving, during learning process, values of weights, providing more-precise control over learning process. Written in ANSI standard C language. Machine-independent version (MSC-21588) includes only code for command-line-interface version of NETS 3.0.

Characterization of NvLWamide-like neurons reveals stereotypy in Nematostella nerve net development.

PubMed

Havrilak, Jamie A; Faltine-Gonzalez, Dylan; Wen, Yiling; Fodera, Daniella; Simpson, Ayanna C; Magie, Craig R; Layden, Michael J

2017-11-15

The organization of cnidarian nerve nets is traditionally described as diffuse with randomly arranged neurites that show minimal reproducibility between animals. However, most observations of nerve nets are conducted using cross-reactive antibodies that broadly label neurons, which potentially masks stereotyped patterns produced by individual neuronal subtypes. Additionally, many cnidarians species have overt structures such as a nerve ring, suggesting higher levels of organization and stereotypy exist, but mechanisms that generated that stereotypy are unknown. We previously demonstrated that NvLWamide-like is expressed in a small subset of the Nematostella nerve net and speculated that observing a few neurons within the developing nerve net would provide a better indication of potential stereotypy. Here we document NvLWamide-like expression more systematically. NvLWamide-like is initially expressed in the typical neurogenic salt and pepper pattern within the ectoderm at the gastrula stage, and expression expands to include endodermal salt and pepper expression at the planula larval stage. Expression persists in both ectoderm and endoderm in adults. We characterized our NvLWamide-like::mCherry transgenic reporter line to visualize neural architecture and found that NvLWamide-like is expressed in six neural subtypes identifiable by neural morphology and location. Upon completing development the numbers of neurons in each neural subtype are minimally variable between animals and the projection patterns of each subtype are consistent. Furthermore, between the juvenile polyp and adult stages the number of neurons for each subtype increases. We conclude that development of the Nematostella nerve net is stereotyped between individuals. Our data also imply that one aspect of generating adult cnidarian nervous systems is to modify the basic structural architecture generated in the juvenile by increasing neural number proportionally with size. Copyright © 2017 The Authors. Published by Elsevier Inc. All rights reserved.

Forecasting volcanic air pollution in Hawaii: Tests of time series models

NASA Astrophysics Data System (ADS)

Reikard, Gordon

2012-12-01

Volcanic air pollution, known as vog (volcanic smog) has recently become a major issue in the Hawaiian islands. Vog is caused when volcanic gases react with oxygen and water vapor. It consists of a mixture of gases and aerosols, which include sulfur dioxide and other sulfates. The source of the volcanic gases is the continuing eruption of Mount Kilauea. This paper studies predicting vog using statistical methods. The data sets include time series for SO2 and SO4, over locations spanning the west, south and southeast coasts of Hawaii, and the city of Hilo. The forecasting models include regressions and neural networks, and a frequency domain algorithm. The most typical pattern for the SO2 data is for the frequency domain method to yield the most accurate forecasts over the first few hours, and at the 24 h horizon. The neural net places second. For the SO4 data, the results are less consistent. At two sites, the neural net generally yields the most accurate forecasts, except at the 1 and 24 h horizons, where the frequency domain technique wins narrowly. At one site, the neural net and the frequency domain algorithm yield comparable errors over the first 5 h, after which the neural net dominates. At the remaining site, the frequency domain method is more accurate over the first 4 h, after which the neural net achieves smaller errors. For all the series, the average errors are well within one standard deviation of the actual data at all the horizons. However, the errors also show irregular outliers. In essence, the models capture the central tendency of the data, but are less effective in predicting the extreme events.

Neural Nets for Generalization and Classification: Comment on Staddon and Reid (1990).

ERIC Educational Resources Information Center

Shepard, Roger N.

1990-01-01

The neural net model of J. E. R. Staddon and A. K. Reid (1990) explains exponential and Gaussian generalization gradients in the same way as the diffusion model of R. N. Shepard (1958). The cognitive generalization theory of Shepard (1987), also implemented as a connectionist network, goes beyond both models in accounting for classification…

Neural Net-Based Redesign of Transonic Turbines for Improved Unsteady Aerodynamic Performance

NASA Technical Reports Server (NTRS)

Madavan, Nateri K.; Rai, Man Mohan; Huber, Frank W.

1998-01-01

A recently developed neural net-based aerodynamic design procedure is used in the redesign of a transonic turbine stage to improve its unsteady aerodynamic performance. The redesign procedure used incorporates the advantages of both traditional response surface methodology (RSM) and neural networks by employing a strategy called parameter-based partitioning of the design space. Starting from the reference design, a sequence of response surfaces based on both neural networks and polynomial fits are constructed to traverse the design space in search of an optimal solution that exhibits improved unsteady performance. The procedure combines the power of neural networks and the economy of low-order polynomials (in terms of number of simulations required and network training requirements). A time-accurate, two-dimensional, Navier-Stokes solver is used to evaluate the various intermediate designs and provide inputs to the optimization procedure. The optimization procedure yields a modified design that improves the aerodynamic performance through small changes to the reference design geometry. The computed results demonstrate the capabilities of the neural net-based design procedure, and also show the tremendous advantages that can be gained by including high-fidelity unsteady simulations that capture the relevant flow physics in the design optimization process.

A real time neural net estimator of fatigue life

NASA Technical Reports Server (NTRS)

Troudet, T.; Merrill, W.

1990-01-01

A neural network architecture is proposed to estimate, in real-time, the fatigue life of mechanical components, as part of the intelligent Control System for Reusable Rocket Engines. Arbitrary component loading values were used as input to train a two hidden-layer feedforward neural net to estimate component fatigue damage. The ability of the net to learn, based on a local strain approach, the mapping between load sequence and fatigue damage has been demonstrated for a uniaxial specimen. Because of its demonstrated performance, the neural computation may be extended to complex cases where the loads are biaxial or triaxial, and the geometry of the component is complex (e.g., turbopumps blades). The generality of the approach is such that load/damage mappings can be directly extracted from experimental data without requiring any knowledge of the stress/strain profile of the component. In addition, the parallel network architecture allows real-time life calculations even for high-frequency vibrations. Owing to its distributed nature, the neural implementation will be robust and reliable, enabling its use in hostile environments such as rocket engines.

Bladder control, urgency, and urge incontinence: evidence from functional brain imaging.

PubMed

Griffiths, Derek; Tadic, Stasa D

2008-01-01

To review brain imaging studies of bladder control in subjects with normal control and urge incontinence; to define a simple model of supraspinal bladder control; and to propose a neural correlate of urgency and possible origins of urge incontinence. Review of published reports of brain imaging relevant to urine storage, and secondary analyses of our own recent observations. In a simple model of normal urine storage, bladder and urethral afferents received in the periaqueductal gray (PAG) are mapped in the insula, forming the basis of sensation; the anterior cingulate gyrus (ACG) provides monitoring and control; the prefrontal cortex makes voiding decisions. The net result, as the bladder fills, is inhibition of the pontine micturition center (PMC) and of voiding, together with gradual increase in insular response, corresponding to increasing desire to void. In urge-incontinent subjects, brain responses differ. At large bladder volumes and strong sensation, but without detrusor overactivity (DO), most cortical responses become exaggerated, especially in ACG. This may be both a learned reaction to previous incontinence episodes and the neural correlate of urgency. The neural signature of DO itself seems to be prefrontal deactivation. Possible causes of urge incontinence include dysfunction of prefrontal cortex or limbic system, suggested by weak responses and/or deactivation, as well as abnormal afferent signals or re-emergence of infantile reflexes. Bladder control depends on an extensive network of brain regions. Dysfunction in various parts may contribute to urge incontinence, suggesting that there are different phenotypes requiring different treatments. (c) 2007 Wiley-Liss, Inc.

tf_unet: Generic convolutional neural network U-Net implementation in Tensorflow

NASA Astrophysics Data System (ADS)

Akeret, Joel; Chang, Chihway; Lucchi, Aurelien; Refregier, Alexandre

2016-11-01

tf_unet mitigates radio frequency interference (RFI) signals in radio data using a special type of Convolutional Neural Network, the U-Net, that enables the classification of clean signal and RFI signatures in 2D time-ordered data acquired from a radio telescope. The code is not tied to a specific segmentation and can be used, for example, to detect radio frequency interference (RFI) in radio astronomy or galaxies and stars in widefield imaging data. This U-Net implementation can outperform classical RFI mitigation algorithms.

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.

Quantum Neural Nets

NASA Technical Reports Server (NTRS)

Zak, Michail; Williams, Colin P.

1997-01-01

The capacity of classical neurocomputers is limited by the number of classical degrees of freedom which is roughly proportional to the size of the computer. By Contrast, a Hypothetical quantum neurocomputer can implement an exponentially large number of the degrees of freedom within the same size. In this paper an attempt is made to reconcile linear reversible structure of quantum evolution with nonlinear irreversible dynamics for neural nets.

Acoustic method of damage sensing in composite materials

NASA Technical Reports Server (NTRS)

Workman, Gary L.; Walker, James; Lansing, Matthew

1994-01-01

The use of acoustic emission and acousto-ultrasonics to characterize impact damage in composite structures is being performed on both graphite epoxy and kevlar bottles. Further development of the acoustic emission methodology to include neural net analysis and/or other multivariate techniques will enhance the capability of the technique to identify failure mechanisms during fracture. The acousto-ultrasonics technique will be investigated to determine its ability to predict regions prone to failure prior to the burst tests. The combination of the two methods will allow for simple nondestructive tests to be capable of predicting the performance of a composite structure prior to being placed in service and during service.

Partially pre-calculated weights for the backpropagation learning regime and high accuracy function mapping using continuous input RAM-based sigma-pi nets.

PubMed

Neville, R S; Stonham, T J; Glover, R J

2000-01-01

In this article we present a methodology that partially pre-calculates the weight updates of the backpropagation learning regime and obtains high accuracy function mapping. The paper shows how to implement neural units in a digital formulation which enables the weights to be quantised to 8-bits and the activations to 9-bits. A novel methodology is introduced to enable the accuracy of sigma-pi units to be increased by expanding their internal state space. We, also, introduce a novel means of implementing bit-streams in ring memories instead of utilising shift registers. The investigation utilises digital "Higher Order" sigma-pi nodes and studies continuous input RAM-based sigma-pi units. The units are trained with the backpropagation learning regime to learn functions to a high accuracy. The neural model is the sigma-pi units which can be implemented in digital microelectronic technology. The ability to perform tasks that require the input of real-valued information, is one of the central requirements of any cognitive system that utilises artificial neural network methodologies. In this article we present recent research which investigates a technique that can be used for mapping accurate real-valued functions to RAM-nets. One of our goals was to achieve accuracies of better than 1% for target output functions in the range Y epsilon [0,1], this is equivalent to an average Mean Square Error (MSE) over all training vectors of 0.0001 or an error modulus of 0.01. We present a development of the sigma-pi node which enables the provision of high accuracy outputs. The sigma-pi neural model was initially developed by Gurney (Learning in nets of structured hypercubes. PhD Thesis, Department of Electrical Engineering, Brunel University, Middlessex, UK, 1989; available as Technical Memo CN/R/144). Gurney's neuron models, the Time Integration Node (TIN), utilises an activation that was derived from a bit-stream. In this article we present a new methodology for storing sigma-pi node's activations as single values which are averages. In the course of the article we state what we define as a real number; how we represent real numbers and input of continuous values in our neural system. We show how to utilise the bounded quantised site-values (weights) of sigma-pi nodes to make training of these neurocomputing systems simple, using pre-calculated look-up tables to train the nets. In order to meet our accuracy goal, we introduce a means of increasing the bandwidth capability of sigma-pi units by expanding their internal state-space. In our implementation we utilise bit-streams when we calculate the real-valued outputs of the net. To simplify the hardware implementation of bit-streams we present a method of mapping them to RAM-based hardware using 'ring memories'. Finally, we study the sigma-pi units' ability to generalise once they are trained to map real-valued, high accuracy, continuous functions. We use sigma-pi units as they have been shown to have shorter training times than their analogue counterparts and can also overcome some of the drawbacks of semi-linear units (Gurney, 1992. Neural Networks, 5, 289-303).

Fuzzy Petri nets to model vision system decisions within a flexible manufacturing system

NASA Astrophysics Data System (ADS)

Hanna, Moheb M.; Buck, A. A.; Smith, R.

1994-10-01

The paper presents a Petri net approach to modelling, monitoring and control of the behavior of an FMS cell. The FMS cell described comprises a pick and place robot, vision system, CNC-milling machine and 3 conveyors. The work illustrates how the block diagrams in a hierarchical structure can be used to describe events at different levels of abstraction. It focuses on Fuzzy Petri nets (Fuzzy logic with Petri nets) including an artificial neural network (Fuzzy Neural Petri nets) to model and control vision system decisions and robot sequences within an FMS cell. This methodology can be used as a graphical modelling tool to monitor and control the imprecise, vague and uncertain situations, and determine the quality of the output product of an FMS cell.

Implementing neural nets with programmable logic

NASA Technical Reports Server (NTRS)

Vidal, Jacques J.

1988-01-01

Networks of Boolean programmable logic modules are presented as one purely digital class of artificial neural nets. The approach contrasts with the continuous analog framework usually suggested. Programmable logic networks are capable of handling many neural-net applications. They avoid some of the limitations of threshold logic networks and present distinct opportunities. The network nodes are called dynamically programmable logic modules. They can be implemented with digitally controlled demultiplexers. Each node performs a Boolean function of its inputs which can be dynamically assigned. The overall network is therefore a combinational circuit and its outputs are Boolean global functions of the network's input variables. The approach offers definite advantages for VLSI implementation, namely, a regular architecture with limited connectivity, simplicity of the control machinery, natural modularity, and the support of a mature technology.

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.

Artificial neural network prediction of aircraft aeroelastic behavior

NASA Astrophysics Data System (ADS)

Pesonen, Urpo Juhani

An Artificial Neural Network that predicts aeroelastic behavior of aircraft is presented. The neural net was designed to predict the shape of a flexible wing in static flight conditions using results from a structural analysis and an aerodynamic analysis performed with traditional computational tools. To generate reliable training and testing data for the network, an aeroelastic analysis code using these tools as components was designed and validated. To demonstrate the advantages and reliability of Artificial Neural Networks, a network was also designed and trained to predict airfoil maximum lift at low Reynolds numbers where wind tunnel data was used for the training. Finally, a neural net was designed and trained to predict the static aeroelastic behavior of a wing without the need to iterate between the structural and aerodynamic solvers.

Integration of perception and reasoning in fast neural modules

NASA Technical Reports Server (NTRS)

Fritz, David G.

1989-01-01

Artificial neural systems promise to integrate symbolic and sub-symbolic processing to achieve real time control of physical systems. Two potential alternatives exist. In one, neural nets can be used to front-end expert systems. The expert systems, in turn, are developed with varying degrees of parallelism, including their implementation in neural nets. In the other, rule-based reasoning and sensor data can be integrated within a single hybrid neural system. The hybrid system reacts as a unit to provide decisions (problem solutions) based on the simultaneous evaluation of data and rules. Discussed here is a model hybrid system based on the fuzzy cognitive map (FCM). The operation of the model is illustrated with the control of a hypothetical satellite that intelligently alters its attitude in space in response to an intersecting micrometeorite shower.

A 3D Active Learning Application for NeMO-Net, the NASA Neural Multi-Modal Observation and Training Network for Global Coral Reef Assessment

NASA Technical Reports Server (NTRS)

van den Bergh, Jarrett; Schutz, Joey; Li, Alan; Chirayath, Ved

2017-01-01

NeMO-Net, the NASA neural multi-modal observation and training network for global coral reef assessment, is an open-source deep convolutional neural network and interactive active learning training software aiming to accurately assess the present and past dynamics of coral reef ecosystems through determination of percent living cover and morphology as well as mapping of spatial distribution. We present an interactive video game prototype for tablet and mobile devices where users interactively label morphology classifications over mm-scale 3D coral reef imagery captured using fluid lensing to create a dataset that will be used to train NeMO-Nets convolutional neural network. The application currently allows for users to classify preselected regions of coral in the Pacific and will be expanded to include additional regions captured using our NASA FluidCam instrument, presently the highest-resolution remote sensing benthic imaging technology capable of removing ocean wave distortion, as well as lower-resolution airborne remote sensing data from the ongoing NASA CORAL campaign. Active learning applications present a novel methodology for efficiently training large-scale Neural Networks wherein variances in identification can be rapidly mitigated against control data. NeMO-Net periodically checks users input against pre-classified coral imagery to gauge their accuracy and utilize in-game mechanics to provide classification training. Users actively communicate with a server and are requested to classify areas of coral for which other users had conflicting classifications and contribute their input to a larger database for ranking. In partnering with Mission Blue and IUCN, NeMO-Net leverages an international consortium of subject matter experts to classify areas of confusion identified by NeMO-Net and generate additional labels crucial for identifying decision boundary locations in coral reef assessment.

A 3D Active Learning Application for NeMO-Net, the NASA Neural Multi-Modal Observation and Training Network for Global Coral Reef Assessment

NASA Astrophysics Data System (ADS)

van den Bergh, J.; Schutz, J.; Chirayath, V.; Li, A.

2017-12-01

NeMO-Net, the NASA neural multi-modal observation and training network for global coral reef assessment, is an open-source deep convolutional neural network and interactive active learning training software aiming to accurately assess the present and past dynamics of coral reef ecosystems through determination of percent living cover and morphology as well as mapping of spatial distribution. We present an interactive video game prototype for tablet and mobile devices where users interactively label morphology classifications over mm-scale 3D coral reef imagery captured using fluid lensing to create a dataset that will be used to train NeMO-Net's convolutional neural network. The application currently allows for users to classify preselected regions of coral in the Pacific and will be expanded to include additional regions captured using our NASA FluidCam instrument, presently the highest-resolution remote sensing benthic imaging technology capable of removing ocean wave distortion, as well as lower-resolution airborne remote sensing data from the ongoing NASA CORAL campaign.Active learning applications present a novel methodology for efficiently training large-scale Neural Networks wherein variances in identification can be rapidly mitigated against control data. NeMO-Net periodically checks users' input against pre-classified coral imagery to gauge their accuracy and utilizes in-game mechanics to provide classification training. Users actively communicate with a server and are requested to classify areas of coral for which other users had conflicting classifications and contribute their input to a larger database for ranking. In partnering with Mission Blue and IUCN, NeMO-Net leverages an international consortium of subject matter experts to classify areas of confusion identified by NeMO-Net and generate additional labels crucial for identifying decision boundary locations in coral reef assessment.

A solution to neural field equations by a recurrent neural network method

NASA Astrophysics Data System (ADS)

Alharbi, Abir

2012-09-01

Neural field equations (NFE) are used to model the activity of neurons in the brain, it is introduced from a single neuron 'integrate-and-fire model' starting point. The neural continuum is spatially discretized for numerical studies, and the governing equations are modeled as a system of ordinary differential equations. In this article the recurrent neural network approach is used to solve this system of ODEs. This consists of a technique developed by combining the standard numerical method of finite-differences with the Hopfield neural network. The architecture of the net, energy function, updating equations, and algorithms are developed for the NFE model. A Hopfield Neural Network is then designed to minimize the energy function modeling the NFE. Results obtained from the Hopfield-finite-differences net show excellent performance in terms of accuracy and speed. The parallelism nature of the Hopfield approaches may make them easier to implement on fast parallel computers and give them the speed advantage over the traditional methods.

Convolutional neural network approach for enhanced capture of breast parenchymal complexity patterns associated with breast cancer risk

NASA Astrophysics Data System (ADS)

Oustimov, Andrew; Gastounioti, Aimilia; Hsieh, Meng-Kang; Pantalone, Lauren; Conant, Emily F.; Kontos, Despina

2017-03-01

We assess the feasibility of a parenchymal texture feature fusion approach, utilizing a convolutional neural network (ConvNet) architecture, to benefit breast cancer risk assessment. Hypothesizing that by capturing sparse, subtle interactions between localized motifs present in two-dimensional texture feature maps derived from mammographic images, a multitude of texture feature descriptors can be optimally reduced to five meta-features capable of serving as a basis on which a linear classifier, such as logistic regression, can efficiently assess breast cancer risk. We combine this methodology with our previously validated lattice-based strategy for parenchymal texture analysis and we evaluate the feasibility of this approach in a case-control study with 424 digital mammograms. In a randomized split-sample setting, we optimize our framework in training/validation sets (N=300) and evaluate its descriminatory performance in an independent test set (N=124). The discriminatory capacity is assessed in terms of the the area under the curve (AUC) of the receiver operator characteristic (ROC). The resulting meta-features exhibited strong classification capability in the test dataset (AUC = 0.90), outperforming conventional, non-fused, texture analysis which previously resulted in an AUC=0.85 on the same case-control dataset. Our results suggest that informative interactions between localized motifs exist and can be extracted and summarized via a fairly simple ConvNet architecture.

Fast neural net simulation with a DSP processor array.

PubMed

Muller, U A; Gunzinger, A; Guggenbuhl, W

1995-01-01

This paper describes the implementation of a fast neural net simulator on a novel parallel distributed-memory computer. A 60-processor system, named MUSIC (multiprocessor system with intelligent communication), is operational and runs the backpropagation algorithm at a speed of 330 million connection updates per second (continuous weight update) using 32-b floating-point precision. This is equal to 1.4 Gflops sustained performance. The complete system with 3.8 Gflops peak performance consumes less than 800 W of electrical power and fits into a 19-in rack. While reaching the speed of modern supercomputers, MUSIC still can be used as a personal desktop computer at a researcher's own disposal. In neural net simulation, this gives a computing performance to a single user which was unthinkable before. The system's real-time interfaces make it especially useful for embedded applications.

Neural networks with fuzzy Petri nets for modeling a machining process

NASA Astrophysics Data System (ADS)

Hanna, Moheb M.

1998-03-01

The paper presents an intelligent architecture based a feedforward neural network with fuzzy Petri nets for modeling product quality in a CNC machining center. It discusses how the proposed architecture can be used for modeling, monitoring and control a product quality specification such as surface roughness. The surface roughness represents the output quality specification manufactured by a CNC machining center as a result of a milling process. The neural network approach employed the selected input parameters which defined by the machine operator via the CNC code. The fuzzy Petri nets approach utilized the exact input milling parameters, such as spindle speed, feed rate, tool diameter and coolant (off/on), which can be obtained via the machine or sensors system. An aim of the proposed architecture is to model the demanded quality of surface roughness as high, medium or low.

Application of a neural network to simulate analysis in an optimization process

NASA Technical Reports Server (NTRS)

Rogers, James L.; Lamarsh, William J., II

1992-01-01

A new experimental software package called NETS/PROSSS aimed at reducing the computing time required to solve a complex design problem is described. The software combines a neural network for simulating the analysis program with an optimization program. The neural network is applied to approximate results of a finite element analysis program to quickly obtain a near-optimal solution. Results of the NETS/PROSSS optimization process can also be used as an initial design in a normal optimization process and make it possible to converge to an optimum solution with significantly fewer iterations.

Neural net forecasting for geomagnetic activity

NASA Technical Reports Server (NTRS)

Hernandez, J. V.; Tajima, T.; Horton, W.

1993-01-01

We use neural nets to construct nonlinear models to forecast the AL index given solar wind and interplanetary magnetic field (IMF) data. We follow two approaches: (1) the state space reconstruction approach, which is a nonlinear generalization of autoregressive-moving average models (ARMA) and (2) the nonlinear filter approach, which reduces to a moving average model (MA) in the linear limit. The database used here is that of Bargatze et al. (1985).

Adaptive Remote-Sensing Techniques Implementing Swarms of Mobile Agents

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

Asher, R.B.; Cameron, S.M.; Loubriel, G.M.

1998-11-25

In many situations, stand-off remote-sensing and hazard-interdiction techniques over realistic operational areas are often impractical "and difficult to characterize. An alternative approach is to implement an adap- tively deployable array of sensitive agent-specific devices. Our group has been studying the collective be- havior of an autonomous, multi-agent system applied to chedbio detection and related emerging threat applications, The current physics-based models we are using coordinate a sensor array for mukivanate sig- nal optimization and coverage as re,alized by a swarm of robots or mobile vehicles. These intelligent control systems integrate'glob"ally operating decision-making systems and locally cooperative learning neural net- worksmore » to enhance re+-timp operational responses to dynarnical environments examples of which include obstacle avoidance, res~onding to prevailing wind patterns, and overcoming other natural obscurants or in- terferences. Collectively',tkensor nefirons with simple properties, interacting according to basic community rules, can accomplish complex interconnecting functions such as generalization, error correction, pattern recognition, sensor fusion, and localization. Neural nets provide a greater degree of robusmess and fault tolerance than conventional systems in that minor variations or imperfections do not impair performance. The robotic platforms would be equipped with sensor devices that perform opticaI detection of biologicais in combination with multivariate chemical analysis tools based on genetic and neural network algorithms, laser-diode LIDAR analysis, ultra-wideband short-pulsed transmitting and receiving antennas, thermal im- a:ing sensors, and optical Communication technology providing robust data throughput pathways. Mission scenarios under consideration include ground penetrating radar (GPR) for detection of underground struc- tures, airborne systems, and plume migration and mitigation. We will describe our research in these areas anti give a status report on our progress.« less

Neural net diagnostics for VLSI test

NASA Technical Reports Server (NTRS)

Lin, T.; Tseng, H.; Wu, A.; Dogan, N.; Meador, J.

1990-01-01

This paper discusses the application of neural network pattern analysis algorithms to the IC fault diagnosis problem. A fault diagnostic is a decision rule combining what is known about an ideal circuit test response with information about how it is distorted by fabrication variations and measurement noise. The rule is used to detect fault existence in fabricated circuits using real test equipment. Traditional statistical techniques may be used to achieve this goal, but they can employ unrealistic a priori assumptions about measurement data. Our approach to this problem employs an adaptive pattern analysis technique based on feedforward neural networks. During training, a feedforward network automatically captures unknown sample distributions. This is important because distributions arising from the nonlinear effects of process variation can be more complex than is typically assumed. A feedforward network is also able to extract measurement features which contribute significantly to making a correct decision. Traditional feature extraction techniques employ matrix manipulations which can be particularly costly for large measurement vectors. In this paper we discuss a software system which we are developing that uses this approach. We also provide a simple example illustrating the use of the technique for fault detection in an operational amplifier.

A Feasibility Study for Perioperative Ventricular Tachycardia Prognosis and Detection and Noise Detection Using a Neural Network and Predictive Linear Operators

NASA Technical Reports Server (NTRS)

Moebes, T. A.

1994-01-01

To locate the accessory pathway(s) in preexicitation syndromes, epicardial and endocardial ventricular mapping is performed during anterograde ventricular activation via accessory pathway(s) from data originally received in signal form. As the number of channels increases, it is pertinent that more automated detection of coherent/incoherent signals is achieved as well as the prediction and prognosis of ventricular tachywardia (VT). Today's computers and computer program algorithms are not good in simple perceptual tasks such as recognizing a pattern or identifying a sound. This discrepancy, among other things, has been a major motivating factor in developing brain-based, massively parallel computing architectures. Neural net paradigms have proven to be effective at pattern recognition tasks. In signal processing, the picking of coherent/incoherent signals represents a pattern recognition task for computer systems. The picking of signals representing the onset ot VT also represents such a computer task. We attacked this problem by defining four signal attributes for each potential first maximal arrival peak and one signal attribute over the entire signal as input to a back propagation neural network. One attribute was the predicted amplitude value after the maximum amplitude over a data window. Then, by using a set of known (user selected) coherent/incoherent signals, and signals representing the onset of VT, we trained the back propagation network to recognize coherent/incoherent signals, and signals indicating the onset of VT. Since our output scheme involves a true or false decision, and since the output unit computes values between 0 and 1, we used a Fuzzy Arithmetic approach to classify data as coherent/incoherent signals. Furthermore, a Mean-Square Error Analysis was used to determine system stability. The neural net based picking coherent/incoherent signal system achieved high accuracy on picking coherent/incoherent signals on different patients. The system also achieved a high accuracy of picking signals which represent the onset of VT, that is, VT immediately followed these signals. A special binary representation of the input and output data allowed the neural network to train very rapidly as compared to another standard decimal or normalized representations of the data.

BrainNetCNN: Convolutional neural networks for brain networks; towards predicting neurodevelopment.

PubMed

Kawahara, Jeremy; Brown, Colin J; Miller, Steven P; Booth, Brian G; Chau, Vann; Grunau, Ruth E; Zwicker, Jill G; Hamarneh, Ghassan

2017-02-01

We propose BrainNetCNN, a convolutional neural network (CNN) framework to predict clinical neurodevelopmental outcomes from brain networks. In contrast to the spatially local convolutions done in traditional image-based CNNs, our BrainNetCNN is composed of novel edge-to-edge, edge-to-node and node-to-graph convolutional filters that leverage the topological locality of structural brain networks. We apply the BrainNetCNN framework to predict cognitive and motor developmental outcome scores from structural brain networks of infants born preterm. Diffusion tensor images (DTI) of preterm infants, acquired between 27 and 46 weeks gestational age, were used to construct a dataset of structural brain connectivity networks. We first demonstrate the predictive capabilities of BrainNetCNN on synthetic phantom networks with simulated injury patterns and added noise. BrainNetCNN outperforms a fully connected neural-network with the same number of model parameters on both phantoms with focal and diffuse injury patterns. We then apply our method to the task of joint prediction of Bayley-III cognitive and motor scores, assessed at 18 months of age, adjusted for prematurity. We show that our BrainNetCNN framework outperforms a variety of other methods on the same data. Furthermore, BrainNetCNN is able to identify an infant's postmenstrual age to within about 2 weeks. Finally, we explore the high-level features learned by BrainNetCNN by visualizing the importance of each connection in the brain with respect to predicting the outcome scores. These findings are then discussed in the context of the anatomy and function of the developing preterm infant brain. Copyright © 2016 Elsevier Inc. All rights reserved.

Landslide susceptibility assesssment in the Uttarakhand area (India) using GIS: a comparison study of prediction capability of naïve bayes, multilayer perceptron neural networks, and functional trees methods

NASA Astrophysics Data System (ADS)

Pham, Binh Thai; Tien Bui, Dieu; Pourghasemi, Hamid Reza; Indra, Prakash; Dholakia, M. B.

2017-04-01

The objective of this study is to make a comparison of the prediction performance of three techniques, Functional Trees (FT), Multilayer Perceptron Neural Networks (MLP Neural Nets), and Naïve Bayes (NB) for landslide susceptibility assessment at the Uttarakhand Area (India). Firstly, a landslide inventory map with 430 landslide locations in the study area was constructed from various sources. Landslide locations were then randomly split into two parts (i) 70 % landslide locations being used for training models (ii) 30 % landslide locations being employed for validation process. Secondly, a total of eleven landslide conditioning factors including slope angle, slope aspect, elevation, curvature, lithology, soil, land cover, distance to roads, distance to lineaments, distance to rivers, and rainfall were used in the analysis to elucidate the spatial relationship between these factors and landslide occurrences. Feature selection of Linear Support Vector Machine (LSVM) algorithm was employed to assess the prediction capability of these conditioning factors on landslide models. Subsequently, the NB, MLP Neural Nets, and FT models were constructed using training dataset. Finally, success rate and predictive rate curves were employed to validate and compare the predictive capability of three used models. Overall, all the three models performed very well for landslide susceptibility assessment. Out of these models, the MLP Neural Nets and the FT models had almost the same predictive capability whereas the MLP Neural Nets (AUC = 0.850) was slightly better than the FT model (AUC = 0.849). The NB model (AUC = 0.838) had the lowest predictive capability compared to other models. Landslide susceptibility maps were final developed using these three models. These maps would be helpful to planners and engineers for the development activities and land-use planning.

Evaluating the performance of two neutron spectrum unfolding codes based on iterative procedures and artificial neural networks

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

Ortiz-Rodriguez, J. M.; Reyes Alfaro, A.; Reyes Haro, A.

In this work the performance of two neutron spectrum unfolding codes based on iterative procedures and artificial neural networks is evaluated. The first one code based on traditional iterative procedures and called Neutron spectrometry and dosimetry from the Universidad Autonoma de Zacatecas (NSDUAZ) use the SPUNIT iterative algorithm and was designed to unfold neutron spectrum and calculate 15 dosimetric quantities and 7 IAEA survey meters. The main feature of this code is the automated selection of the initial guess spectrum trough a compendium of neutron spectrum compiled by the IAEA. The second one code known as Neutron spectrometry and dosimetrymore » with artificial neural networks (NDSann) is a code designed using neural nets technology. The artificial intelligence approach of neural net does not solve mathematical equations. By using the knowledge stored at synaptic weights on a neural net properly trained, the code is capable to unfold neutron spectrum and to simultaneously calculate 15 dosimetric quantities, needing as entrance data, only the rate counts measured with a Bonner spheres system. Similarities of both NSDUAZ and NSDann codes are: they follow the same easy and intuitive user's philosophy and were designed in a graphical interface under the LabVIEW programming environment. Both codes unfold the neutron spectrum expressed in 60 energy bins, calculate 15 dosimetric quantities and generate a full report in HTML format. Differences of these codes are: NSDUAZ code was designed using classical iterative approaches and needs an initial guess spectrum in order to initiate the iterative procedure. In NSDUAZ, a programming routine was designed to calculate 7 IAEA instrument survey meters using the fluence-dose conversion coefficients. NSDann code use artificial neural networks for solving the ill-conditioned equation system of neutron spectrometry problem through synaptic weights of a properly trained neural network. Contrary to iterative procedures, in neural net approach it is possible to reduce the rate counts used to unfold the neutron spectrum. To evaluate these codes a computer tool called Neutron Spectrometry and dosimetry computer tool was designed. The results obtained with this package are showed. The codes here mentioned are freely available upon request to the authors.« less

Evaluating the performance of two neutron spectrum unfolding codes based on iterative procedures and artificial neural networks

NASA Astrophysics Data System (ADS)

Ortiz-Rodríguez, J. M.; Reyes Alfaro, A.; Reyes Haro, A.; Solís Sánches, L. O.; Miranda, R. Castañeda; Cervantes Viramontes, J. M.; Vega-Carrillo, H. R.

2013-07-01

In this work the performance of two neutron spectrum unfolding codes based on iterative procedures and artificial neural networks is evaluated. The first one code based on traditional iterative procedures and called Neutron spectrometry and dosimetry from the Universidad Autonoma de Zacatecas (NSDUAZ) use the SPUNIT iterative algorithm and was designed to unfold neutron spectrum and calculate 15 dosimetric quantities and 7 IAEA survey meters. The main feature of this code is the automated selection of the initial guess spectrum trough a compendium of neutron spectrum compiled by the IAEA. The second one code known as Neutron spectrometry and dosimetry with artificial neural networks (NDSann) is a code designed using neural nets technology. The artificial intelligence approach of neural net does not solve mathematical equations. By using the knowledge stored at synaptic weights on a neural net properly trained, the code is capable to unfold neutron spectrum and to simultaneously calculate 15 dosimetric quantities, needing as entrance data, only the rate counts measured with a Bonner spheres system. Similarities of both NSDUAZ and NSDann codes are: they follow the same easy and intuitive user's philosophy and were designed in a graphical interface under the LabVIEW programming environment. Both codes unfold the neutron spectrum expressed in 60 energy bins, calculate 15 dosimetric quantities and generate a full report in HTML format. Differences of these codes are: NSDUAZ code was designed using classical iterative approaches and needs an initial guess spectrum in order to initiate the iterative procedure. In NSDUAZ, a programming routine was designed to calculate 7 IAEA instrument survey meters using the fluence-dose conversion coefficients. NSDann code use artificial neural networks for solving the ill-conditioned equation system of neutron spectrometry problem through synaptic weights of a properly trained neural network. Contrary to iterative procedures, in neural net approach it is possible to reduce the rate counts used to unfold the neutron spectrum. To evaluate these codes a computer tool called Neutron Spectrometry and dosimetry computer tool was designed. The results obtained with this package are showed. The codes here mentioned are freely available upon request to the authors.

Prediction of Disease Causing Non-Synonymous SNPs by the Artificial Neural Network Predictor NetDiseaseSNP

PubMed Central

Johansen, Morten Bo; Izarzugaza, Jose M. G.; Brunak, Søren; Petersen, Thomas Nordahl; Gupta, Ramneek

2013-01-01

We have developed a sequence conservation-based artificial neural network predictor called NetDiseaseSNP which classifies nsSNPs as disease-causing or neutral. Our method uses the excellent alignment generation algorithm of SIFT to identify related sequences and a combination of 31 features assessing sequence conservation and the predicted surface accessibility to produce a single score which can be used to rank nsSNPs based on their potential to cause disease. NetDiseaseSNP classifies successfully disease-causing and neutral mutations. In addition, we show that NetDiseaseSNP discriminates cancer driver and passenger mutations satisfactorily. Our method outperforms other state-of-the-art methods on several disease/neutral datasets as well as on cancer driver/passenger mutation datasets and can thus be used to pinpoint and prioritize plausible disease candidates among nsSNPs for further investigation. NetDiseaseSNP is publicly available as an online tool as well as a web service: http://www.cbs.dtu.dk/services/NetDiseaseSNP PMID:23935863

Measurement of relative density of tissue using wavelet analysis and neural nets

NASA Astrophysics Data System (ADS)

Suyatinov, Sergey I.; Kolentev, Sergey V.; Buldakova, Tatyana I.

2001-01-01

Development of methods for indirect measurement of substance's consistence and characteristics is highly actual problem of medical diagnostics. Many diseases bring about changes of tissue density or appearances of alien bodies (e.g. stones in kidneys or gallbladders). Propose to use wavelet-analysis and neural nets for indirect measurement of relative density of tissue by images of internal organs. It shall allow to reveal a disease on early stage.

A comparative study of a theoretical neural net model with MEG data from epileptic patients and normal individuals.

PubMed

Kotini, A; Anninos, P; Anastasiadis, A N; Tamiolakis, D

2005-09-07

The aim of this study was to compare a theoretical neural net model with MEG data from epileptic patients and normal individuals. Our experimental study population included 10 epilepsy sufferers and 10 healthy subjects. The recordings were obtained with a one-channel biomagnetometer SQUID in a magnetically shielded room. Using the method of x2-fitting it was found that the MEG amplitudes in epileptic patients and normal subjects had Poisson and Gauss distributions respectively. The Poisson connectivity derived from the theoretical neural model represents the state of epilepsy, whereas the Gauss connectivity represents normal behavior. The MEG data obtained from epileptic areas had higher amplitudes than the MEG from normal regions and were comparable with the theoretical magnetic fields from Poisson and Gauss distributions. Furthermore, the magnetic field derived from the theoretical model had amplitudes in the same order as the recorded MEG from the 20 participants. The approximation of the theoretical neural net model with real MEG data provides information about the structure of the brain function in epileptic and normal states encouraging further studies to be conducted.

TopologyNet: Topology based deep convolutional and multi-task neural networks for biomolecular property predictions

PubMed Central

2017-01-01

Although deep learning approaches have had tremendous success in image, video and audio processing, computer vision, and speech recognition, their applications to three-dimensional (3D) biomolecular structural data sets have been hindered by the geometric and biological complexity. To address this problem we introduce the element-specific persistent homology (ESPH) method. ESPH represents 3D complex geometry by one-dimensional (1D) topological invariants and retains important biological information via a multichannel image-like representation. This representation reveals hidden structure-function relationships in biomolecules. We further integrate ESPH and deep convolutional neural networks to construct a multichannel topological neural network (TopologyNet) for the predictions of protein-ligand binding affinities and protein stability changes upon mutation. To overcome the deep learning limitations from small and noisy training sets, we propose a multi-task multichannel topological convolutional neural network (MM-TCNN). We demonstrate that TopologyNet outperforms the latest methods in the prediction of protein-ligand binding affinities, mutation induced globular protein folding free energy changes, and mutation induced membrane protein folding free energy changes. Availability: weilab.math.msu.edu/TDL/ PMID:28749969

Automation of the NDT diagnostic using neural nets. Application: Inspection of Airbus longitudinal joints during maintenance

NASA Astrophysics Data System (ADS)

Brousset, Christine; Baudrillard, Gilles

A neural network tool was developed to automate the Non Destructive Testing (NDT) of aeronautical structures carried out with the SIAM system. The SIAM system is used to reveal splits in longitudinal metal joints on the Airbus fuselage. The integration of the neural net tool within the SIAM control system is considered possible. The automatic diagnostic should provide the operator with an aid which will permit a greater reliability of maintenance control. The diagnostic performed with this tool would be rapid;: the control of 30,000 rivets on the Airbus fuselage would take approximately 45 minutes.

Application of neural network to remote sensing of soil moisture using theoretical polarimetric backscattering coefficients

NASA Technical Reports Server (NTRS)

Wang, L.; Shin, R. T.; Kong, J. A.; Yueh, S. H.

1993-01-01

This paper investigates the potential application of neural network to inversion of soil moisture using polarimetric remote sensing data. The neural network used for the inversion of soil parameters is multi-layer perceptron trained with the back-propagation algorithm. The training data include the polarimetric backscattering coefficients obtained from theoretical surface scattering models together with an assumed nominal range of soil parameters which are comprised of the soil permittivity and surface roughness parameters. Soil permittivity is calculated from the soil moisture and the assumed soil texture based on an empirical formula at C-, L-, and P-bands. The rough surface parameters for the soil surface, which is described by the Gaussian random process, are the root-mean-square (rms) height and correlation length. For the rough surface scattering, small perturbation method is used for the L-band frequency, and Kirchhoff approximation is used for the C-band frequency to obtain the corresponding backscattering coefficients. During the training, the backscattering coefficients are the inputs to the neural net and the output from the net are compared with the desired soil parameters to adjust the interconnecting weights. The process is repeated for each input-output data entry and then for the entire training data until convergence is reached. After training, the backscattering coefficients are applied to the trained neural net to retrieve the soil parameters which are compared with the desired soil parameters to verify the effectiveness of this technique. Several cases are examined. First, for simplicity, the correlation length and rms height of the soil surface are fixed while soil moisture is varied. Soil moisture obtained using the neural networks with either L-band or C-band backscattering coefficients for the HH and VV polarizations as inputs is in good agreement with the desired soil moisture. The neural net output matches the desired output for the soil moisture range of 16 to 60 percent for the C-band case. The next case investigated is to vary both soil moisture and rms height while keeping the correlation length fixed. For this case, C-band backscattering coefficients are not sufficient for retrieving two parameters because the Kirchhoff approximation gives the same HH and VV backscattering coefficients. Therefore, the backscattering coefficients at two different frequency bands are necessary to find both the soil moisture and rms height. Finally, the neural nets are also applied to simultaneously invert soil moisture, rms height, and correlation length. Overall, the soil moisture retrieved from the neural network agrees very well with the desired soil moisture. This suggests that the neural network shows potential for retrieval of soil parameters from remote sensing data.

Inspection of Space Station Cold Plate Using Visual and Automated Holographic Techniques

NASA Technical Reports Server (NTRS)

Decker, Arthur J.; Melis, Matthew E.; Weiland, Kenneth E.

1999-01-01

Real-time holography has been used to confirm the presence of non-uniformity in the construction of an International Space Station cold plate. Ultrasonic C-scans have previously shown suspected areas of cooling fin disbonds. But both neural-net processed and visual holography did not evidence any progressive permanent changes resulting from 3000 pressurization and relaxation cycles of a Dash 8 cold plate. Neural-net and visual inspections were performed of characteristic patterns generated from electronic time-average holograms of the vibrating cold plate. Normal modes of vibration were excited at very low amplitudes for this purpose, The neural nets were trained to flag very small changes in the mode shapes as encoded in the characteristic patterns. Both the whole cold plate and a zoomed region were inspected. The inspections were conducted before, after, and during pressurization and relaxation cycles of the cold plate. A water-filled cold plate was pressurized to 120 psig (827 kPa) and relaxed for each cycle. Each cycle required 5 seconds. Both the artificial neural networks and the inspectors were unable to detect changes in the mode shapes of the relaxed cold plate. The cold plate was also inspected visually using real-time holography and double-exposure holography. Regions of non-uniformity correlating with the C-scans were apparent, but the interference patterns did not change after 3000 pressurization and relaxation cycles. These tests constituted the first practical application of a neural-net inspection technique developed originally with support from the Director's Discretionary Fund at the Glenn Research Center at Lewis Field.

Applications of artificial neural nets in clinical biomechanics.

PubMed

Schöllhorn, W I

2004-11-01

The purpose of this article is to provide an overview of current applications of artificial neural networks in the area of clinical biomechanics. The body of literature on artificial neural networks grew intractably vast during the last 15 years. Conventional statistical models may present certain limitations that can be overcome by neural networks. Artificial neural networks in general are introduced, some limitations, and some proven benefits are discussed.

Load distribution of articular cartilage from MR-images by neural nets.

PubMed

Seidel, Peter; Hanke, Göran; Gründer, Wilfried

2005-01-01

Artificial neural nets were used to determine the Young's modulus and spatial load distribution in articular cartilage by means of T2-weighted MR imaging. MR images were obtained in vitro (ex vivo?) from the joints of sheep of different ages (3 months, 9 months, 15 months, 1.5 years, 5 years, 5.5 years) and pigs (4 and 6 months) with a Bruker AMX 300 (7 T) spectrometer equipped with a micro-imaging unit. The knee of a 29-year-old male volunteer was studied in vivo under mechanical load using a clinical Siemens Vision MRT (1.5 T). The load of the cartilage is understood as a non-linear image transformation of loaded versus unloaded images. The artificial neural net was used to recognize given reference pixels of the unloaded cartilage within the image of the loaded cartilage. The Young's modulus was calculated from the local strain and the external pressure using the Hooke's law. With this method, the average Young's modulus was obtained in relationship to the biological age of the cartilage. The investigated age interval showed a progressive increase of 0.5 +/- 0.3 MPa per year. These results are consistent with published results. As shown in this pilot study, the method of neural nets allows the visualization of the spatial load distribution within the articular cartilage.

Invariant-feature-based adaptive automatic target recognition in obscured 3D point clouds

NASA Astrophysics Data System (ADS)

Khuon, Timothy; Kershner, Charles; Mattei, Enrico; Alverio, Arnel; Rand, Robert

2014-06-01

Target recognition and classification in a 3D point cloud is a non-trivial process due to the nature of the data collected from a sensor system. The signal can be corrupted by noise from the environment, electronic system, A/D converter, etc. Therefore, an adaptive system with a desired tolerance is required to perform classification and recognition optimally. The feature-based pattern recognition algorithm architecture as described below is particularly devised for solving a single-sensor classification non-parametrically. Feature set is extracted from an input point cloud, normalized, and classifier a neural network classifier. For instance, automatic target recognition in an urban area would require different feature sets from one in a dense foliage area. The figure above (see manuscript) illustrates the architecture of the feature based adaptive signature extraction of 3D point cloud including LIDAR, RADAR, and electro-optical data. This network takes a 3D cluster and classifies it into a specific class. The algorithm is a supervised and adaptive classifier with two modes: the training mode and the performing mode. For the training mode, a number of novel patterns are selected from actual or artificial data. A particular 3D cluster is input to the network as shown above for the decision class output. The network consists of three sequential functional modules. The first module is for feature extraction that extracts the input cluster into a set of singular value features or feature vector. Then the feature vector is input into the feature normalization module to normalize and balance it before being fed to the neural net classifier for the classification. The neural net can be trained by actual or artificial novel data until each trained output reaches the declared output within the defined tolerance. In case new novel data is added after the neural net has been learned, the training is then resumed until the neural net has incrementally learned with the new novel data. The associative memory capability of the neural net enables the incremental learning. The back propagation algorithm or support vector machine can be utilized for the classification and recognition.

Weakly connected neural nets

NASA Technical Reports Server (NTRS)

Zak, Michail

1990-01-01

A new neural network architecture is proposed based upon effects of non-Lipschitzian dynamics. The network is fully connected, but these connections are active only during vanishingly short time periods. The advantages of this architecture are discussed.

Effect of design selection on response surface performance

NASA Technical Reports Server (NTRS)

Carpenter, William C.

1993-01-01

Artificial neural nets and polynomial approximations were used to develop response surfaces for several test problems. Based on the number of functional evaluations required to build the approximations and the number of undetermined parameters associated with the approximations, the performance of the two types of approximations was found to be comparable. A rule of thumb is developed for determining the number of nodes to be used on a hidden layer of an artificial neural net and the number of designs needed to train an approximation is discussed.

Modulated error diffusion CGHs for neural nets

NASA Astrophysics Data System (ADS)

Vermeulen, Pieter J. E.; Casasent, David P.

1990-05-01

New modulated error diffusion CGHs (computer generated holograms) for optical computing are considered. Specific attention is given to their use in optical matrix-vector, associative processor, neural net and optical interconnection architectures. We consider lensless CGH systems (many CGHs use an external Fourier transform (FT) lens), the Fresnel sampling requirements, the effects of finite CGH apertures (sample and hold inputs), dot size correction (for laser recorders), and new applications for this novel encoding method (that devotes attention to quantization noise effects).

Searching for exoplanets using artificial intelligence

NASA Astrophysics Data System (ADS)

Pearson, Kyle A.; Palafox, Leon; Griffith, Caitlin A.

2018-02-01

In the last decade, over a million stars were monitored to detect transiting planets. Manual interpretation of potential exoplanet candidates is labor intensive and subject to human error, the results of which are difficult to quantify. Here we present a new method of detecting exoplanet candidates in large planetary search projects which, unlike current methods uses a neural network. Neural networks, also called "deep learning" or "deep nets" are designed to give a computer perception into a specific problem by training it to recognize patterns. Unlike past transit detection algorithms deep nets learn to recognize planet features instead of relying on hand-coded metrics that humans perceive as the most representative. Our convolutional neural network is capable of detecting Earth-like exoplanets in noisy time-series data with a greater accuracy than a least-squares method. Deep nets are highly generalizable allowing data to be evaluated from different time series after interpolation without compromising performance. As validated by our deep net analysis of Kepler light curves, we detect periodic transits consistent with the true period without any model fitting. Our study indicates that machine learning will facilitate the characterization of exoplanets in future analysis of large astronomy data sets.

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.

Geodemographic segmentation systems for screening health data.

PubMed Central

Openshaw, S; Blake, M

1995-01-01

AIM--To describe how geodemographic segmentation systems might be useful as a quick and easy way of exploring postcoded health databases for potential interesting patterns related to deprivation and other socioeconomic characteristics. DESIGN AND SETTING--This is demonstrated using GB Profiles, a freely available geodemographic classification system developed at Leeds University. It is used here to screen a database of colorectal cancer registrations as a first step in the analysis of that data. RESULTS AND CONCLUSION--Conventional geodemographics is a fairly simple technology and a number of outstanding methodological problems are identified. A solution to some problems is illustrated by using neural net based classifiers and then by reference to a more sophisticated geodemographic approach via a data optimal segmentation technique. Images PMID:8594132

Deep neural nets as a method for quantitative structure-activity relationships.

PubMed

Ma, Junshui; Sheridan, Robert P; Liaw, Andy; Dahl, George E; Svetnik, Vladimir

2015-02-23

Neural networks were widely used for quantitative structure-activity relationships (QSAR) in the 1990s. Because of various practical issues (e.g., slow on large problems, difficult to train, prone to overfitting, etc.), they were superseded by more robust methods like support vector machine (SVM) and random forest (RF), which arose in the early 2000s. The last 10 years has witnessed a revival of neural networks in the machine learning community thanks to new methods for preventing overfitting, more efficient training algorithms, and advancements in computer hardware. In particular, deep neural nets (DNNs), i.e. neural nets with more than one hidden layer, have found great successes in many applications, such as computer vision and natural language processing. Here we show that DNNs can routinely make better prospective predictions than RF on a set of large diverse QSAR data sets that are taken from Merck's drug discovery effort. The number of adjustable parameters needed for DNNs is fairly large, but our results show that it is not necessary to optimize them for individual data sets, and a single set of recommended parameters can achieve better performance than RF for most of the data sets we studied. The usefulness of the parameters is demonstrated on additional data sets not used in the calibration. Although training DNNs is still computationally intensive, using graphical processing units (GPUs) can make this issue manageable.

Bilinear Convolutional Neural Networks for Fine-grained Visual Recognition.

PubMed

Lin, Tsung-Yu; RoyChowdhury, Aruni; Maji, Subhransu

2017-07-04

We present a simple and effective architecture for fine-grained recognition called Bilinear Convolutional Neural Networks (B-CNNs). These networks represent an image as a pooled outer product of features derived from two CNNs and capture localized feature interactions in a translationally invariant manner. B-CNNs are related to orderless texture representations built on deep features but can be trained in an end-to-end manner. Our most accurate model obtains 84.1%, 79.4%, 84.5% and 91.3% per-image accuracy on the Caltech-UCSD birds [66], NABirds [63], FGVC aircraft [42], and Stanford cars [33] dataset respectively and runs at 30 frames-per-second on a NVIDIA Titan X GPU. We then present a systematic analysis of these networks and show that (1) the bilinear features are highly redundant and can be reduced by an order of magnitude in size without significant loss in accuracy, (2) are also effective for other image classification tasks such as texture and scene recognition, and (3) can be trained from scratch on the ImageNet dataset offering consistent improvements over the baseline architecture. Finally, we present visualizations of these models on various datasets using top activations of neural units and gradient-based inversion techniques. The source code for the complete system is available at http://vis-www.cs.umass.edu/bcnn.

Combining deep residual neural network features with supervised machine learning algorithms to classify diverse food image datasets.

PubMed

McAllister, Patrick; Zheng, Huiru; Bond, Raymond; Moorhead, Anne

2018-04-01

Obesity is increasing worldwide and can cause many chronic conditions such as type-2 diabetes, heart disease, sleep apnea, and some cancers. Monitoring dietary intake through food logging is a key method to maintain a healthy lifestyle to prevent and manage obesity. Computer vision methods have been applied to food logging to automate image classification for monitoring dietary intake. In this work we applied pretrained ResNet-152 and GoogleNet convolutional neural networks (CNNs), initially trained using ImageNet Large Scale Visual Recognition Challenge (ILSVRC) dataset with MatConvNet package, to extract features from food image datasets; Food 5K, Food-11, RawFooT-DB, and Food-101. Deep features were extracted from CNNs and used to train machine learning classifiers including artificial neural network (ANN), support vector machine (SVM), Random Forest, and Naive Bayes. Results show that using ResNet-152 deep features with SVM with RBF kernel can accurately detect food items with 99.4% accuracy using Food-5K validation food image dataset and 98.8% with Food-5K evaluation dataset using ANN, SVM-RBF, and Random Forest classifiers. Trained with ResNet-152 features, ANN can achieve 91.34%, 99.28% when applied to Food-11 and RawFooT-DB food image datasets respectively and SVM with RBF kernel can achieve 64.98% with Food-101 image dataset. From this research it is clear that using deep CNN features can be used efficiently for diverse food item image classification. The work presented in this research shows that pretrained ResNet-152 features provide sufficient generalisation power when applied to a range of food image classification tasks. Copyright © 2018 Elsevier Ltd. All rights reserved.

Neural system modeling and simulation using Hybrid Functional Petri Net.

PubMed

Tang, Yin; Wang, Fei

2012-02-01

The Petri net formalism has been proved to be powerful in biological modeling. It not only boasts of a most intuitive graphical presentation but also combines the methods of classical systems biology with the discrete modeling technique. Hybrid Functional Petri Net (HFPN) was proposed specially for biological system modeling. An array of well-constructed biological models using HFPN yielded very interesting results. In this paper, we propose a method to represent neural system behavior, where biochemistry and electrical chemistry are both included using the Petri net formalism. We built a model for the adrenergic system using HFPN and employed quantitative analysis. Our simulation results match the biological data well, showing that the model is very effective. Predictions made on our model further manifest the modeling power of HFPN and improve the understanding of the adrenergic system. The file of our model and more results with their analysis are available in our supplementary material.

Learning normalized inputs for iterative estimation in medical image segmentation.

PubMed

Drozdzal, Michal; Chartrand, Gabriel; Vorontsov, Eugene; Shakeri, Mahsa; Di Jorio, Lisa; Tang, An; Romero, Adriana; Bengio, Yoshua; Pal, Chris; Kadoury, Samuel

2018-02-01

In this paper, we introduce a simple, yet powerful pipeline for medical image segmentation that combines Fully Convolutional Networks (FCNs) with Fully Convolutional Residual Networks (FC-ResNets). We propose and examine a design that takes particular advantage of recent advances in the understanding of both Convolutional Neural Networks as well as ResNets. Our approach focuses upon the importance of a trainable pre-processing when using FC-ResNets and we show that a low-capacity FCN model can serve as a pre-processor to normalize medical input data. In our image segmentation pipeline, we use FCNs to obtain normalized images, which are then iteratively refined by means of a FC-ResNet to generate a segmentation prediction. As in other fully convolutional approaches, our pipeline can be used off-the-shelf on different image modalities. We show that using this pipeline, we exhibit state-of-the-art performance on the challenging Electron Microscopy benchmark, when compared to other 2D methods. We improve segmentation results on CT images of liver lesions, when contrasting with standard FCN methods. Moreover, when applying our 2D pipeline on a challenging 3D MRI prostate segmentation challenge we reach results that are competitive even when compared to 3D methods. The obtained results illustrate the strong potential and versatility of the pipeline by achieving accurate segmentations on a variety of image modalities and different anatomical regions. Copyright © 2017 Elsevier B.V. All rights reserved.

NetMHCpan-3.0; improved prediction of binding to MHC class I molecules integrating information from multiple receptor and peptide length datasets.

PubMed

Nielsen, Morten; Andreatta, Massimo

2016-03-30

Binding of peptides to MHC class I molecules (MHC-I) is essential for antigen presentation to cytotoxic T-cells. Here, we demonstrate how a simple alignment step allowing insertions and deletions in a pan-specific MHC-I binding machine-learning model enables combining information across both multiple MHC molecules and peptide lengths. This pan-allele/pan-length algorithm significantly outperforms state-of-the-art methods, and captures differences in the length profile of binders to different MHC molecules leading to increased accuracy for ligand identification. Using this model, we demonstrate that percentile ranks in contrast to affinity-based thresholds are optimal for ligand identification due to uniform sampling of the MHC space. We have developed a neural network-based machine-learning algorithm leveraging information across multiple receptor specificities and ligand length scales, and demonstrated how this approach significantly improves the accuracy for prediction of peptide binding and identification of MHC ligands. The method is available at www.cbs.dtu.dk/services/NetMHCpan-3.0 .

Neural network error correction for solving coupled ordinary differential equations

NASA Technical Reports Server (NTRS)

Shelton, R. O.; Darsey, J. A.; Sumpter, B. G.; Noid, D. W.

1992-01-01

A neural network is presented to learn errors generated by a numerical algorithm for solving coupled nonlinear differential equations. The method is based on using a neural network to correctly learn the error generated by, for example, Runge-Kutta on a model molecular dynamics (MD) problem. The neural network programs used in this study were developed by NASA. Comparisons are made for training the neural network using backpropagation and a new method which was found to converge with fewer iterations. The neural net programs, the MD model and the calculations are discussed.

Predicting lettuce canopy photosynthesis with statistical and neural network models

NASA Technical Reports Server (NTRS)

Frick, J.; Precetti, C.; Mitchell, C. A.

1998-01-01

An artificial neural network (NN) and a statistical regression model were developed to predict canopy photosynthetic rates (Pn) for 'Waldman's Green' leaf lettuce (Latuca sativa L.). All data used to develop and test the models were collected for crop stands grown hydroponically and under controlled-environment conditions. In the NN and regression models, canopy Pn was predicted as a function of three independent variables: shootzone CO2 concentration (600 to 1500 micromoles mol-1), photosynthetic photon flux (PPF) (600 to 1100 micromoles m-2 s-1), and canopy age (10 to 20 days after planting). The models were used to determine the combinations of CO2 and PPF setpoints required each day to maintain maximum canopy Pn. The statistical model (a third-order polynomial) predicted Pn more accurately than the simple NN (a three-layer, fully connected net). Over an 11-day validation period, average percent difference between predicted and actual Pn was 12.3% and 24.6% for the statistical and NN models, respectively. Both models lost considerable accuracy when used to determine relatively long-range Pn predictions (> or = 6 days into the future).

The Basis of Hyperspecificity in Autism: A Preliminary Suggestion Based on Properties of Neural Nets.

ERIC Educational Resources Information Center

McClelland, James L.

2000-01-01

This article discusses representation of information in neural networks and the apparent hyperspecificity that is often seen in the application of previously acquired information by children with autism. Hyperspecificity is seen as reflecting a possible feature of the neural codes used to represent concepts in the autistic brain. (Contains 12…

LiteNet: Lightweight Neural Network for Detecting Arrhythmias at Resource-Constrained Mobile Devices.

PubMed

He, Ziyang; Zhang, Xiaoqing; Cao, Yangjie; Liu, Zhi; Zhang, Bo; Wang, Xiaoyan

2018-04-17

By running applications and services closer to the user, edge processing provides many advantages, such as short response time and reduced network traffic. Deep-learning based algorithms provide significantly better performances than traditional algorithms in many fields but demand more resources, such as higher computational power and more memory. Hence, designing deep learning algorithms that are more suitable for resource-constrained mobile devices is vital. In this paper, we build a lightweight neural network, termed LiteNet which uses a deep learning algorithm design to diagnose arrhythmias, as an example to show how we design deep learning schemes for resource-constrained mobile devices. Compare to other deep learning models with an equivalent accuracy, LiteNet has several advantages. It requires less memory, incurs lower computational cost, and is more feasible for deployment on resource-constrained mobile devices. It can be trained faster than other neural network algorithms and requires less communication across different processing units during distributed training. It uses filters of heterogeneous size in a convolutional layer, which contributes to the generation of various feature maps. The algorithm was tested using the MIT-BIH electrocardiogram (ECG) arrhythmia database; the results showed that LiteNet outperforms comparable schemes in diagnosing arrhythmias, and in its feasibility for use at the mobile devices.

LiteNet: Lightweight Neural Network for Detecting Arrhythmias at Resource-Constrained Mobile Devices

PubMed Central

Zhang, Xiaoqing; Cao, Yangjie; Liu, Zhi; Zhang, Bo; Wang, Xiaoyan

2018-01-01

By running applications and services closer to the user, edge processing provides many advantages, such as short response time and reduced network traffic. Deep-learning based algorithms provide significantly better performances than traditional algorithms in many fields but demand more resources, such as higher computational power and more memory. Hence, designing deep learning algorithms that are more suitable for resource-constrained mobile devices is vital. In this paper, we build a lightweight neural network, termed LiteNet which uses a deep learning algorithm design to diagnose arrhythmias, as an example to show how we design deep learning schemes for resource-constrained mobile devices. Compare to other deep learning models with an equivalent accuracy, LiteNet has several advantages. It requires less memory, incurs lower computational cost, and is more feasible for deployment on resource-constrained mobile devices. It can be trained faster than other neural network algorithms and requires less communication across different processing units during distributed training. It uses filters of heterogeneous size in a convolutional layer, which contributes to the generation of various feature maps. The algorithm was tested using the MIT-BIH electrocardiogram (ECG) arrhythmia database; the results showed that LiteNet outperforms comparable schemes in diagnosing arrhythmias, and in its feasibility for use at the mobile devices. PMID:29673171

Multispectral confocal microscopy images and artificial neural nets to monitor the photosensitizer uptake and degradation in Candida albicans cells

NASA Astrophysics Data System (ADS)

Romano, Renan A.; Pratavieira, Sebastião.; da Silva, Ana P.; Kurachi, Cristina; Guimarães, Francisco E. G.

2017-07-01

This study clearly demonstrates that multispectral confocal microscopy images analyzed by artificial neural networks provides a powerful tool to real-time monitoring photosensitizer uptake, as well as photochemical transformations occurred.

Modulation of Perineuronal Nets and Parvalbumin with Developmental Song Learning

PubMed Central

Balmer, Timothy S.; Carels, Vanessa M.; Frisch, Jillian L.; Nick, Teresa A.

2009-01-01

Neural circuits and behavior are shaped during developmental phases of maximal plasticity known as sensitive or critical periods. Neural correlates of sensory critical periods have been identified, but their roles remain unclear. Factors that define critical periods in sensorimotor circuits and behavior are not known. Birdsong learning in the zebra finch occurs during a sensitive period similar to that for human speech. We now show that perineuronal nets, which correlate with sensory critical periods, surround parvalbumin-positive neurons in brain areas that are dedicated to singing. The percentage of both total and parvalbumin-positive neurons with perineuronal nets increased with development. In HVC (this acronym is the proper name), a song area important for sensorimotor integration, the percentage of parvalbumin neurons with perineuronal nets correlated with song maturity. Shifting the vocal critical period with tutor song deprivation decreased the percentage of neurons that were parvalbumin positive and the relative staining intensity of both parvalbumin and a component of perineuronal nets. Developmental song learning shares key characteristics with sensory critical periods, suggesting shared underlying mechanisms. PMID:19828802

Using Neural Net Technology To Enhance the Efficiency of a Computer Adaptive Testing Application.

ERIC Educational Resources Information Center

Van Nelson, C.; Henriksen, Larry W.

The potential for computer adaptive testing (CAT) has been well documented. In order to improve the efficiency of this process, it may be possible to utilize a neural network, or more specifically, a back propagation neural network. The paper asserts that in order to accomplish this end, it must be shown that grouping examinees by ability as…

On Improved Least Squares Regression and Artificial Neural Network Meta-Models for Simulation via Control Variates

DTIC Science & Technology

2016-09-15

18] under the context of robust parameter design for simulation. Bellucci’s technique is used in this research, primarily because the interior -point...Fundamentals of Radial Basis Neural Network (RBNN) . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 28 1.2.2.2 Design of Experiments...with Neural Nets . . . . . . . . . . . . . 31 1.2.2.3 Factorial Design . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 32 1.2.2.4

Improving the Unsteady Aerodynamic Performance of Transonic Turbines using Neural Networks

NASA Technical Reports Server (NTRS)

Rai, Man Mohan; Madavan, Nateri K.; Huber, Frank W.

1999-01-01

A recently developed neural net-based aerodynamic design procedure is used in the redesign of a transonic turbine stage to improve its unsteady aerodynamic performance. The redesign procedure used incorporates the advantages of both traditional response surface methodology and neural networks by employing a strategy called parameter-based partitioning of the design space. Starting from the reference design, a sequence of response surfaces based on both neural networks and polynomial fits are constructed to traverse the design space in search of an optimal solution that exhibits improved unsteady performance. The procedure combines the power of neural networks and the economy of low-order polynomials (in terms of number of simulations required and network training requirements). A time-accurate, two-dimensional, Navier-Stokes solver is used to evaluate the various intermediate designs and provide inputs to the optimization procedure. The procedure yielded a modified design that improves the aerodynamic performance through small changes to the reference design geometry. These results demonstrate the capabilities of the neural net-based design procedure, and also show the advantages of including high-fidelity unsteady simulations that capture the relevant flow physics in the design optimization process.

Optical neural network system for pose determination of spinning satellites

NASA Technical Reports Server (NTRS)

Lee, Andrew; Casasent, David

1990-01-01

An optical neural network architecture and algorithm based on a Hopfield optimization network are presented for multitarget tracking. This tracker utilizes a neuron for every possible target track, and a quadratic energy function of neural activities which is minimized using gradient descent neural evolution. The neural net tracker is demonstrated as part of a system for determining position and orientation (pose) of spinning satellites with respect to a robotic spacecraft. The input to the system is time sequence video from a single camera. Novelty detection and filtering are utilized to locate and segment novel regions from the input images. The neural net multitarget tracker determines the correspondences (or tracks) of the novel regions as a function of time, and hence the paths of object (satellite) parts. The path traced out by a given part or region is approximately elliptical in image space, and the position, shape and orientation of the ellipse are functions of the satellite geometry and its pose. Having a geometric model of the satellite, and the elliptical path of a part in image space, the three-dimensional pose of the satellite is determined. Digital simulation results using this algorithm are presented for various satellite poses and lighting conditions.

Devices and circuits for nanoelectronic implementation of artificial neural networks

NASA Astrophysics Data System (ADS)

Turel, Ozgur

Biological neural networks perform complicated information processing tasks at speeds better than conventional computers based on conventional algorithms. This has inspired researchers to look into the way these networks function, and propose artificial networks that mimic their behavior. Unfortunately, most artificial neural networks, either software or hardware, do not provide either the speed or the complexity of a human brain. Nanoelectronics, with high density and low power dissipation that it provides, may be used in developing more efficient artificial neural networks. This work consists of two major contributions in this direction. First is the proposal of the CMOL concept, hybrid CMOS-molecular hardware [1-8]. CMOL may circumvent most of the problems in posed by molecular devices, such as low yield, vet provide high active device density, ˜1012/cm 2. The second contribution is CrossNets, artificial neural networks that are based on CMOL. We showed that CrossNets, with their fault tolerance, exceptional speed (˜ 4 to 6 orders of magnitude faster than biological neural networks) can perform any task any artificial neural network can perform. Moreover, there is a hope that if their integration scale is increased to that of human cerebral cortex (˜ 1010 neurons and ˜ 1014 synapses), they may be capable of performing more advanced tasks.

Ultraflexible nanoelectronic probes form reliable, glial scar–free neural integration

PubMed Central

Luan, Lan; Wei, Xiaoling; Zhao, Zhengtuo; Siegel, Jennifer J.; Potnis, Ojas; Tuppen, Catherine A; Lin, Shengqing; Kazmi, Shams; Fowler, Robert A.; Holloway, Stewart; Dunn, Andrew K.; Chitwood, Raymond A.; Xie, Chong

2017-01-01

Implanted brain electrodes construct the only means to electrically interface with individual neurons in vivo, but their recording efficacy and biocompatibility pose limitations on scientific and clinical applications. We showed that nanoelectronic thread (NET) electrodes with subcellular dimensions, ultraflexibility, and cellular surgical footprints form reliable, glial scar–free neural integration. We demonstrated that NET electrodes reliably detected and tracked individual units for months; their impedance, noise level, single-unit recording yield, and the signal amplitude remained stable during long-term implantation. In vivo two-photon imaging and postmortem histological analysis revealed seamless, subcellular integration of NET probes with the local cellular and vasculature networks, featuring fully recovered capillaries with an intact blood-brain barrier and complete absence of chronic neuronal degradation and glial scar. PMID:28246640

Radio frequency interference mitigation using deep convolutional neural networks

NASA Astrophysics Data System (ADS)

Akeret, J.; Chang, C.; Lucchi, A.; Refregier, A.

2017-01-01

We propose a novel approach for mitigating radio frequency interference (RFI) signals in radio data using the latest advances in deep learning. We employ a special type of Convolutional Neural Network, the U-Net, that enables the classification of clean signal and RFI signatures in 2D time-ordered data acquired from a radio telescope. We train and assess the performance of this network using the HIDE &SEEK radio data simulation and processing packages, as well as early Science Verification data acquired with the 7m single-dish telescope at the Bleien Observatory. We find that our U-Net implementation is showing competitive accuracy to classical RFI mitigation algorithms such as SEEK's SUMTHRESHOLD implementation. We publish our U-Net software package on GitHub under GPLv3 license.

How Deep Neural Networks Can Improve Emotion Recognition on Video Data

DTIC Science & Technology

2016-09-25

HOW DEEP NEURAL NETWORKS CAN IMPROVE EMOTION RECOGNITION ON VIDEO DATA Pooya Khorrami1 , Tom Le Paine1, Kevin Brady2, Charlie Dagli2, Thomas S...this work, we present a system that per- forms emotion recognition on video data using both con- volutional neural networks (CNNs) and recurrent...neural net- works (RNNs). We present our findings on videos from the Audio/Visual+Emotion Challenge (AV+EC2015). In our experiments, we analyze the effects

A neutron spectrum unfolding code based on generalized regression artificial neural networks.

PubMed

Del Rosario Martinez-Blanco, Ma; Ornelas-Vargas, Gerardo; Castañeda-Miranda, Celina Lizeth; Solís-Sánchez, Luis Octavio; Castañeda-Miranada, Rodrigo; Vega-Carrillo, Héctor René; Celaya-Padilla, Jose M; Garza-Veloz, Idalia; Martínez-Fierro, Margarita; Ortiz-Rodríguez, José Manuel

2016-11-01

The most delicate part of neutron spectrometry, is the unfolding process. The derivation of the spectral information is not simple because the unknown is not given directly as a result of the measurements. Novel methods based on Artificial Neural Networks have been widely investigated. In prior works, back propagation neural networks (BPNN) have been used to solve the neutron spectrometry problem, however, some drawbacks still exist using this kind of neural nets, i.e. the optimum selection of the network topology and the long training time. Compared to BPNN, it's usually much faster to train a generalized regression neural network (GRNN). That's mainly because spread constant is the only parameter used in GRNN. Another feature is that the network will converge to a global minimum, provided that the optimal values of spread has been determined and that the dataset adequately represents the problem space. In addition, GRNN are often more accurate than BPNN in the prediction. These characteristics make GRNNs to be of great interest in the neutron spectrometry domain. This work presents a computational tool based on GRNN capable to solve the neutron spectrometry problem. This computational code, automates the pre-processing, training and testing stages using a k-fold cross validation of 3 folds, the statistical analysis and the post-processing of the information, using 7 Bonner spheres rate counts as only entrance data. The code was designed for a Bonner Spheres System based on a 6 LiI(Eu) neutron detector and a response matrix expressed in 60 energy bins taken from an International Atomic Energy Agency compilation. Copyright © 2016 Elsevier Ltd. All rights reserved.

Case-based explanation of non-case-based learning methods.

PubMed Central

Caruana, R.; Kangarloo, H.; Dionisio, J. D.; Sinha, U.; Johnson, D.

1999-01-01

We show how to generate case-based explanations for non-case-based learning methods such as artificial neural nets or decision trees. The method uses the trained model (e.g., the neural net or the decision tree) as a distance metric to determine which cases in the training set are most similar to the case that needs to be explained. This approach is well suited to medical domains, where it is important to understand predictions made by complex machine learning models, and where training and clinical practice makes users adept at case interpretation. PMID:10566351

Neural networks as a control methodology

NASA Technical Reports Server (NTRS)

Mccullough, Claire L.

1990-01-01

While conventional computers must be programmed in a logical fashion by a person who thoroughly understands the task to be performed, the motivation behind neural networks is to develop machines which can train themselves to perform tasks, using available information about desired system behavior and learning from experience. There are three goals of this fellowship program: (1) to evaluate various neural net methods and generate computer software to implement those deemed most promising on a personal computer equipped with Matlab; (2) to evaluate methods currently in the professional literature for system control using neural nets to choose those most applicable to control of flexible structures; and (3) to apply the control strategies chosen in (2) to a computer simulation of a test article, the Control Structures Interaction Suitcase Demonstrator, which is a portable system consisting of a small flexible beam driven by a torque motor and mounted on springs tuned to the first flexible mode of the beam. Results of each are discussed.

International Neural Network Society Annual Meeting (1994) Held in San Diego, California on 5-9 June 1994. Volume 3.

DTIC Science & Technology

1994-06-09

Competitive Neural Nets Speed Complex Fluid Flow Calculations 1-366 T. Long, E. Hanzevack Neural Networks for Steam Boiler MIMO Modeling and Advisory Control...Gallinr The Cochlear Nucleus and Primary Cortex as a Sequence of Distributed Neural Filters in Phoneme IV-607 Perception J. Antrobus, C. Tarshish, S...propulsion linear model, a fuel flow actuator modelled as a linear second order system with position and rate limits, and a thrust vectoring actuator

Theory of cortical function

PubMed Central

Heeger, David J.

2017-01-01

Most models of sensory processing in the brain have a feedforward architecture in which each stage comprises simple linear filtering operations and nonlinearities. Models of this form have been used to explain a wide range of neurophysiological and psychophysical data, and many recent successes in artificial intelligence (with deep convolutional neural nets) are based on this architecture. However, neocortex is not a feedforward architecture. This paper proposes a first step toward an alternative computational framework in which neural activity in each brain area depends on a combination of feedforward drive (bottom-up from the previous processing stage), feedback drive (top-down context from the next stage), and prior drive (expectation). The relative contributions of feedforward drive, feedback drive, and prior drive are controlled by a handful of state parameters, which I hypothesize correspond to neuromodulators and oscillatory activity. In some states, neural responses are dominated by the feedforward drive and the theory is identical to a conventional feedforward model, thereby preserving all of the desirable features of those models. In other states, the theory is a generative model that constructs a sensory representation from an abstract representation, like memory recall. In still other states, the theory combines prior expectation with sensory input, explores different possible perceptual interpretations of ambiguous sensory inputs, and predicts forward in time. The theory, therefore, offers an empirically testable framework for understanding how the cortex accomplishes inference, exploration, and prediction. PMID:28167793

Deep learning with convolutional neural networks for EEG decoding and visualization

PubMed Central

Springenberg, Jost Tobias; Fiederer, Lukas Dominique Josef; Glasstetter, Martin; Eggensperger, Katharina; Tangermann, Michael; Hutter, Frank; Burgard, Wolfram; Ball, Tonio

2017-01-01

Abstract Deep learning with convolutional neural networks (deep ConvNets) has revolutionized computer vision through end‐to‐end learning, that is, learning from the raw data. There is increasing interest in using deep ConvNets for end‐to‐end EEG analysis, but a better understanding of how to design and train ConvNets for end‐to‐end EEG decoding and how to visualize the informative EEG features the ConvNets learn is still needed. Here, we studied deep ConvNets with a range of different architectures, designed for decoding imagined or executed tasks from raw EEG. Our results show that recent advances from the machine learning field, including batch normalization and exponential linear units, together with a cropped training strategy, boosted the deep ConvNets decoding performance, reaching at least as good performance as the widely used filter bank common spatial patterns (FBCSP) algorithm (mean decoding accuracies 82.1% FBCSP, 84.0% deep ConvNets). While FBCSP is designed to use spectral power modulations, the features used by ConvNets are not fixed a priori. Our novel methods for visualizing the learned features demonstrated that ConvNets indeed learned to use spectral power modulations in the alpha, beta, and high gamma frequencies, and proved useful for spatially mapping the learned features by revealing the topography of the causal contributions of features in different frequency bands to the decoding decision. Our study thus shows how to design and train ConvNets to decode task‐related information from the raw EEG without handcrafted features and highlights the potential of deep ConvNets combined with advanced visualization techniques for EEG‐based brain mapping. Hum Brain Mapp 38:5391–5420, 2017. © 2017 Wiley Periodicals, Inc. PMID:28782865

Deep learning with convolutional neural networks for EEG decoding and visualization.

PubMed

Schirrmeister, Robin Tibor; Springenberg, Jost Tobias; Fiederer, Lukas Dominique Josef; Glasstetter, Martin; Eggensperger, Katharina; Tangermann, Michael; Hutter, Frank; Burgard, Wolfram; Ball, Tonio

2017-11-01

Deep learning with convolutional neural networks (deep ConvNets) has revolutionized computer vision through end-to-end learning, that is, learning from the raw data. There is increasing interest in using deep ConvNets for end-to-end EEG analysis, but a better understanding of how to design and train ConvNets for end-to-end EEG decoding and how to visualize the informative EEG features the ConvNets learn is still needed. Here, we studied deep ConvNets with a range of different architectures, designed for decoding imagined or executed tasks from raw EEG. Our results show that recent advances from the machine learning field, including batch normalization and exponential linear units, together with a cropped training strategy, boosted the deep ConvNets decoding performance, reaching at least as good performance as the widely used filter bank common spatial patterns (FBCSP) algorithm (mean decoding accuracies 82.1% FBCSP, 84.0% deep ConvNets). While FBCSP is designed to use spectral power modulations, the features used by ConvNets are not fixed a priori. Our novel methods for visualizing the learned features demonstrated that ConvNets indeed learned to use spectral power modulations in the alpha, beta, and high gamma frequencies, and proved useful for spatially mapping the learned features by revealing the topography of the causal contributions of features in different frequency bands to the decoding decision. Our study thus shows how to design and train ConvNets to decode task-related information from the raw EEG without handcrafted features and highlights the potential of deep ConvNets combined with advanced visualization techniques for EEG-based brain mapping. Hum Brain Mapp 38:5391-5420, 2017. © 2017 Wiley Periodicals, Inc. © 2017 The Authors Human Brain Mapping Published by Wiley Periodicals, Inc.

KIKI-net: cross-domain convolutional neural networks for reconstructing undersampled magnetic resonance images.

PubMed

Eo, Taejoon; Jun, Yohan; Kim, Taeseong; Jang, Jinseong; Lee, Ho-Joon; Hwang, Dosik

2018-04-06

To demonstrate accurate MR image reconstruction from undersampled k-space data using cross-domain convolutional neural networks (CNNs) METHODS: Cross-domain CNNs consist of 3 components: (1) a deep CNN operating on the k-space (KCNN), (2) a deep CNN operating on an image domain (ICNN), and (3) an interleaved data consistency operations. These components are alternately applied, and each CNN is trained to minimize the loss between the reconstructed and corresponding fully sampled k-spaces. The final reconstructed image is obtained by forward-propagating the undersampled k-space data through the entire network. Performances of K-net (KCNN with inverse Fourier transform), I-net (ICNN with interleaved data consistency), and various combinations of the 2 different networks were tested. The test results indicated that K-net and I-net have different advantages/disadvantages in terms of tissue-structure restoration. Consequently, the combination of K-net and I-net is superior to single-domain CNNs. Three MR data sets, the T 2 fluid-attenuated inversion recovery (T 2 FLAIR) set from the Alzheimer's Disease Neuroimaging Initiative and 2 data sets acquired at our local institute (T 2 FLAIR and T 1 weighted), were used to evaluate the performance of 7 conventional reconstruction algorithms and the proposed cross-domain CNNs, which hereafter is referred to as KIKI-net. KIKI-net outperforms conventional algorithms with mean improvements of 2.29 dB in peak SNR and 0.031 in structure similarity. KIKI-net exhibits superior performance over state-of-the-art conventional algorithms in terms of restoring tissue structures and removing aliasing artifacts. The results demonstrate that KIKI-net is applicable up to a reduction factor of 3 to 4 based on variable-density Cartesian undersampling. © 2018 International Society for Magnetic Resonance in Medicine.

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.

An application of deep learning in the analysis of stellar spectra

NASA Astrophysics Data System (ADS)

Fabbro, S.; Venn, K. A.; O'Briain, T.; Bialek, S.; Kielty, C. L.; Jahandar, F.; Monty, S.

2018-04-01

Spectroscopic surveys require fast and efficient analysis methods to maximize their scientific impact. Here, we apply a deep neural network architecture to analyse both SDSS-III APOGEE DR13 and synthetic stellar spectra. When our convolutional neural network model (StarNet) is trained on APOGEE spectra, we show that the stellar parameters (temperature, gravity, and metallicity) are determined with similar precision and accuracy as the APOGEE pipeline. StarNet can also predict stellar parameters when trained on synthetic data, with excellent precision and accuracy for both APOGEE data and synthetic data, over a wide range of signal-to-noise ratios. In addition, the statistical uncertainties in the stellar parameter determinations are comparable to the differences between the APOGEE pipeline results and those determined independently from optical spectra. We compare StarNet to other data-driven methods; for example, StarNet and the Cannon 2 show similar behaviour when trained with the same data sets; however, StarNet performs poorly on small training sets like those used by the original Cannon. The influence of the spectral features on the stellar parameters is examined via partial derivatives of the StarNet model results with respect to the input spectra. While StarNet was developed using the APOGEE observed spectra and corresponding ASSET synthetic data, we suggest that this technique is applicable to other wavelength ranges and other spectral surveys.

Automated Pathogenesis-Based Diagnosis of Lumbar Neural Foraminal Stenosis via Deep Multiscale Multitask Learning.

PubMed

Han, Zhongyi; Wei, Benzheng; Leung, Stephanie; Nachum, Ilanit Ben; Laidley, David; Li, Shuo

2018-02-15

Pathogenesis-based diagnosis is a key step to prevent and control lumbar neural foraminal stenosis (LNFS). It conducts both early diagnosis and comprehensive assessment by drawing crucial pathological links between pathogenic factors and LNFS. Automated pathogenesis-based diagnosis would simultaneously localize and grade multiple spinal organs (neural foramina, vertebrae, intervertebral discs) to diagnose LNFS and discover pathogenic factors. The automated way facilitates planning optimal therapeutic schedules and relieving clinicians from laborious workloads. However, no successful work has been achieved yet due to its extreme challenges since 1) multiple targets: each lumbar spine has at least 17 target organs, 2) multiple scales: each type of target organ has structural complexity and various scales across subjects, and 3) multiple tasks, i.e., simultaneous localization and diagnosis of all lumbar organs, are extremely difficult than individual tasks. To address these huge challenges, we propose a deep multiscale multitask learning network (DMML-Net) integrating a multiscale multi-output learning and a multitask regression learning into a fully convolutional network. 1) DMML-Net merges semantic representations to reinforce the salience of numerous target organs. 2) DMML-Net extends multiscale convolutional layers as multiple output layers to boost the scale-invariance for various organs. 3) DMML-Net joins a multitask regression module and a multitask loss module to prompt the mutual benefit between tasks. Extensive experimental results demonstrate that DMML-Net achieves high performance (0.845 mean average precision) on T1/T2-weighted MRI scans from 200 subjects. This endows our method an efficient tool for clinical LNFS diagnosis.

Single-shot T2 mapping using overlapping-echo detachment planar imaging and a deep convolutional neural network.

PubMed

Cai, Congbo; Wang, Chao; Zeng, Yiqing; Cai, Shuhui; Liang, Dong; Wu, Yawen; Chen, Zhong; Ding, Xinghao; Zhong, Jianhui

2018-04-24

An end-to-end deep convolutional neural network (CNN) based on deep residual network (ResNet) was proposed to efficiently reconstruct reliable T 2 mapping from single-shot overlapping-echo detachment (OLED) planar imaging. The training dataset was obtained from simulations that were carried out on SPROM (Simulation with PRoduct Operator Matrix) software developed by our group. The relationship between the original OLED image containing two echo signals and the corresponding T 2 mapping was learned by ResNet training. After the ResNet was trained, it was applied to reconstruct the T 2 mapping from simulation and in vivo human brain data. Although the ResNet was trained entirely on simulated data, the trained network was generalized well to real human brain data. The results from simulation and in vivo human brain experiments show that the proposed method significantly outperforms the echo-detachment-based method. Reliable T 2 mapping with higher accuracy is achieved within 30 ms after the network has been trained, while the echo-detachment-based OLED reconstruction method took approximately 2 min. The proposed method will facilitate real-time dynamic and quantitative MR imaging via OLED sequence, and deep convolutional neural network has the potential to reconstruct maps from complex MRI sequences efficiently. © 2018 International Society for Magnetic Resonance in Medicine.

Ontological function annotation of long non-coding RNAs through hierarchical multi-label classification.

PubMed

Zhang, Jingpu; Zhang, Zuping; Wang, Zixiang; Liu, Yuting; Deng, Lei

2018-05-15

Long non-coding RNAs (lncRNAs) are an enormous collection of functional non-coding RNAs. Over the past decades, a large number of novel lncRNA genes have been identified. However, most of the lncRNAs remain function uncharacterized at present. Computational approaches provide a new insight to understand the potential functional implications of lncRNAs. Considering that each lncRNA may have multiple functions and a function may be further specialized into sub-functions, here we describe NeuraNetL2GO, a computational ontological function prediction approach for lncRNAs using hierarchical multi-label classification strategy based on multiple neural networks. The neural networks are incrementally trained level by level, each performing the prediction of gene ontology (GO) terms belonging to a given level. In NeuraNetL2GO, we use topological features of the lncRNA similarity network as the input of the neural networks and employ the output results to annotate the lncRNAs. We show that NeuraNetL2GO achieves the best performance and the overall advantage in maximum F-measure and coverage on the manually annotated lncRNA2GO-55 dataset compared to other state-of-the-art methods. The source code and data are available at http://denglab.org/NeuraNetL2GO/. leideng@csu.edu.cn. Supplementary data are available at Bioinformatics online.

Program Aids Analysis And Optimization Of Design

NASA Technical Reports Server (NTRS)

Rogers, James L., Jr.; Lamarsh, William J., II

1994-01-01

NETS/ PROSSS (NETS Coupled With Programming System for Structural Synthesis) computer program developed to provide system for combining NETS (MSC-21588), neural-network application program and CONMIN (Constrained Function Minimization, ARC-10836), optimization program. Enables user to reach nearly optimal design. Design then used as starting point in normal optimization process, possibly enabling user to converge to optimal solution in significantly fewer iterations. NEWT/PROSSS written in C language and FORTRAN 77.

Multiview fusion for activity recognition using deep neural networks

NASA Astrophysics Data System (ADS)

Kavi, Rahul; Kulathumani, Vinod; Rohit, Fnu; Kecojevic, Vlad

2016-07-01

Convolutional neural networks (ConvNets) coupled with long short term memory (LSTM) networks have been recently shown to be effective for video classification as they combine the automatic feature extraction capabilities of a neural network with additional memory in the temporal domain. This paper shows how multiview fusion can be applied to such a ConvNet LSTM architecture. Two different fusion techniques are presented. The system is first evaluated in the context of a driver activity recognition system using data collected in a multicamera driving simulator. These results show significant improvement in accuracy with multiview fusion and also show that deep learning performs better than a traditional approach using spatiotemporal features even without requiring any background subtraction. The system is also validated on another publicly available multiview action recognition dataset that has 12 action classes and 8 camera views.

Scaling deep learning workloads: NVIDIA DGX-1/Pascal and Intel Knights Landing

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

Gawande, Nitin A.; Landwehr, Joshua B.; Daily, Jeffrey A.

Deep Learning (DL) algorithms have become ubiquitous in data analytics. As a result, major computing vendors --- including NVIDIA, Intel, AMD, and IBM --- have architectural road-maps influenced by DL workloads. Furthermore, several vendors have recently advertised new computing products as accelerating large DL workloads. Unfortunately, it is difficult for data scientists to quantify the potential of these different products. This paper provides a performance and power analysis of important DL workloads on two major parallel architectures: NVIDIA DGX-1 (eight Pascal P100 GPUs interconnected with NVLink) and Intel Knights Landing (KNL) CPUs interconnected with Intel Omni-Path or Cray Aries. Ourmore » evaluation consists of a cross section of convolutional neural net workloads: CifarNet, AlexNet, GoogLeNet, and ResNet50 topologies using the Cifar10 and ImageNet datasets. The workloads are vendor-optimized for each architecture. Our analysis indicates that although GPUs provide the highest overall performance, the gap can close for some convolutional networks; and the KNL can be competitive in performance/watt. We find that NVLink facilitates scaling efficiency on GPUs. However, its importance is heavily dependent on neural network architecture. Furthermore, for weak-scaling --- sometimes encouraged by restricted GPU memory --- NVLink is less important.« less

Consciousness of Unification: The Mind-Matter Phallacy Bites the Dust

NASA Astrophysics Data System (ADS)

Beichler, James E.

A complete theoretical model of how consciousness arises in neural nets can be developed based on a mixed quantum/classical basis. Both mind and consciousness are multi-leveled scalar and vector electromagnetic complexity patterns, respectively, which emerge within all living organisms through the process of evolution. Like life, the mind and consciousness patterns extend throughout living organisms (bodies), but the neural nets and higher level groupings that distinguish higher levels of consciousness only exist in the brain so mind and consciousness have been traditionally associated with the brain alone. A close study of neurons and neural nets in the brain shows that the microtubules within axons are classical bio-magnetic inductors that emit and absorb electromagnetic pulses from each other. These pulses establish interference patterns that influence the quantized vector potential patterns of interstitial water molecules within the neurons as well as create the coherence within neurons and neural nets that scientists normally associate with more complex memories, thought processes and streams of thought. Memory storage and recall are guided by the microtubules and the actual memory patterns are stored as magnetic vector potential complexity patterns in the points of space at the quantum level occupied by the water molecules. This model also accounts for the plasticity of the brain and implies that mind and consciousness, like life itself, are the result of evolutionary processes. However, consciousness can evolve independent of an organism's birth genetics once it has evolved by normal bottom-up genetic processes and thus force a new type of top-down evolution on living organisms and species as a whole that can be explained by expanding the laws of thermodynamics to include orderly systems.

Detection and diagnosis of colitis on computed tomography using deep convolutional neural networks.

PubMed

Liu, Jiamin; Wang, David; Lu, Le; Wei, Zhuoshi; Kim, Lauren; Turkbey, Evrim B; Sahiner, Berkman; Petrick, Nicholas A; Summers, Ronald M

2017-09-01

Colitis refers to inflammation of the inner lining of the colon that is frequently associated with infection and allergic reactions. In this paper, we propose deep convolutional neural networks methods for lesion-level colitis detection and a support vector machine (SVM) classifier for patient-level colitis diagnosis on routine abdominal CT scans. The recently developed Faster Region-based Convolutional Neural Network (Faster RCNN) is utilized for lesion-level colitis detection. For each 2D slice, rectangular region proposals are generated by region proposal networks (RPN). Then, each region proposal is jointly classified and refined by a softmax classifier and bounding-box regressor. Two convolutional neural networks, eight layers of ZF net and 16 layers of VGG net are compared for colitis detection. Finally, for each patient, the detections on all 2D slices are collected and a SVM classifier is applied to develop a patient-level diagnosis. We trained and evaluated our method with 80 colitis patients and 80 normal cases using 4 × 4-fold cross validation. For lesion-level colitis detection, with ZF net, the mean of average precisions (mAP) were 48.7% and 50.9% for RCNN and Faster RCNN, respectively. The detection system achieved sensitivities of 51.4% and 54.0% at two false positives per patient for RCNN and Faster RCNN, respectively. With VGG net, Faster RCNN increased the mAP to 56.9% and increased the sensitivity to 58.4% at two false positive per patient. For patient-level colitis diagnosis, with ZF net, the average areas under the ROC curve (AUC) were 0.978 ± 0.009 and 0.984 ± 0.008 for RCNN and Faster RCNN method, respectively. The difference was not statistically significant with P = 0.18. At the optimal operating point, the RCNN method correctly identified 90.4% (72.3/80) of the colitis patients and 94.0% (75.2/80) of normal cases. The sensitivity improved to 91.6% (73.3/80) and the specificity improved to 95.0% (76.0/80) for the Faster RCNN method. With VGG net, Faster RCNN increased the AUC to 0.986 ± 0.007 and increased the diagnosis sensitivity to 93.7% (75.0/80) and specificity was unchanged at 95.0% (76.0/80). Colitis detection and diagnosis by deep convolutional neural networks is accurate and promising for future clinical application. Published 2017. This article is a U.S. Government work and is in the public domain in the USA.

Framework for Detection and Localization of Extreme Climate Event with Pixel Recursive Super Resolution

NASA Astrophysics Data System (ADS)

Kim, S. K.; Lee, J.; Zhang, C.; Ames, S.; Williams, D. N.

2017-12-01

Deep learning techniques have been successfully applied to solve many problems in climate and geoscience using massive-scaled observed and modeled data. For extreme climate event detections, several models based on deep neural networks have been recently proposed and attend superior performance that overshadows all previous handcrafted expert based method. The issue arising, though, is that accurate localization of events requires high quality of climate data. In this work, we propose framework capable of detecting and localizing extreme climate events in very coarse climate data. Our framework is based on two models using deep neural networks, (1) Convolutional Neural Networks (CNNs) to detect and localize extreme climate events, and (2) Pixel recursive recursive super resolution model to reconstruct high resolution climate data from low resolution climate data. Based on our preliminary work, we have presented two CNNs in our framework for different purposes, detection and localization. Our results using CNNs for extreme climate events detection shows that simple neural nets can capture the pattern of extreme climate events with high accuracy from very coarse reanalysis data. However, localization accuracy is relatively low due to the coarse resolution. To resolve this issue, the pixel recursive super resolution model reconstructs the resolution of input of localization CNNs. We present a best networks using pixel recursive super resolution model that synthesizes details of tropical cyclone in ground truth data while enhancing their resolution. Therefore, this approach not only dramat- ically reduces the human effort, but also suggests possibility to reduce computing cost required for downscaling process to increase resolution of data.

Pattern recognition neural-net by spatial mapping of biology visual field

NASA Astrophysics Data System (ADS)

Lin, Xin; Mori, Masahiko

2000-05-01

The method of spatial mapping in biology vision field is applied to artificial neural networks for pattern recognition. By the coordinate transform that is called the complex-logarithm mapping and Fourier transform, the input images are transformed into scale- rotation- and shift- invariant patterns, and then fed into a multilayer neural network for learning and recognition. The results of computer simulation and an optical experimental system are described.

Implicity Defined Neural Networks for Sequence Labeling

DTIC Science & Technology

2017-02-13

popularity of the Long Short - Term Memory (LSTM) (Hochreiter and Schmidhuber, 1997) and variants such as the Gated Recurrent Unit (GRU) (Cho et al., 2014...bidirectional lstm and other neural network architectures. Neural Net- works 18(5):602–610. Sepp Hochreiter and Jürgen Schmidhuber. 1997. Long short - term ...hid- den states of the network to coupled together, allowing potential improvement on problems with complex, long -distance dependencies. Initial

Non-Lipschitzian dynamics for neural net modelling

NASA Technical Reports Server (NTRS)

Zak, Michail

1989-01-01

Failure of the Lipschitz condition in unstable equilibrium points of dynamical systems leads to a multiple-choice response to an initial deterministic input. The evolution of such systems is characterized by a special type of unpredictability measured by unbounded Liapunov exponents. Possible relation of these systems to future neural networks is discussed.

Predictive Models of Procedural Human Supervisory Control Behavior

DTIC Science & Technology

2011-01-01

Campbell in Australia and Prof. Axel Schulte in Germany: they say a mind stretched by an idea never goes back to its original size, thank you for...recurrent neural network (RNN). Neural nets have been successfully used in diverse applications such as handwriting recognition (Gader, Mohamed et al

Identification and interpretation of patterns in rocket engine data: Artificial intelligence and neural network approaches

NASA Technical Reports Server (NTRS)

Ali, Moonis; Whitehead, Bruce; Gupta, Uday K.; Ferber, Harry

1995-01-01

This paper describes an expert system which is designed to perform automatic data analysis, identify anomalous events and determine the characteristic features of these events. We have employed both artificial intelligence and neural net approaches in the design of this expert system.

NSDann2BS, a neutron spectrum unfolding code based on neural networks technology and two bonner spheres

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

Ortiz-Rodriguez, J. M.; Reyes Alfaro, A.; Reyes Haro, A.

In this work a neutron spectrum unfolding code, based on artificial intelligence technology is presented. The code called ''Neutron Spectrometry and Dosimetry with Artificial Neural Networks and two Bonner spheres'', (NSDann2BS), was designed in a graphical user interface under the LabVIEW programming environment. The main features of this code are to use an embedded artificial neural network architecture optimized with the ''Robust design of artificial neural networks methodology'' and to use two Bonner spheres as the only piece of information. In order to build the code here presented, once the net topology was optimized and properly trained, knowledge stored atmore » synaptic weights was extracted and using a graphical framework build on the LabVIEW programming environment, the NSDann2BS code was designed. This code is friendly, intuitive and easy to use for the end user. The code is freely available upon request to authors. To demonstrate the use of the neural net embedded in the NSDann2BS code, the rate counts of {sup 252}Cf, {sup 241}AmBe and {sup 239}PuBe neutron sources measured with a Bonner spheres system.« less

NSDann2BS, a neutron spectrum unfolding code based on neural networks technology and two bonner spheres

NASA Astrophysics Data System (ADS)

Ortiz-Rodríguez, J. M.; Reyes Alfaro, A.; Reyes Haro, A.; Solís Sánches, L. O.; Miranda, R. Castañeda; Cervantes Viramontes, J. M.; Vega-Carrillo, H. R.

2013-07-01

In this work a neutron spectrum unfolding code, based on artificial intelligence technology is presented. The code called "Neutron Spectrometry and Dosimetry with Artificial Neural Networks and two Bonner spheres", (NSDann2BS), was designed in a graphical user interface under the LabVIEW programming environment. The main features of this code are to use an embedded artificial neural network architecture optimized with the "Robust design of artificial neural networks methodology" and to use two Bonner spheres as the only piece of information. In order to build the code here presented, once the net topology was optimized and properly trained, knowledge stored at synaptic weights was extracted and using a graphical framework build on the LabVIEW programming environment, the NSDann2BS code was designed. This code is friendly, intuitive and easy to use for the end user. The code is freely available upon request to authors. To demonstrate the use of the neural net embedded in the NSDann2BS code, the rate counts of 252Cf, 241AmBe and 239PuBe neutron sources measured with a Bonner spheres system.

Spurious symptom reduction in fault monitoring

NASA Technical Reports Server (NTRS)

Shontz, William D.; Records, Roger M.; Choi, Jai J.

1993-01-01

Previous work accomplished on NASA's Faultfinder concept suggested that the concept was jeopardized by spurious symptoms generated in the monitoring phase. The purpose of the present research was to investigate methods of reducing the generation of spurious symptoms during in-flight engine monitoring. Two approaches for reducing spurious symptoms were investigated. A knowledge base of rules was constructed to filter known spurious symptoms and a neural net was developed to improve the expectation values used in the monitoring process. Both approaches were effective in reducing spurious symptoms individually. However, the best results were obtained using a hybrid system combining the neural net capability to improve expectation values with the rule-based logic filter.

Evaluation of a deep learning architecture for MR imaging prediction of ATRX in glioma patients

NASA Astrophysics Data System (ADS)

Korfiatis, Panagiotis; Kline, Timothy L.; Erickson, Bradley J.

2018-02-01

Predicting mutation/loss of alpha-thalassemia/mental retardation syndrome X-linked (ATRX) gene utilizing MR imaging is of high importance since it is a predictor of response and prognosis in brain tumors. In this study, we compare a deep neural network approach based on a residual deep neural network (ResNet) architecture and one based on a classical machine learning approach and evaluate their ability in predicting ATRX mutation status without the need for a distinct tumor segmentation step. We found that the ResNet50 (50 layers) architecture, pre trained on ImageNet data was the best performing model, achieving an accuracy of 0.91 for the test set (classification of a slice as no tumor, ATRX mutated, or mutated) in terms of f1 score in a test set of 35 cases. The SVM classifier achieved 0.63 for differentiating the Flair signal abnormality regions from the test patients based on their mutation status. We report a method that alleviates the need for extensive preprocessing and acts as a proof of concept that deep neural network architectures can be used to predict molecular biomarkers from routine medical images.

[Protective role of autotypic contacts under cerebellar neural net injury by toxic doses of NO-generative compounds].

PubMed

Samosudova, N V; Reutov, V P; Larionova, N P; Chaĭlakhian, L M

2005-01-01

In the present work, cerebellar neural net injury was induced by toxic doses of NO-generative compound (NaNO2). A protective role of glial cells was revealed in such conditions. The present results were compared with those of the previous work concerning the action of high concentration glutamate on the frog cerebellum (Samosudova et al., 1996). In both cases we observed the appearance of spiral-like structures--"wrappers)"--involving several rows of transformed glial processes with smaller width and bridges connecting the inner sides of row (autotypic contact). A statistic analysis was made according to both previous and present data. We calculated the number and width of rows, and intervals between bridges depending on experimental conditions. As the injury increased (stimulation in the NO-presence), the row number in "wrappers" also increased, while the row width and intervals between bridges decreased. The presence of autotypic contacts in glial "wrappers" enables us to suppose the involvement of adhesive proteins--cadherins in its formation. The obtained data suggested that the formation of spiral structures--"wrappers" may be regarded as a compensative-adaptive reaction on the injury of cerebellar neural net glutamate and NO-generative compounds.

Classification of breast cancer cytological specimen using convolutional neural network

NASA Astrophysics Data System (ADS)

Żejmo, Michał; Kowal, Marek; Korbicz, Józef; Monczak, Roman

2017-01-01

The paper presents a deep learning approach for automatic classification of breast tumors based on fine needle cytology. The main aim of the system is to distinguish benign from malignant cases based on microscopic images. Experiment was carried out on cytological samples derived from 50 patients (25 benign cases + 25 malignant cases) diagnosed in Regional Hospital in Zielona Góra. To classify microscopic images, we used convolutional neural networks (CNN) of two types: GoogLeNet and AlexNet. Due to the very large size of images of cytological specimen (on average 200000 × 100000 pixels), they were divided into smaller patches of size 256 × 256 pixels. Breast cancer classification usually is based on morphometric features of nuclei. Therefore, training and validation patches were selected using Support Vector Machine (SVM) so that suitable amount of cell material was depicted. Neural classifiers were tuned using GPU accelerated implementation of gradient descent algorithm. Training error was defined as a cross-entropy classification loss. Classification accuracy was defined as the percentage ratio of successfully classified validation patches to the total number of validation patches. The best accuracy rate of 83% was obtained by GoogLeNet model. We observed that more misclassified patches belong to malignant cases.

Optics-Only Calibration of a Neural-Net Based Optical NDE Method for Structural Health Monitoring

NASA Technical Reports Server (NTRS)

Decker, Arthur J.

2004-01-01

A calibration process is presented that uses optical measurements alone to calibrate a neural-net based NDE method. The method itself detects small changes in the vibration mode shapes of structures. The optics-only calibration process confirms previous work that the sensitivity to vibration-amplitude changes can be as small as 10 nanometers. A more practical value in an NDE service laboratory is shown to be 50 nanometers. Both model-generated and experimental calibrations are demonstrated using two implementations of the calibration technique. The implementations are based on previously published demonstrations of the NDE method and an alternative calibration procedure that depends on comparing neural-net and point sensor measurements. The optics-only calibration method, unlike the alternative method, does not require modifications of the structure being tested or the creation of calibration objects. The calibration process can be used to test improvements in the NDE process and to develop a vibration-mode-independence of damagedetection sensitivity. The calibration effort was intended to support NASA s objective to promote safety in the operations of ground test facilities or aviation safety, in general, by allowing the detection of the gradual onset of structural changes and damage.

A neutron spectrum unfolding computer code based on artificial neural networks

NASA Astrophysics Data System (ADS)

Ortiz-Rodríguez, J. M.; Reyes Alfaro, A.; Reyes Haro, A.; Cervantes Viramontes, J. M.; Vega-Carrillo, H. R.

2014-02-01

The Bonner Spheres Spectrometer consists of a thermal neutron sensor placed at the center of a number of moderating polyethylene spheres of different diameters. From the measured readings, information can be derived about the spectrum of the neutron field where measurements were made. Disadvantages of the Bonner system are the weight associated with each sphere and the need to sequentially irradiate the spheres, requiring long exposure periods. Provided a well-established response matrix and adequate irradiation conditions, the most delicate part of neutron spectrometry, is the unfolding process. The derivation of the spectral information is not simple because the unknown is not given directly as a result of the measurements. The drawbacks associated with traditional unfolding procedures have motivated the need of complementary approaches. Novel methods based on Artificial Intelligence, mainly Artificial Neural Networks, have been widely investigated. In this work, a neutron spectrum unfolding code based on neural nets technology is presented. This code is called Neutron Spectrometry and Dosimetry with Artificial Neural networks unfolding code that was designed in a graphical interface. The core of the code is an embedded neural network architecture previously optimized using the robust design of artificial neural networks methodology. The main features of the code are: easy to use, friendly and intuitive to the user. This code was designed for a Bonner Sphere System based on a 6LiI(Eu) neutron detector and a response matrix expressed in 60 energy bins taken from an International Atomic Energy Agency compilation. The main feature of the code is that as entrance data, for unfolding the neutron spectrum, only seven rate counts measured with seven Bonner spheres are required; simultaneously the code calculates 15 dosimetric quantities as well as the total flux for radiation protection purposes. This code generates a full report with all information of the unfolding in the HTML format. NSDann unfolding code is freely available, upon request to the authors.

NASA's Software Bank (NETS)

NASA Technical Reports Server (NTRS)

1992-01-01

NETS (A Neural Network Development Tool) is a software system for mimicking the human brain. It is used in a University of Arkansas project in pattern matching of chemical systems. If successful, chemists would be able to identify mixtures of compounds without long and costly separation procedures. Using NETS, the group has trained the computer to recognize pattern relationships in a known compound and associate the results to an unknown compound. The research appears to be promising.

QSAR modelling using combined simple competitive learning networks and RBF neural networks.

PubMed

Sheikhpour, R; Sarram, M A; Rezaeian, M; Sheikhpour, E

2018-04-01

The aim of this study was to propose a QSAR modelling approach based on the combination of simple competitive learning (SCL) networks with radial basis function (RBF) neural networks for predicting the biological activity of chemical compounds. The proposed QSAR method consisted of two phases. In the first phase, an SCL network was applied to determine the centres of an RBF neural network. In the second phase, the RBF neural network was used to predict the biological activity of various phenols and Rho kinase (ROCK) inhibitors. The predictive ability of the proposed QSAR models was evaluated and compared with other QSAR models using external validation. The results of this study showed that the proposed QSAR modelling approach leads to better performances than other models in predicting the biological activity of chemical compounds. This indicated the efficiency of simple competitive learning networks in determining the centres of RBF neural networks.

Neural nets for aligning optical components in harsh environments: Beam smoothing spatial filter as an example

NASA Technical Reports Server (NTRS)

Decker, Arthur J.; Krasowski, Michael J.

1991-01-01

The goal is to develop an approach to automating the alignment and adjustment of optical measurement, visualization, inspection, and control systems. Classical controls, expert systems, and neural networks are three approaches to automating the alignment of an optical system. Neural networks were chosen for this project and the judgements that led to this decision are presented. Neural networks were used to automate the alignment of the ubiquitous laser-beam-smoothing spatial filter. The results and future plans of the project are presented.

An Artificial Neural Networks Method for Solving Partial Differential Equations

NASA Astrophysics Data System (ADS)

Alharbi, Abir

2010-09-01

While there already exists many analytical and numerical techniques for solving PDEs, this paper introduces an approach using artificial neural networks. The approach consists of a technique developed by combining the standard numerical method, finite-difference, with the Hopfield neural network. The method is denoted Hopfield-finite-difference (HFD). The architecture of the nets, energy function, updating equations, and algorithms are developed for the method. The HFD method has been used successfully to approximate the solution of classical PDEs, such as the Wave, Heat, Poisson and the Diffusion equations, and on a system of PDEs. The software Matlab is used to obtain the results in both tabular and graphical form. The results are similar in terms of accuracy to those obtained by standard numerical methods. In terms of speed, the parallel nature of the Hopfield nets methods makes them easier to implement on fast parallel computers while some numerical methods need extra effort for parallelization.

Multi-layer holographic bifurcative neural network system for real-time adaptive EOS data analysis

NASA Technical Reports Server (NTRS)

Liu, Hua-Kuang; Huang, K. S.; Diep, J.

1993-01-01

Optical data processing techniques have the inherent advantage of high data throughout, low weight and low power requirements. These features are particularly desirable for onboard spacecraft in-situ real-time data analysis and data compression applications. the proposed multi-layer optical holographic neural net pattern recognition technique will utilize the nonlinear photorefractive devices for real-time adaptive learning to classify input data content and recognize unexpected features. Information can be stored either in analog or digital form in a nonlinear photofractive device. The recording can be accomplished in time scales ranging from milliseconds to microseconds. When a system consisting of these devices is organized in a multi-layer structure, a feedforward neural net with bifurcating data classification capability is formed. The interdisciplinary research will involve the collaboration with top digital computer architecture experts at the University of Southern California.

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.

Enhancement Of Reading Accuracy By Multiple Data Integration

NASA Astrophysics Data System (ADS)

Lee, Kangsuk

1989-07-01

In this paper, a multiple sensor integration technique with neural network learning algorithms is presented which can enhance the reading accuracy of the hand-written numerals. Many document reading applications involve hand-written numerals in a predetermined location on a form, and in many cases, critical data is redundantly described. The amount of a personal check is one such case which is written redundantly in numerals and in alphabetical form. Information from two optical character recognition modules, one specialized for digits and one for words, is combined to yield an enhanced recognition of the amount. The combination can be accomplished by a decision tree with "if-then" rules, but by simply fusing two or more sets of sensor data in a single expanded neural net, the same functionality can be expected with a much reduced system cost. Experimental results of fusing two neural nets to enhance overall recognition performance using a controlled data set are presented.

An acoustic emission and acousto-ultrasonic analysis of impact damaged composite pressure vessels

NASA Technical Reports Server (NTRS)

Workman, Gary L. (Principal Investigator); Walker, James L.

1996-01-01

The use of acoustic emission to characterize impact damage in composite structures is being performed on composite bottles wrapped with graphite epoxy and kevlar bottles. Further development of the acoustic emission methodology will include neural net analysis and/or other multivariate techniques to enhance the capability of the technique to identify dominant failure mechanisms during fracture. The acousto-ultrasonics technique will also continue to be investigated to determine its ability to predict regions prone to failure prior to the burst tests. Characterization of the stress wave factor before, and after impact damage will be useful for inspection purposes in manufacturing processes. The combination of the two methods will also allow for simple nondestructive tests capable of predicting the performance of a composite structure prior to its being placed in service and during service.

The power of neural nets

NASA Technical Reports Server (NTRS)

Ryan, J. P.; Shah, B. H.

1987-01-01

Implementation of the Hopfield net which is used in the image processing type of applications where only partial information about the image may be available is discussed. The image classification type of algorithm of Hopfield and other learning algorithms, such as the Boltzmann machine and the back-propagation training algorithm, have many vital applications in space.

The use of artificial neural networks in experimental data acquisition and aerodynamic design

NASA Technical Reports Server (NTRS)

Meade, Andrew J., Jr.

1991-01-01

It is proposed that an artificial neural network be used to construct an intelligent data acquisition system. The artificial neural networks (ANN) model has a potential for replacing traditional procedures as well as for use in computational fluid dynamics validation. Potential advantages of the ANN model are listed. As a proof of concept, the author modeled a NACA 0012 airfoil at specific conditions, using the neural network simulator NETS, developed by James Baffes of the NASA Johnson Space Center. The neural network predictions were compared to the actual data. It is concluded that artificial neural networks can provide an elegant and valuable class of mathematical tools for data analysis.

Searching for Exoplanets using Artificial Intelligence

NASA Astrophysics Data System (ADS)

Pearson, Kyle Alexander; Palafox, Leon; Griffith, Caitlin Ann

2017-10-01

In the last decade, over a million stars were monitored to detect transiting planets. The large volume of data obtained from current and future missions (e.g. Kepler, K2, TESS and LSST) requires automated methods to detect the signature of a planet. Manual interpretation of potential exoplanet candidates is labor intensive and subject to human error, the results of which are difficult to quantify. Here we present a new method of detecting exoplanet candidates in large planetary search projects which, unlike current methods uses a neural network. Neural networks, also called ``deep learning'' or ``deep nets'', are a state of the art machine learning technique designed to give a computer perception into a specific problem by training it to recognize patterns. Unlike past transit detection algorithms, the deep net learns to characterize the data instead of relying on hand-coded metrics that humans perceive as the most representative. Exoplanet transits have different shapes, as a result of, e.g. the planet's and stellar atmosphere and transit geometry. Thus, a simple template does not suffice to capture the subtle details, especially if the signal is below the noise or strong systematics are present. Current false-positive rates from the Kepler data are estimated around 12.3% for Earth-like planets and there has been no study of the false negative rates. It is therefore important to ask how the properties of current algorithms exactly affect the results of the Kepler mission and, future missions such as TESS, which flies next year. These uncertainties affect the fundamental research derived from missions, such as the discovery of habitable planets, estimates of their occurrence rates and our understanding about the nature and evolution of planetary systems.

Real-time support for high performance aircraft operation

NASA Technical Reports Server (NTRS)

Vidal, Jacques J.

1989-01-01

The feasibility of real-time processing schemes using artificial neural networks (ANNs) is investigated. A rationale for digital neural nets is presented and a general processor architecture for control applications is illustrated. Research results on ANN structures for real-time applications are given. Research results on ANN algorithms for real-time control are also shown.

Stochastic architecture for Hopfield neural nets

NASA Technical Reports Server (NTRS)

Pavel, Sandy

1992-01-01

An expandable stochastic digital architecture for recurrent (Hopfield like) neural networks is proposed. The main features and basic principles of stochastic processing are presented. The stochastic digital architecture is based on a chip with n full interconnected neurons with a pipeline, bit processing structure. For large applications, a flexible way to interconnect many such chips is provided.

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

Jason L. Wright; Milos Manic

Finding and identifying cryptography is a growing concern in the malware analysis community. In this paper, artificial neural networks are used to classify functional blocks from a disassembled program as being either cryptography related or not. The resulting system, referred to as NNLC (Neural Net for Locating Cryptography) is presented and results of applying this system to various libraries are described.

The ventral tegmental area modulates intracortical microstimulation (ICMS)-evoked M1 activity in a time-dependent manner.

PubMed

Kunori, Nobuo; Kajiwara, Riichi; Takashima, Ichiro

2016-03-11

Intracortical microstimulation (ICMS)-evoked neural activity combined with ventral tegmental area (VTA) stimulation was studied in rat primary motor cortex (M1). We used voltage-sensitive dye (VSD) imaging to analyze the spatiotemporal dynamics of M1 activity following VTA-M1 paired stimulation. VTA stimulation was preceded by M1 ICMS at inter-stimulus intervals (ISIs) of 15-350ms. VSD imaging showed an excitatory-inhibitory sequence of neural activity after composing VTA stimulus- and ICMS-induced M1 neural activity. To evaluate the net ICMS M1 response, the optical response to unpaired VTA stimulation was subtracted from the VTA-M1 paired response. This revealed that the net ICMS-evoked M1 neural activity was inhibited when the ISI was 30-50ms, but highly facilitated when the ISI was 100-350ms. These results suggest that VTA modulates M1 excitability in the order of tens to hundreds of milliseconds and might directly affect the motor command generation process in the M1. Copyright © 2016 Elsevier Ireland Ltd. All rights reserved.

Methods and decision making on a Mars rover for identification of fossils

NASA Technical Reports Server (NTRS)

Eberlein, Susan; Yates, Gigi

1989-01-01

A system for automated fusion and interpretation of image data from multiple sensors, including multispectral data from an imaging spectrometer is being developed. Classical artificial intelligence techniques and artificial neural networks are employed to make real time decision based on current input and known scientific goals. Emphasis is placed on identifying minerals which could indicate past life activity or an environment supportive of life. Multispectral data can be used for geological analysis because different minerals have characteristic spectral reflectance in the visible and near infrared range. Classification of each spectrum into a broad class, based on overall spectral shape and locations of absorption bands is possible in real time using artificial neural networks. The goal of the system is twofold: multisensor and multispectral data must be interpreted in real time so that potentially interesting sites can be flagged and investigated in more detail while the rover is near those sites; and the sensed data must be reduced to the most compact form possible without loss of crucial information. Autonomous decision making will allow a rover to achieve maximum scientific benefit from a mission. Both a classical rule based approach and a decision neural network for making real time choices are being considered. Neural nets may work well for adaptive decision making. A neural net can be trained to work in two steps. First, the actual input state is mapped to the closest of a number of memorized states. After weighing the importance of various input parameters, the net produces an output decision based on the matched memory state. Real time, autonomous image data analysis and decision making capabilities are required for achieving maximum scientific benefit from a rover mission. The system under development will enhance the chances of identifying fossils or environments capable of supporting life on Mars

Document analysis with neural net circuits

NASA Technical Reports Server (NTRS)

Graf, Hans Peter

1994-01-01

Document analysis is one of the main applications of machine vision today and offers great opportunities for neural net circuits. Despite more and more data processing with computers, the number of paper documents is still increasing rapidly. A fast translation of data from paper into electronic format is needed almost everywhere, and when done manually, this is a time consuming process. Markets range from small scanners for personal use to high-volume document analysis systems, such as address readers for the postal service or check processing systems for banks. A major concern with present systems is the accuracy of the automatic interpretation. Today's algorithms fail miserably when noise is present, when print quality is poor, or when the layout is complex. A common approach to circumvent these problems is to restrict the variations of the documents handled by a system. In our laboratory, we had the best luck with circuits implementing basic functions, such as convolutions, that can be used in many different algorithms. To illustrate the flexibility of this approach, three applications of the NET32K circuit are described in this short viewgraph presentation: locating address blocks, cleaning document images by removing noise, and locating areas of interest in personal checks to improve image compression. Several of the ideas realized in this circuit that were inspired by neural nets, such as analog computation with a low resolution, resulted in a chip that is well suited for real-world document analysis applications and that compares favorably with alternative, 'conventional' circuits.

Deep Convolutional Neural Networks for Endotracheal Tube Position and X-ray Image Classification: Challenges and Opportunities.

PubMed

Lakhani, Paras

2017-08-01

The goal of this study is to evaluate the efficacy of deep convolutional neural networks (DCNNs) in differentiating subtle, intermediate, and more obvious image differences in radiography. Three different datasets were created, which included presence/absence of the endotracheal (ET) tube (n = 300), low/normal position of the ET tube (n = 300), and chest/abdominal radiographs (n = 120). The datasets were split into training, validation, and test. Both untrained and pre-trained deep neural networks were employed, including AlexNet and GoogLeNet classifiers, using the Caffe framework. Data augmentation was performed for the presence/absence and low/normal ET tube datasets. Receiver operating characteristic (ROC), area under the curves (AUC), and 95% confidence intervals were calculated. Statistical differences of the AUCs were determined using a non-parametric approach. The pre-trained AlexNet and GoogLeNet classifiers had perfect accuracy (AUC 1.00) in differentiating chest vs. abdominal radiographs, using only 45 training cases. For more difficult datasets, including the presence/absence and low/normal position endotracheal tubes, more training cases, pre-trained networks, and data-augmentation approaches were helpful to increase accuracy. The best-performing network for classifying presence vs. absence of an ET tube was still very accurate with an AUC of 0.99. However, for the most difficult dataset, such as low vs. normal position of the endotracheal tube, DCNNs did not perform as well, but achieved a reasonable AUC of 0.81.

Scaling Deep Learning workloads: NVIDIA DGX-1/Pascal and Intel Knights Landing

DOE PAGES

Gawande, Nitin A.; Daily, Jeff A.; Siegel, Charles; ...

2018-05-05

Deep Learning (DL) algorithms have become ubiquitous in data analytics. As a result, major computing vendors—including NVIDIA, Intel, AMD, and IBM—have architectural road maps influenced by DL workloads. Furthermore, several vendors have recently advertised new computing products as accelerating large DL workloads. Unfortunately, it is difficult for data scientists to quantify the potential of these different products. Here, this article provides a performance and power analysis of important DL workloads on two major parallel architectures: NVIDIA DGX-1 (eight Pascal P100 GPUs interconnected with NVLink) and Intel Knights Landing (KNL) CPUs interconnected with Intel Omni-Path or Cray Aries. Our evaluation consistsmore » of a cross section of convolutional neural net workloads: CifarNet, AlexNet, GoogLeNet, and ResNet50 topologies using the Cifar10 and ImageNet datasets. The workloads are vendor-optimized for each architecture. We use sequentially equivalent implementations to maintain iso-accuracy between parallel and sequential DL models. Our analysis indicates that although GPUs provide the highest overall performance, the gap can close for some convolutional networks; and the KNL can be competitive in performance/watt. We find that NVLink facilitates scaling efficiency on GPUs. However, its importance is heavily dependent on neural network architecture. Furthermore, for weak-scaling—sometimes encouraged by restricted GPU memory—NVLink is less important.« less

Scaling Deep Learning workloads: NVIDIA DGX-1/Pascal and Intel Knights Landing

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

Gawande, Nitin A.; Daily, Jeff A.; Siegel, Charles

Deep Learning (DL) algorithms have become ubiquitous in data analytics. As a result, major computing vendors—including NVIDIA, Intel, AMD, and IBM—have architectural road maps influenced by DL workloads. Furthermore, several vendors have recently advertised new computing products as accelerating large DL workloads. Unfortunately, it is difficult for data scientists to quantify the potential of these different products. Here, this article provides a performance and power analysis of important DL workloads on two major parallel architectures: NVIDIA DGX-1 (eight Pascal P100 GPUs interconnected with NVLink) and Intel Knights Landing (KNL) CPUs interconnected with Intel Omni-Path or Cray Aries. Our evaluation consistsmore » of a cross section of convolutional neural net workloads: CifarNet, AlexNet, GoogLeNet, and ResNet50 topologies using the Cifar10 and ImageNet datasets. The workloads are vendor-optimized for each architecture. We use sequentially equivalent implementations to maintain iso-accuracy between parallel and sequential DL models. Our analysis indicates that although GPUs provide the highest overall performance, the gap can close for some convolutional networks; and the KNL can be competitive in performance/watt. We find that NVLink facilitates scaling efficiency on GPUs. However, its importance is heavily dependent on neural network architecture. Furthermore, for weak-scaling—sometimes encouraged by restricted GPU memory—NVLink is less important.« less

Using artificial intelligence to predict permeability from petrographic data

NASA Astrophysics Data System (ADS)

Ali, Maqsood; Chawathé, Adwait

2000-10-01

Petrographic data collected during thin section analysis can be invaluable for understanding the factors that control permeability distribution. Reliable prediction of permeability is important for reservoir characterization. The petrographic elements (mineralogy, porosity types, cements and clays, and pore morphology) interact with each other uniquely to generate a specific permeability distribution. It is difficult to quantify accurately this interaction and its consequent effect on permeability, emphasizing the non-linear nature of the process. To capture these non-linear interactions, neural networks were used to predict permeability from petrographic data. The neural net was used as a multivariate correlative tool because of its ability to learn the non-linear relationships between multiple input and output variables. The study was conducted on the upper Queen formation called the Shattuck Member (Permian age). The Shattuck Member is composed of very fine-grained arkosic sandstone. The core samples were available from the Sulimar Queen and South Lucky Lake fields located in Chaves County, New Mexico. Nineteen petrographic elements were collected for each permeability value using a combined minipermeameter-petrographic technique. In order to reduce noise and overfitting the permeability model, these petrographic elements were screened, and their control (ranking) with respect to permeability was determined using fuzzy logic. Since the fuzzy logic algorithm provides unbiased ranking, it was used to reduce the dimensionality of the input variables. Based on the fuzzy logic ranking, only the most influential petrographic elements were selected as inputs for permeability prediction. The neural net was trained and tested using data from Well 1-16 in the Sulimar Queen field. Relying on the ranking obtained from the fuzzy logic analysis, the net was trained using the most influential three, five, and ten petrographic elements. A fast algorithm (the scaled conjugate gradient method) was used to optimize the network weight matrix. The net was then successfully used to predict the permeability in the nearby South Lucky Lake field, also in the Shattuck Member. This study underscored various important aspects of using neural networks as non-linear estimators. The neural network learnt the complex relationships between petrographic control and permeability. By predicting permeability in a remotely-located, yet geologically similar field, the generalizing capability of the neural network was also demonstrated. In old fields, where conventional petrographic analysis was routine, this technique may be used to supplement core permeability estimates.

Nanoelectronics enabled chronic multimodal neural platform in a mouse ischemic model.

PubMed

Luan, Lan; Sullender, Colin T; Li, Xue; Zhao, Zhengtuo; Zhu, Hanlin; Wei, Xiaoling; Xie, Chong; Dunn, Andrew K

2018-02-01

Despite significant advancements of optical imaging techniques for mapping hemodynamics in small animal models, it remains challenging to combine imaging with spatially resolved electrical recording of individual neurons especially for longitudinal studies. This is largely due to the strong invasiveness to the living brain from the penetrating electrodes and their limited compatibility with longitudinal imaging. We implant arrays of ultraflexible nanoelectronic threads (NETs) in mice for neural recording both at the brain surface and intracortically, which maintain great tissue compatibility chronically. By mounting a cranial window atop of the NET arrays that allows for chronic optical access, we establish a multimodal platform that combines spatially resolved electrical recording of neural activity and laser speckle contrast imaging (LSCI) of cerebral blood flow (CBF) for longitudinal studies. We induce peri-infarct depolarizations (PIDs) by targeted photothrombosis, and show the ability to detect its occurrence and propagation through spatiotemporal variations in both extracellular potentials and CBF. We also demonstrate chronic tracking of single-unit neural activity and CBF over days after photothrombosis, from which we observe reperfusion and increased firing rates. This multimodal platform enables simultaneous mapping of neural activity and hemodynamic parameters at the microscale for quantitative, longitudinal comparisons with minimal perturbation to the baseline neurophysiology. The ability to spatiotemporally resolve and chronically track CBF and neural electrical activity in the same living brain region has broad applications for studying the interplay between neural and hemodynamic responses in health and in cerebrovascular and neurological pathologies. Copyright © 2017 Elsevier B.V. All rights reserved.

Neural network based speech synthesizer: A preliminary report

NASA Technical Reports Server (NTRS)

Villarreal, James A.; Mcintire, Gary

1987-01-01

A neural net based speech synthesis project is discussed. The novelty is that the reproduced speech was extracted from actual voice recordings. In essence, the neural network learns the timing, pitch fluctuations, connectivity between individual sounds, and speaking habits unique to that individual person. The parallel distributed processing network used for this project is the generalized backward propagation network which has been modified to also learn sequences of actions or states given in a particular plan.

Electronic neuroprocessors

NASA Technical Reports Server (NTRS)

Thakoor, Anil

1991-01-01

The JPL Center for Space Microelectronics Technology (CSMT) is actively pursuing research in the neural network theory, algorithms, and electronics as well as optoelectronic neural net hardware implementations, to explore the strengths and application potential for a variety of NASA, DoD, as well as commercial application problems, where conventional computing techniques are extremely time-consuming, cumbersome, or simply non-existent. An overview of the JPL electronic neural network hardware development activities and some of the striking applications of the JPL electronic neuroprocessors are presented.

The altered expression of perineuronal net elements during neural differentiation.

PubMed

Eskici, Nazli F; Erdem-Ozdamar, Sevim; Dayangac-Erden, Didem

2018-01-01

Perineuronal nets (PNNs), which are localized around neurons during development, are specialized forms of neural extracellular matrix with neuroprotective and plasticity-regulating roles. Hyaluronan and proteoglycan link protein 1 (HAPLN1), tenascin-R (TNR) and aggrecan (ACAN) are key elements of PNNs. In diseases characterized by neuritogenesis defects, the expression of these proteins is known to be downregulated, suggesting that PNNs may have a role in neural differentiation. In this study, the mRNA and protein levels of HAPLN1, TNR and ACAN were determined and compared at specific time points of neural differentiation. We used PC12 cells as the in vitro model because they reflect this developmental process. On day 7, the HAPLN1 mRNA level showed a 2.9-fold increase compared to the non-differentiated state. However, the cellular HAPLN1 protein level showed a decrease, indicating that the protein may have roles in neural differentiation, and may be secreted during the early period of differentiation. By contrast, TNR mRNA and protein levels remained unchanged, and the amount of cellular ACAN protein showed a 3.7-fold increase at day 7. These results suggest that ACAN may be secreted after day 7, possibly due to its large amount of post-translational modifications. Our results provide preliminary data on the expression of PNN elements during neural differentiation. Further investigations will be performed on the role of these elements in neurological disease models.

ConvNetQuake: Convolutional Neural Network for Earthquake Detection and Location

NASA Astrophysics Data System (ADS)

Denolle, M.; Perol, T.; Gharbi, M.

2017-12-01

Over the last decades, the volume of seismic data has increased exponentially, creating a need for efficient algorithms to reliably detect and locate earthquakes. Today's most elaborate methods scan through the plethora of continuous seismic records, searching for repeating seismic signals. In this work, we leverage the recent advances in artificial intelligence and present ConvNetQuake, a highly scalable convolutional neural network for probabilistic earthquake detection and location from single stations. We apply our technique to study two years of induced seismicity in Oklahoma (USA). We detect 20 times more earthquakes than previously cataloged by the Oklahoma Geological Survey. Our algorithm detection performances are at least one order of magnitude faster than other established methods.

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.

A simple miniature device for wireless stimulation of neural circuits in small behaving animals.

PubMed

Zhang, Yisi; Langford, Bruce; Kozhevnikov, Alexay

2011-10-30

The use of wireless neural stimulation devices offers significant advantages for neural stimulation experiments in behaving animals. We demonstrate a simple, low-cost and extremely lightweight wireless neural stimulation device which is made from off-the-shelf components. The device has low power consumption and does not require a high-power RF preamplifier. Neural stimulation can be carried out in either a voltage source mode or a current source mode. Using the device, we carry out wireless stimulation in the premotor brain area HVC of a songbird and demonstrate that such stimulation causes rapid perturbations of the acoustic structure of the song. Published by Elsevier B.V.

Neural nets with terminal chaos for simulation of non-deterministic patterns

NASA Technical Reports Server (NTRS)

Zak, Michail

1993-01-01

Models for simulating some aspects of neural intelligence are presented and discussed. Special attention is given to terminal neurodynamics as a particular architecture of terminal dynamics suitable for modeling information flows. Applications of terminal chaos to information fusion as well as to planning and modeling coordination among neurons in biological systems are disussed.

Neural-Net Processing of Characteristic Patterns From Electronic Holograms of Vibrating Blades

NASA Technical Reports Server (NTRS)

Decker, Arthur J.

1999-01-01

Finite-element-model-trained artificial neural networks can be used to process efficiently the characteristic patterns or mode shapes from electronic holograms of vibrating blades. The models used for routine design may not yet be sufficiently accurate for this application. This document discusses the creation of characteristic patterns; compares model generated and experimental characteristic patterns; and discusses the neural networks that transform the characteristic patterns into strain or damage information. The current potential to adapt electronic holography to spin rigs, wind tunnels and engines provides an incentive to have accurate finite element models lor training neural networks.

Sequential neural text compression.

PubMed

Schmidhuber, J; Heil, S

1996-01-01

The purpose of this paper is to show that neural networks may be promising tools for data compression without loss of information. We combine predictive neural nets and statistical coding techniques to compress text files. We apply our methods to certain short newspaper articles and obtain compression ratios exceeding those of the widely used Lempel-Ziv algorithms (which build the basis of the UNIX functions "compress" and "gzip"). The main disadvantage of our methods is that they are about three orders of magnitude slower than standard methods.

Quantitative phase microscopy using deep neural networks

NASA Astrophysics Data System (ADS)

Li, Shuai; Sinha, Ayan; Lee, Justin; Barbastathis, George

2018-02-01

Deep learning has been proven to achieve ground-breaking accuracy in various tasks. In this paper, we implemented a deep neural network (DNN) to achieve phase retrieval in a wide-field microscope. Our DNN utilized the residual neural network (ResNet) architecture and was trained using the data generated by a phase SLM. The results showed that our DNN was able to reconstruct the profile of the phase target qualitatively. In the meantime, large error still existed, which indicated that our approach still need to be improved.

International Neural Network Society Annual Meeting (1994) Held in San Diego, California on 5-9 June 1994. Volume 1

DTIC Science & Technology

1994-06-09

Ethics and the Soul 1-221 P. Werbos A Net Program for Natural Language Comprehension 1-863 J. Weiss Applications Oral ANN Design of Image Processing...Controlling Nonlinear Dynamic Systems Using Neuro-Fuzzy Networks 1-787 E. Teixera, G. Laforga, H. Azevedo Neural Fuzzy Logics as a Tool for Design Ecological ...Discrete Neural Network 11-466 Z. Cheng-fu Representation of Number A Theory of Mathematical Modeling 11-479 J. Cristofano An Ecological Approach to

PCANet: A Simple Deep Learning Baseline for Image Classification?

PubMed

Chan, Tsung-Han; Jia, Kui; Gao, Shenghua; Lu, Jiwen; Zeng, Zinan; Ma, Yi

2015-12-01

In this paper, we propose a very simple deep learning network for image classification that is based on very basic data processing components: 1) cascaded principal component analysis (PCA); 2) binary hashing; and 3) blockwise histograms. In the proposed architecture, the PCA is employed to learn multistage filter banks. This is followed by simple binary hashing and block histograms for indexing and pooling. This architecture is thus called the PCA network (PCANet) and can be extremely easily and efficiently designed and learned. For comparison and to provide a better understanding, we also introduce and study two simple variations of PCANet: 1) RandNet and 2) LDANet. They share the same topology as PCANet, but their cascaded filters are either randomly selected or learned from linear discriminant analysis. We have extensively tested these basic networks on many benchmark visual data sets for different tasks, including Labeled Faces in the Wild (LFW) for face verification; the MultiPIE, Extended Yale B, AR, Facial Recognition Technology (FERET) data sets for face recognition; and MNIST for hand-written digit recognition. Surprisingly, for all tasks, such a seemingly naive PCANet model is on par with the state-of-the-art features either prefixed, highly hand-crafted, or carefully learned [by deep neural networks (DNNs)]. Even more surprisingly, the model sets new records for many classification tasks on the Extended Yale B, AR, and FERET data sets and on MNIST variations. Additional experiments on other public data sets also demonstrate the potential of PCANet to serve as a simple but highly competitive baseline for texture classification and object recognition.

An integrated epidemiological and neural net model of the warfarin effect in managed care patients.

PubMed

Jacobs, David M; Stefanovic, Filip; Wilton, Greg; Gomez-Caminero, Andres; Schentag, Jerome J

2017-01-01

Risk assessment tools are utilized to estimate the risk for stroke and need of anticoagulation therapy for patients with atrial fibrillation (AF). These risk stratification scores are limited by the information inputted into them and a reliance on time-independent variables. The objective of this study was to develop a time-dependent neural net model to identify AF populations at high risk of poor clinical outcomes and evaluate the discriminatory ability of the model in a managed care population. We performed a longitudinal, cohort study within a health-maintenance organization from 1997 to 2008. Participants were identified with incident AF irrespective of warfarin status and followed through their duration within the database. Three clinical outcome measures were evaluated including stroke, myocardial infarction, and hemorrhage. A neural net model was developed to identify patients at high risk of clinical events and defined to be an "enriched" patient. The model defines the enrichment based on the top 10 minimum mean square error output parameters that describe the three clinical outcomes. Cox proportional hazard models were utilized to evaluate the outcome measures. Among 285 patients, the mean age was 74±12 years with a mean follow-up of 4.3±2.6 years, and 154 (54%) were treated with warfarin. After propensity score adjustment, warfarin use was associated with a slightly increased risk of adverse outcomes (including stroke, myocardial infarction, and hemorrhage), though it did not attain statistical significance (adjusted hazard ratio [aHR] =1.22; 95% confidence interval [CI] 0.75-1.97; p =0.42). Within the neural net model, subjects at high risk of adverse outcomes were identified and labeled as "enriched." Following propensity score adjustment, enriched subjects were associated with an 81% higher risk of adverse outcomes as compared to nonenriched subjects (aHR=1.81; 95% CI, 1.15-2.88; p =0.01). Enrichment methodology improves the statistical discrimination of meaningful endpoints when used in a health records-based analysis.

PatterNet: a system to learn compact physical design pattern representations for pattern-based analytics

NASA Astrophysics Data System (ADS)

Lutich, Andrey

2017-07-01

This research considers the problem of generating compact vector representations of physical design patterns for analytics purposes in semiconductor patterning domain. PatterNet uses a deep artificial neural network to learn mapping of physical design patterns to a compact Euclidean hyperspace. Distances among mapped patterns in this space correspond to dissimilarities among patterns defined at the time of the network training. Once the mapping network has been trained, PatterNet embeddings can be used as feature vectors with standard machine learning algorithms, and pattern search, comparison, and clustering become trivial problems. PatterNet is inspired by the concepts developed within the framework of generative adversarial networks as well as the FaceNet. Our method facilitates a deep neural network (DNN) to learn directly the compact representation by supplying it with pairs of design patterns and dissimilarity among these patterns defined by a user. In the simplest case, the dissimilarity is represented by an area of the XOR of two patterns. Important to realize that our PatterNet approach is very different to the methods developed for deep learning on image data. In contrast to "conventional" pictures, the patterns in the CAD world are the lists of polygon vertex coordinates. The method solely relies on the promise of deep learning to discover internal structure of the incoming data and learn its hierarchical representations. Artificial intelligence arising from the combination of PatterNet and clustering analysis very precisely follows intuition of patterning/optical proximity correction experts paving the way toward human-like and human-friendly engineering tools.

Evolution and development of brain networks: from Caenorhabditis elegans to Homo sapiens.

PubMed

Kaiser, Marcus; Varier, Sreedevi

2011-01-01

Neural networks show a progressive increase in complexity during the time course of evolution. From diffuse nerve nets in Cnidaria to modular, hierarchical systems in macaque and humans, there is a gradual shift from simple processes involving a limited amount of tasks and modalities to complex functional and behavioral processing integrating different kinds of information from highly specialized tissue. However, studies in a range of species suggest that fundamental similarities, in spatial and topological features as well as in developmental mechanisms for network formation, are retained across evolution. 'Small-world' topology and highly connected regions (hubs) are prevalent across the evolutionary scale, ensuring efficient processing and resilience to internal (e.g. lesions) and external (e.g. environment) changes. Furthermore, in most species, even the establishment of hubs, long-range connections linking distant components, and a modular organization, relies on similar mechanisms. In conclusion, evolutionary divergence leads to greater complexity while following essential developmental constraints.

Nanoelectronics enabled chronic multimodal neural platform in a mouse ischemic model

PubMed Central

Luan, Lan; Sullender, Colin T.; Li, Xue; Zhao, Zhengtuo; Zhu, Hanlin; Wei, Xiaoling; Xie, Chong; Dunn, Andrew K.

2018-01-01

Background Despite significant advancements of optical imaging techniques for mapping hemodynamics in small animal models, it remains challenging to combine imaging with spatially resolved electrical recording of individual neurons especially for longitudinal studies. This is largely due to the strong invasiveness to the living brain from the penetrating electrodes and their limited compatibility with longitudinal imaging. New Method We implant arrays of ultraflexible nanoelectronic threads (NETs) in mice for neural recording both at the brain surface and intracortically, which maintain great tissue compatibility chronically. By mounting a cranial window atop of the NET arrays that allows for chronic optical access, we establish a multimodal platform that combines spatially resolved electrical recording of neural activity and laser speckle contrast imaging (LSCI) of cerebral blood flow (CBF) for longitudinal studies. Results We induce peri-infarct depolarizations (PIDs) by targeted photothrombosis, and show the ability to detect its occurrence and propagation through spatiotemporal variations in both extracellular potentials and CBF. We also demonstrate chronic tracking of single-unit neural activity and CBF over days after photothrombosis, from which we observe reperfusion and increased firing rates. Comparison with Existing Method(s) This multimodal platform enables simultaneous mapping of neural activity and hemodynamic parameters at the microscale for quantitative, longitudinal comparisons with minimal perturbation to the baseline neurophysiology. Conclusion The ability to spatiotemporally resolve and chronically track CBF and neural electrical activity in the same living brain region has broad applications for studying the interplay between neural and hemodynamic responses in health and in cerebrovascular and neurological pathologies. PMID:29203409

Attenuation correction for brain PET imaging using deep neural network based on dixon and ZTE MR images.

PubMed

Gong, Kuang; Yang, Jaewon; Kim, Kyungsang; El Fakhri, Georges; Seo, Youngho; Li, Quanzheng

2018-05-23

Positron Emission Tomography (PET) is a functional imaging modality widely used in neuroscience studies. To obtain meaningful quantitative results from PET images, attenuation correction is necessary during image reconstruction. For PET/MR hybrid systems, PET attenuation is challenging as Magnetic Resonance (MR) images do not reflect attenuation coefficients directly. To address this issue, we present deep neural network methods to derive the continuous attenuation coefficients for brain PET imaging from MR images. With only Dixon MR images as the network input, the existing U-net structure was adopted and analysis using forty patient data sets shows it is superior than other Dixon based methods. When both Dixon and zero echo time (ZTE) images are available, we have proposed a modified U-net structure, named GroupU-net, to efficiently make use of both Dixon and ZTE information through group convolution modules when the network goes deeper. Quantitative analysis based on fourteen real patient data sets demonstrates that both network approaches can perform better than the standard methods, and the proposed network structure can further reduce the PET quantification error compared to the U-net structure. © 2018 Institute of Physics and Engineering in Medicine.

Planarian homologs of netrin and netrin receptor are required for proper regeneration of the central nervous system and the maintenance of nervous system architecture.

PubMed

Cebrià, Francesc; Newmark, Phillip A

2005-08-01

Conserved axon guidance mechanisms are essential for proper wiring of the nervous system during embryogenesis; however, the functions of these cues in adults and during regeneration remain poorly understood. Because freshwater planarians can regenerate a functional central nervous system (CNS) from almost any portion of their body, they are useful models in which to study the roles of guidance cues during neural regeneration. Here, we characterize two netrin homologs and one netrin receptor family member from Schmidtea mediterranea. RNAi analyses indicate that Smed-netR (netrin receptor) and Smed-netrin2 are required for proper CNS regeneration and that Smed-netR may mediate the response to Smed-netrin2. Remarkably, Smed-netR and Smed-netrin2 are also required in intact planarians to maintain the proper patterning of the CNS. These results suggest a crucial role for guidance cues, not only in CNS regeneration but also in maintenance of neural architecture.

Auto-programmable impulse neural circuits

NASA Technical Reports Server (NTRS)

Watula, D.; Meador, J.

1990-01-01

Impulse neural networks use pulse trains to communicate neuron activation levels. Impulse neural circuits emulate natural neurons at a more detailed level than that typically employed by contemporary neural network implementation methods. An impulse neural circuit which realizes short term memory dynamics is presented. The operation of that circuit is then characterized in terms of pulse frequency modulated signals. Both fixed and programmable synapse circuits for realizing long term memory are also described. The implementation of a simple and useful unsupervised learning law is then presented. The implementation of a differential Hebbian learning rule for a specific mean-frequency signal interpretation is shown to have a straightforward implementation using digital combinational logic with a variation of a previously developed programmable synapse circuit. This circuit is expected to be exploited for simple and straightforward implementation of future auto-adaptive neural circuits.

Classification of polycystic ovary based on ultrasound images using competitive neural network

NASA Astrophysics Data System (ADS)

Dewi, R. M.; Adiwijaya; Wisesty, U. N.; Jondri

2018-03-01

Infertility in the women reproduction system due to inhibition of follicles maturation process causing the number of follicles which is called polycystic ovaries (PCO). PCO detection is still operated manually by a gynecologist by counting the number and size of follicles in the ovaries, so it takes a long time and needs high accuracy. In general, PCO can be detected by calculating stereology or feature extraction and classification. In this paper, we designed a system to classify PCO by using the feature extraction (Gabor Wavelet method) and Competitive Neural Network (CNN). CNN was selected because this method is the combination between Hemming Net and The Max Net so that the data classification can be performed based on the specific characteristics of ultrasound data. Based on the result of system testing, Competitive Neural Network obtained the highest accuracy is 80.84% and the time process is 60.64 seconds (when using 32 feature vectors as well as weight and bias values respectively of 0.03 and 0.002).

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.

Adaptive Neural Star Tracker Calibration for Precision Spacecraft Pointing and Tracking

NASA Technical Reports Server (NTRS)

Bayard, David S.

1996-01-01

The Star Tracker is an essential sensor for precision pointing and tracking in most 3-axis stabilized spacecraft. In the interest (of) improving pointing performance by taking advantage of dramatic increases in flight computer power and memory anticipated over the next decade, this paper investigates the use of a neural net for adaptive in-flight calibration of the Star Tracker.

Non-parametric analysis of LANDSAT maps using neural nets and parallel computers

NASA Technical Reports Server (NTRS)

Salu, Yehuda; Tilton, James

1991-01-01

Nearest neighbor approaches and a new neural network, the Binary Diamond, are used for the classification of images of ground pixels obtained by LANDSAT satellite. The performances are evaluated by comparing classifications of a scene in the vicinity of Washington DC. The problem of optimal selection of categories is addressed as a step in the classification process.

Convolutional Neural Network for Histopathological Analysis of Osteosarcoma.

PubMed

Mishra, Rashika; Daescu, Ovidiu; Leavey, Patrick; Rakheja, Dinesh; Sengupta, Anita

2018-03-01

Pathologists often deal with high complexity and sometimes disagreement over osteosarcoma tumor classification due to cellular heterogeneity in the dataset. Segmentation and classification of histology tissue in H&E stained tumor image datasets is a challenging task because of intra-class variations, inter-class similarity, crowded context, and noisy data. In recent years, deep learning approaches have led to encouraging results in breast cancer and prostate cancer analysis. In this article, we propose convolutional neural network (CNN) as a tool to improve efficiency and accuracy of osteosarcoma tumor classification into tumor classes (viable tumor, necrosis) versus nontumor. The proposed CNN architecture contains eight learned layers: three sets of stacked two convolutional layers interspersed with max pooling layers for feature extraction and two fully connected layers with data augmentation strategies to boost performance. The use of a neural network results in higher accuracy of average 92% for the classification. We compare the proposed architecture with three existing and proven CNN architectures for image classification: AlexNet, LeNet, and VGGNet. We also provide a pipeline to calculate percentage necrosis in a given whole slide image. We conclude that the use of neural networks can assure both high accuracy and efficiency in osteosarcoma classification.

Perineuronal net, CSPG receptor and their regulation of neural plasticity.

PubMed

Miao, Qing-Long; Ye, Qian; Zhang, Xiao-Hui

2014-08-25

Perineuronal nets (PNNs) are reticular structures resulting from the aggregation of extracellular matrix (ECM) molecules around the cell body and proximal neurite of specific population of neurons in the central nervous system (CNS). Since the first description of PNNs by Camillo Golgi in 1883, the molecular composition, developmental formation and potential functions of these specialized extracellular matrix structures have only been intensively studied over the last few decades. The main components of PNNs are hyaluronan (HA), chondroitin sulfate proteoglycans (CSPGs) of the lectican family, link proteins and tenascin-R. PNNs appear late in neural development, inversely correlating with the level of neural plasticity. PNNs have long been hypothesized to play a role in stabilizing the extracellular milieu, which secures the characteristic features of enveloped neurons and protects them from the influence of malicious agents. Aberrant PNN signaling can lead to CNS dysfunctions like epilepsy, stroke and Alzheimer's disease. On the other hand, PNNs create a barrier which constrains the neural plasticity and counteracts the regeneration after nerve injury. Digestion of PNNs with chondroitinase ABC accelerates functional recovery from the spinal cord injury and restores activity-dependent mechanisms for modifying neuronal connections in the adult animals, indicating that PNN is an important regulator of neural plasticity. Here, we review recent progress in the studies on the formation of PNNs during early development and the identification of CSPG receptor - an essential molecular component of PNN signaling, along with a discussion on their unique regulatory roles in neural plasticity.

An analysis of image storage systems for scalable training of deep neural networks

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

Lim, Seung-Hwan; Young, Steven R; Patton, Robert M

This study presents a principled empirical evaluation of image storage systems for training deep neural networks. We employ the Caffe deep learning framework to train neural network models for three different data sets, MNIST, CIFAR-10, and ImageNet. While training the models, we evaluate five different options to retrieve training image data: (1) PNG-formatted image files on local file system; (2) pushing pixel arrays from image files into a single HDF5 file on local file system; (3) in-memory arrays to hold the pixel arrays in Python and C++; (4) loading the training data into LevelDB, a log-structured merge tree based key-valuemore » storage; and (5) loading the training data into LMDB, a B+tree based key-value storage. The experimental results quantitatively highlight the disadvantage of using normal image files on local file systems to train deep neural networks and demonstrate reliable performance with key-value storage based storage systems. When training a model on the ImageNet dataset, the image file option was more than 17 times slower than the key-value storage option. Along with measurements on training time, this study provides in-depth analysis on the cause of performance advantages/disadvantages of each back-end to train deep neural networks. We envision the provided measurements and analysis will shed light on the optimal way to architect systems for training neural networks in a scalable manner.« less

Estimating satellite pose and motion parameters using a novelty filter and neural net tracker

NASA Technical Reports Server (NTRS)

Lee, Andrew J.; Casasent, David; Vermeulen, Pieter; Barnard, Etienne

1989-01-01

A system for determining the position, orientation and motion of a satellite with respect to a robotic spacecraft using video data is advanced. This system utilizes two levels of pose and motion estimation: an initial system which provides coarse estimates of pose and motion, and a second system which uses the coarse estimates and further processing to provide finer pose and motion estimates. The present paper emphasizes the initial coarse pose and motion estimation sybsystem. This subsystem utilizes novelty detection and filtering for locating novel parts and a neural net tracker to track these parts over time. Results of using this system on a sequence of images of a spin stabilized satellite are presented.

Method for Constructing Composite Response Surfaces by Combining Neural Networks with Polynominal Interpolation or Estimation Techniques

NASA Technical Reports Server (NTRS)

Rai, Man Mohan (Inventor); Madavan, Nateri K. (Inventor)

2007-01-01

A method and system for data modeling that incorporates the advantages of both traditional response surface methodology (RSM) and neural networks is disclosed. The invention partitions the parameters into a first set of s simple parameters, where observable data are expressible as low order polynomials, and c complex parameters that reflect more complicated variation of the observed data. Variation of the data with the simple parameters is modeled using polynomials; and variation of the data with the complex parameters at each vertex is analyzed using a neural network. Variations with the simple parameters and with the complex parameters are expressed using a first sequence of shape functions and a second sequence of neural network functions. The first and second sequences are multiplicatively combined to form a composite response surface, dependent upon the parameter values, that can be used to identify an accurate mode

Mushroom body defect is required in parallel to Netrin for midline axon guidance in Drosophila

PubMed Central

Cate, Marie-Sophie; Gajendra, Sangeetha; Alsbury, Samantha; Raabe, Thomas; Tear, Guy; Mitchell, Kevin J.

2016-01-01

The outgrowth of many neurons within the central nervous system is initially directed towards or away from the cells lying at the midline. Recent genetic evidence suggests that a simple model of differential sensitivity to the conserved Netrin attractants and Slit repellents is insufficient to explain the guidance of all axons at the midline. In the Drosophila embryonic ventral nerve cord, many axons still cross the midline in the absence of the Netrin genes (NetA and NetB) or their receptor frazzled. Here we show that mutation of mushroom body defect (mud) dramatically enhances the phenotype of Netrin or frazzled mutants, resulting in many more axons failing to cross the midline, although mutations in mud alone have little effect. This suggests that mud, which encodes a microtubule-binding coiled-coil protein homologous to NuMA and LIN-5, is an essential component of a Netrin-independent pathway that acts in parallel to promote midline crossing. We demonstrate that this novel role of Mud in axon guidance is independent of its previously described role in neural precursor development. These studies identify a parallel pathway controlling midline guidance in Drosophila and highlight a novel role for Mud potentially acting downstream of Frizzled to aid axon guidance. PMID:26893348

Fully automatic acute ischemic lesion segmentation in DWI using convolutional neural networks.

PubMed

Chen, Liang; Bentley, Paul; Rueckert, Daniel

2017-01-01

Stroke is an acute cerebral vascular disease, which is likely to cause long-term disabilities and death. Acute ischemic lesions occur in most stroke patients. These lesions are treatable under accurate diagnosis and treatments. Although diffusion-weighted MR imaging (DWI) is sensitive to these lesions, localizing and quantifying them manually is costly and challenging for clinicians. In this paper, we propose a novel framework to automatically segment stroke lesions in DWI. Our framework consists of two convolutional neural networks (CNNs): one is an ensemble of two DeconvNets (Noh et al., 2015), which is the EDD Net; the second CNN is the multi-scale convolutional label evaluation net (MUSCLE Net), which aims to evaluate the lesions detected by the EDD Net in order to remove potential false positives. To the best of our knowledge, it is the first attempt to solve this problem and using both CNNs achieves very good results. Furthermore, we study the network architectures and key configurations in detail to ensure the best performance. It is validated on a large dataset comprising clinical acquired DW images from 741 subjects. A mean accuracy of Dice coefficient obtained is 0.67 in total. The mean Dice scores based on subjects with only small and large lesions are 0.61 and 0.83, respectively. The lesion detection rate achieved is 0.94.

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.

Integrating Artificial Immune, Neural and Endrocine Systems in Autonomous Sailing Robots

DTIC Science & Technology

2010-09-24

system - Development of an adaptive hormone system capable of changing operation and control of the neural network depending on changing enviromental ...and control of the neural network depending on changing enviromental conditions • First basic design of the MOOP and a simple neural-endocrine based

Beyond Reason: Emotion

NASA Astrophysics Data System (ADS)

Suárez Araujo, Carmen Paz; Barahona da Fonseca, Isabel; Barahona da Fonseca, José; Simões da Fonseca, J.

2004-08-01

A theoretical approach that aims to the identification of information processing that may be responsible for emotional dimensions of subjective experience is studied as an initial step in the construction of a neural net model of affective dimensions of psychological experiences. In this paper it is suggested that a way of orientated recombination of attributes can be present not only in the perceptive processing but also in cognitive ones. We will present an analysis of the most important emotion theories, we show their neural organization and we propose the neural computation approach as an appropriate framework for generating knowledge about the neural base of emotional experience. Finally, in this study we present a scheme corresponding to framework to design a computational neural multi-system for Emotion (CONEMSE).

From homeostasis to behavior: Balanced activity in an exploration of embodied dynamic environmental-neural interaction.

PubMed

Hellyer, Peter John; Clopath, Claudia; Kehagia, Angie A; Turkheimer, Federico E; Leech, Robert

2017-08-01

In recent years, there have been many computational simulations of spontaneous neural dynamics. Here, we describe a simple model of spontaneous neural dynamics that controls an agent moving in a simple virtual environment. These dynamics generate interesting brain-environment feedback interactions that rapidly destabilize neural and behavioral dynamics demonstrating the need for homeostatic mechanisms. We investigate roles for homeostatic plasticity both locally (local inhibition adjusting to balance excitatory input) as well as more globally (regional "task negative" activity that compensates for "task positive", sensory input in another region) balancing neural activity and leading to more stable behavior (trajectories through the environment). Our results suggest complementary functional roles for both local and macroscale mechanisms in maintaining neural and behavioral dynamics and a novel functional role for macroscopic "task-negative" patterns of activity (e.g., the default mode network).

NetTurnP – Neural Network Prediction of Beta-turns by Use of Evolutionary Information and Predicted Protein Sequence Features

PubMed Central

Petersen, Bent; Lundegaard, Claus; Petersen, Thomas Nordahl

2010-01-01

β-turns are the most common type of non-repetitive structures, and constitute on average 25% of the amino acids in proteins. The formation of β-turns plays an important role in protein folding, protein stability and molecular recognition processes. In this work we present the neural network method NetTurnP, for prediction of two-class β-turns and prediction of the individual β-turn types, by use of evolutionary information and predicted protein sequence features. It has been evaluated against a commonly used dataset BT426, and achieves a Matthews correlation coefficient of 0.50, which is the highest reported performance on a two-class prediction of β-turn and not-β-turn. Furthermore NetTurnP shows improved performance on some of the specific β-turn types. In the present work, neural network methods have been trained to predict β-turn or not and individual β-turn types from the primary amino acid sequence. The individual β-turn types I, I', II, II', VIII, VIa1, VIa2, VIba and IV have been predicted based on classifications by PROMOTIF, and the two-class prediction of β-turn or not is a superset comprised of all β-turn types. The performance is evaluated using a golden set of non-homologous sequences known as BT426. Our two-class prediction method achieves a performance of: MCC  = 0.50, Qtotal = 82.1%, sensitivity  = 75.6%, PPV  = 68.8% and AUC  = 0.864. We have compared our performance to eleven other prediction methods that obtain Matthews correlation coefficients in the range of 0.17 – 0.47. For the type specific β-turn predictions, only type I and II can be predicted with reasonable Matthews correlation coefficients, where we obtain performance values of 0.36 and 0.31, respectively. Conclusion The NetTurnP method has been implemented as a webserver, which is freely available at http://www.cbs.dtu.dk/services/NetTurnP/. NetTurnP is the only available webserver that allows submission of multiple sequences. PMID:21152409

NetTurnP--neural network prediction of beta-turns by use of evolutionary information and predicted protein sequence features.

PubMed

Petersen, Bent; Lundegaard, Claus; Petersen, Thomas Nordahl

2010-11-30

β-turns are the most common type of non-repetitive structures, and constitute on average 25% of the amino acids in proteins. The formation of β-turns plays an important role in protein folding, protein stability and molecular recognition processes. In this work we present the neural network method NetTurnP, for prediction of two-class β-turns and prediction of the individual β-turn types, by use of evolutionary information and predicted protein sequence features. It has been evaluated against a commonly used dataset BT426, and achieves a Matthews correlation coefficient of 0.50, which is the highest reported performance on a two-class prediction of β-turn and not-β-turn. Furthermore NetTurnP shows improved performance on some of the specific β-turn types. In the present work, neural network methods have been trained to predict β-turn or not and individual β-turn types from the primary amino acid sequence. The individual β-turn types I, I', II, II', VIII, VIa1, VIa2, VIba and IV have been predicted based on classifications by PROMOTIF, and the two-class prediction of β-turn or not is a superset comprised of all β-turn types. The performance is evaluated using a golden set of non-homologous sequences known as BT426. Our two-class prediction method achieves a performance of: MCC=0.50, Qtotal=82.1%, sensitivity=75.6%, PPV=68.8% and AUC=0.864. We have compared our performance to eleven other prediction methods that obtain Matthews correlation coefficients in the range of 0.17-0.47. For the type specific β-turn predictions, only type I and II can be predicted with reasonable Matthews correlation coefficients, where we obtain performance values of 0.36 and 0.31, respectively. The NetTurnP method has been implemented as a webserver, which is freely available at http://www.cbs.dtu.dk/services/NetTurnP/. NetTurnP is the only available webserver that allows submission of multiple sequences.

Optimization of Training Sets For Neural-Net Processing of Characteristic Patterns From Vibrating Solids

NASA Technical Reports Server (NTRS)

Decker, Arthur J. (Inventor)

2006-01-01

An artificial neural network is disclosed that processes holography generated characteristic pattern of vibrating structures along with finite-element models. The present invention provides for a folding operation for conditioning training sets for optimally training forward-neural networks to process characteristic fringe pattern. The folding pattern increases the sensitivity of the feed-forward network for detecting changes in the characteristic pattern The folding routine manipulates input pixels so as to be scaled according to the location in an intensity range rather than the position in the characteristic pattern.

Chaotic itinerancy in the oscillator neural network without Lyapunov functions.

PubMed

Uchiyama, Satoki; Fujisaka, Hirokazu

2004-09-01

Chaotic itinerancy (CI), which is defined as an incessant spontaneous switching phenomenon among attractor ruins in deterministic dynamical systems without Lyapunov functions, is numerically studied in the case of an oscillator neural network model. The model is the pseudoinverse-matrix version of the previous model [S. Uchiyama and H. Fujisaka, Phys. Rev. E 65, 061912 (2002)] that was studied theoretically with the aid of statistical neurodynamics. It is found that CI in neural nets can be understood as the intermittent dynamics of weakly destabilized chaotic retrieval solutions. Copyright 2004 American Institute of Physics

Deep nets vs expert designed features in medical physics: An IMRT QA case study.

PubMed

Interian, Yannet; Rideout, Vincent; Kearney, Vasant P; Gennatas, Efstathios; Morin, Olivier; Cheung, Joey; Solberg, Timothy; Valdes, Gilmer

2018-03-30

The purpose of this study was to compare the performance of Deep Neural Networks against a technique designed by domain experts in the prediction of gamma passing rates for Intensity Modulated Radiation Therapy Quality Assurance (IMRT QA). A total of 498 IMRT plans across all treatment sites were planned in Eclipse version 11 and delivered using a dynamic sliding window technique on Clinac iX or TrueBeam Linacs. Measurements were performed using a commercial 2D diode array, and passing rates for 3%/3 mm local dose/distance-to-agreement (DTA) were recorded. Separately, fluence maps calculated for each plan were used as inputs to a convolution neural network (CNN). The CNNs were trained to predict IMRT QA gamma passing rates using TensorFlow and Keras. A set of model architectures, inspired by the convolutional blocks of the VGG-16 ImageNet model, were constructed and implemented. Synthetic data, created by rotating and translating the fluence maps during training, was created to boost the performance of the CNNs. Dropout, batch normalization, and data augmentation were utilized to help train the model. The performance of the CNNs was compared to a generalized Poisson regression model, previously developed for this application, which used 78 expert designed features. Deep Neural Networks without domain knowledge achieved comparable performance to a baseline system designed by domain experts in the prediction of 3%/3 mm Local gamma passing rates. An ensemble of neural nets resulted in a mean absolute error (MAE) of 0.70 ± 0.05 and the domain expert model resulted in a 0.74 ± 0.06. Convolutional neural networks (CNNs) with transfer learning can predict IMRT QA passing rates by automatically designing features from the fluence maps without human expert supervision. Predictions from CNNs are comparable to a system carefully designed by physicist experts. © 2018 American Association of Physicists in Medicine.

Nonparametric Representations for Integrated Inference, Control, and Sensing

DTIC Science & Technology

2015-10-01

Learning (ICML), 2013. [20] Jeff Donahue, Yangqing Jia, Oriol Vinyals, Judy Hoffman, Ning Zhang, Eric Tzeng, and Trevor Darrell. DeCAF: A deep ...unlimited. Multi-layer feature learning “SuperVision” Convolutional Neural Network (CNN) ImageNet Classification with Deep Convolutional Neural Networks...to develop a new framework for autonomous operations that will extend the state of the art in distributed learning and modeling from data, and

The SoRReL papers: Recent publications of the Software Reuse Repository Lab

NASA Technical Reports Server (NTRS)

Eichmann, David A. (Editor)

1992-01-01

The entire publication is presented of some of the papers recently published by the SoRReL. Some typical titles are as follows: Design of a Lattice-Based Faceted Classification System; A Hybrid Approach to Software Reuse Repository Retrieval; Selecting Reusable Components Using Algebraic Specifications; Neural Network-Based Retrieval from Reuse Repositories; and A Neural Net-Based Approach to Software Metrics.

NETS - A NEURAL NETWORK DEVELOPMENT TOOL, VERSION 3.0 (MACINTOSH VERSION)

NASA Technical Reports Server (NTRS)

Phillips, T. A.

1994-01-01

NETS, A Tool for the Development and Evaluation of Neural Networks, provides a simulation of Neural Network algorithms plus an environment for developing such algorithms. Neural Networks are a class of systems modeled after the human brain. Artificial Neural Networks are formed from hundreds or thousands of simulated neurons, connected to each other in a manner similar to brain neurons. Problems which involve pattern matching readily fit the class of problems which NETS is designed to solve. NETS uses the back propagation learning method for all of the networks which it creates. The nodes of a network are usually grouped together into clumps called layers. Generally, a network will have an input layer through which the various environment stimuli are presented to the network, and an output layer for determining the network's response. The number of nodes in these two layers is usually tied to some features of the problem being solved. Other layers, which form intermediate stops between the input and output layers, are called hidden layers. NETS allows the user to customize the patterns of connections between layers of a network. NETS also provides features for saving the weight values of a network during the learning process, which allows for more precise control over the learning process. NETS is an interpreter. Its method of execution is the familiar "read-evaluate-print" loop found in interpreted languages such as BASIC and LISP. The user is presented with a prompt which is the simulator's way of asking for input. After a command is issued, NETS will attempt to evaluate the command, which may produce more prompts requesting specific information or an error if the command is not understood. The typical process involved when using NETS consists of translating the problem into a format which uses input/output pairs, designing a network configuration for the problem, and finally training the network with input/output pairs until an acceptable error is reached. NETS allows the user to generate C code to implement the network loaded into the system. This permits the placement of networks as components, or subroutines, in other systems. In short, once a network performs satisfactorily, the Generate C Code option provides the means for creating a program separate from NETS to run the network. Other features: files may be stored in binary or ASCII format; multiple input propagation is permitted; bias values may be included; capability to scale data without writing scaling code; quick interactive testing of network from the main menu; and several options that allow the user to manipulate learning efficiency. NETS is written in ANSI standard C language to be machine independent. The Macintosh version (MSC-22108) includes code for both a graphical user interface version and a command line interface version. The machine independent version (MSC-21588) only includes code for the command line interface version of NETS 3.0. The Macintosh version requires a Macintosh II series computer and has been successfully implemented under System 7. Four executables are included on these diskettes, two for floating point operations and two for integer arithmetic. It requires Think C 5.0 to compile. A minimum of 1Mb of RAM is required for execution. Sample input files and executables for both the command line version and the Macintosh user interface version are provided on the distribution medium. The Macintosh version is available on a set of three 3.5 inch 800K Macintosh format diskettes. The machine independent version has been successfully implemented on an IBM PC series compatible running MS-DOS, a DEC VAX running VMS, a SunIPC running SunOS, and a CRAY Y-MP running UNICOS. Two executables for the IBM PC version are included on the MS-DOS distribution media, one compiled for floating point operations and one for integer arithmetic. The machine independent version is available on a set of three 5.25 inch 360K MS-DOS format diskettes (standard distribution medium) or a .25 inch streaming magnetic tape cartridge in UNIX tar format. NETS was developed in 1989 and updated in 1992. IBM PC is a registered trademark of International Business Machines. MS-DOS is a registered trademark of Microsoft Corporation. DEC, VAX, and VMS are trademarks of Digital Equipment Corporation. SunIPC and SunOS are trademarks of Sun Microsystems, Inc. CRAY Y-MP and UNICOS are trademarks of Cray Research, Inc.

NETS - A NEURAL NETWORK DEVELOPMENT TOOL, VERSION 3.0 (MACHINE INDEPENDENT VERSION)

NASA Technical Reports Server (NTRS)

Baffes, P. T.

1994-01-01

NETS, A Tool for the Development and Evaluation of Neural Networks, provides a simulation of Neural Network algorithms plus an environment for developing such algorithms. Neural Networks are a class of systems modeled after the human brain. Artificial Neural Networks are formed from hundreds or thousands of simulated neurons, connected to each other in a manner similar to brain neurons. Problems which involve pattern matching readily fit the class of problems which NETS is designed to solve. NETS uses the back propagation learning method for all of the networks which it creates. The nodes of a network are usually grouped together into clumps called layers. Generally, a network will have an input layer through which the various environment stimuli are presented to the network, and an output layer for determining the network's response. The number of nodes in these two layers is usually tied to some features of the problem being solved. Other layers, which form intermediate stops between the input and output layers, are called hidden layers. NETS allows the user to customize the patterns of connections between layers of a network. NETS also provides features for saving the weight values of a network during the learning process, which allows for more precise control over the learning process. NETS is an interpreter. Its method of execution is the familiar "read-evaluate-print" loop found in interpreted languages such as BASIC and LISP. The user is presented with a prompt which is the simulator's way of asking for input. After a command is issued, NETS will attempt to evaluate the command, which may produce more prompts requesting specific information or an error if the command is not understood. The typical process involved when using NETS consists of translating the problem into a format which uses input/output pairs, designing a network configuration for the problem, and finally training the network with input/output pairs until an acceptable error is reached. NETS allows the user to generate C code to implement the network loaded into the system. This permits the placement of networks as components, or subroutines, in other systems. In short, once a network performs satisfactorily, the Generate C Code option provides the means for creating a program separate from NETS to run the network. Other features: files may be stored in binary or ASCII format; multiple input propagation is permitted; bias values may be included; capability to scale data without writing scaling code; quick interactive testing of network from the main menu; and several options that allow the user to manipulate learning efficiency. NETS is written in ANSI standard C language to be machine independent. The Macintosh version (MSC-22108) includes code for both a graphical user interface version and a command line interface version. The machine independent version (MSC-21588) only includes code for the command line interface version of NETS 3.0. The Macintosh version requires a Macintosh II series computer and has been successfully implemented under System 7. Four executables are included on these diskettes, two for floating point operations and two for integer arithmetic. It requires Think C 5.0 to compile. A minimum of 1Mb of RAM is required for execution. Sample input files and executables for both the command line version and the Macintosh user interface version are provided on the distribution medium. The Macintosh version is available on a set of three 3.5 inch 800K Macintosh format diskettes. The machine independent version has been successfully implemented on an IBM PC series compatible running MS-DOS, a DEC VAX running VMS, a SunIPC running SunOS, and a CRAY Y-MP running UNICOS. Two executables for the IBM PC version are included on the MS-DOS distribution media, one compiled for floating point operations and one for integer arithmetic. The machine independent version is available on a set of three 5.25 inch 360K MS-DOS format diskettes (standard distribution medium) or a .25 inch streaming magnetic tape cartridge in UNIX tar format. NETS was developed in 1989 and updated in 1992. IBM PC is a registered trademark of International Business Machines. MS-DOS is a registered trademark of Microsoft Corporation. DEC, VAX, and VMS are trademarks of Digital Equipment Corporation. SunIPC and SunOS are trademarks of Sun Microsystems, Inc. CRAY Y-MP and UNICOS are trademarks of Cray Research, Inc.

Image Augmentation for Object Image Classification Based On Combination of Pre-Trained CNN and SVM

NASA Astrophysics Data System (ADS)

Shima, Yoshihiro

2018-04-01

Neural networks are a powerful means of classifying object images. The proposed image category classification method for object images combines convolutional neural networks (CNNs) and support vector machines (SVMs). A pre-trained CNN, called Alex-Net, is used as a pattern-feature extractor. Alex-Net is pre-trained for the large-scale object-image dataset ImageNet. Instead of training, Alex-Net, pre-trained for ImageNet is used. An SVM is used as trainable classifier. The feature vectors are passed to the SVM from Alex-Net. The STL-10 dataset are used as object images. The number of classes is ten. Training and test samples are clearly split. STL-10 object images are trained by the SVM with data augmentation. We use the pattern transformation method with the cosine function. We also apply some augmentation method such as rotation, skewing and elastic distortion. By using the cosine function, the original patterns were left-justified, right-justified, top-justified, or bottom-justified. Patterns were also center-justified and enlarged. Test error rate is decreased by 0.435 percentage points from 16.055% by augmentation with cosine transformation. Error rates are increased by other augmentation method such as rotation, skewing and elastic distortion, compared without augmentation. Number of augmented data is 30 times that of the original STL-10 5K training samples. Experimental test error rate for the test 8k STL-10 object images was 15.620%, which shows that image augmentation is effective for image category classification.

Neural-Net Based Optical NDE Method for Structural Health Monitoring

NASA Technical Reports Server (NTRS)

Decker, Arthur J.; Weiland, Kenneth E.

2003-01-01

This paper answers some performance and calibration questions about a non-destructive-evaluation (NDE) procedure that uses artificial neural networks to detect structural damage or other changes from sub-sampled characteristic patterns. The method shows increasing sensitivity as the number of sub-samples increases from 108 to 6912. The sensitivity of this robust NDE method is not affected by noisy excitations of the first vibration mode. A calibration procedure is proposed and demonstrated where the output of a trained net can be correlated with the outputs of the point sensors used for vibration testing. The calibration procedure is based on controlled changes of fastener torques. A heterodyne interferometer is used as a displacement sensor for a demonstration of the challenges to be handled in using standard point sensors for calibration.

Efficient airport detection using region-based fully convolutional neural networks

NASA Astrophysics Data System (ADS)

Xin, Peng; Xu, Yuelei; Zhang, Xulei; Ma, Shiping; Li, Shuai; Lv, Chao

2018-04-01

This paper presents a model for airport detection using region-based fully convolutional neural networks. To achieve fast detection with high accuracy, we shared the conv layers between the region proposal procedure and the airport detection procedure and used graphics processing units (GPUs) to speed up the training and testing time. For lack of labeled data, we transferred the convolutional layers of ZF net pretrained by ImageNet to initialize the shared convolutional layers, then we retrained the model using the alternating optimization training strategy. The proposed model has been tested on an airport dataset consisting of 600 images. Experiments show that the proposed method can distinguish airports in our dataset from similar background scenes almost real-time with high accuracy, which is much better than traditional methods.

Major Upgrades to the AIRS Version-6 Water Vapor Profile Methodology

NASA Technical Reports Server (NTRS)

Susskind, Joel; Blaisdell, John; Iredell, Lena; Lee, Jae N.

2015-01-01

Additional changes in Version-6.19 include all previous updates made to the q(p) retrieval since Version-6: Modified Neural-Net q0(p) guess above the tropopause Linearly tapers the neural net guess to match climatology at 70 mb, not at the top of the atmosphereChanged the 11 trapezoid q(p) perturbation functions used in Version-6 so as to match the 24 functions used in T(p) retrieval step. These modifications resulted in improved water vapor profiles in Version-6.19 compared to Version-6.Version-6.19 is tested for all of August 2013 and August 2014, as well for select other days. Before finalized and operational in 2016, the V-6.19 can be acquired upon request for limited time intervals.

Representing Simple Geometry Types in NetCDF-CF

NASA Astrophysics Data System (ADS)

Blodgett, D. L.; Koziol, B. W.; Whiteaker, T. L.; Simons, R.

2016-12-01

The Climate and Forecast (CF) metadata convention is well-suited for representing gridded and point-based observational datasets. However, CF currently has no accepted mechanism for representing simple geometry types such as lines and polygons. Lack of support for simple geometries within CF has unintentionally excluded a broad set of geoscientific data types from NetCDF-CF data encodings. For example, hydrologic datasets often contain polygon watershed catchments and polyline stream reaches in addition to point sampling stations and water management infrastructure. The latter has an associated CF specification. In the interest of supporting all simple geometry types within CF, a working group was formed following an EarthCube workshop on Advancing NetCDF-CF [1] to draft a CF specification for simple geometries: points, lines, polygons, and their associated multi-geometry representations [2]. The draft also includes parametric geometry types such as circles and ellipses. This presentation will provide an overview of the scope and content of the proposed specification focusing on mechanisms for representing coordinate arrays using variable length or continuous ragged arrays, capturing multi-geometries, and accounting for type-specific geometry artifacts such as polygon holes/interiors, node ordering, etc. The concepts contained in the specification proposal will be described with a use case representing streamflow in rivers and evapotranspiration from HUC12 watersheds. We will also introduce Python and R reference implementations developed alongside the technical specification. These in-development, open source Python and R libraries convert between commonly used GIS software objects (i.e. GEOS-based primitives) and their associated simple geometry CF representation. [1] http://www.unidata.ucar.edu/events/2016CFWorkshop/[2] https://github.com/bekozi/netCDF-CF-simple-geometry

Application of Convolution Neural Network to the forecasts of flare classification and occurrence using SOHO MDI data

NASA Astrophysics Data System (ADS)

Park, Eunsu; Moon, Yong-Jae

2017-08-01

A Convolutional Neural Network(CNN) is one of the well-known deep-learning methods in image processing and computer vision area. In this study, we apply CNN to two kinds of flare forecasting models: flare classification and occurrence. For this, we consider several pre-trained models (e.g., AlexNet, GoogLeNet, and ResNet) and customize them by changing several options such as the number of layers, activation function, and optimizer. Our inputs are the same number of SOHO)/MDI images for each flare class (None, C, M and X) at 00:00 UT from Jan 1996 to Dec 2010 (total 1600 images). Outputs are the results of daily flare forecasting for flare class and occurrence. We build, train, and test the models on TensorFlow, which is well-known machine learning software library developed by Google. Our major results from this study are as follows. First, most of the models have accuracies more than 0.7. Second, ResNet developed by Microsoft has the best accuracies : 0.86 for flare classification and 0.84 for flare occurrence. Third, the accuracies of these models vary greatly with changing parameters. We discuss several possibilities to improve the models.

Center for Aeronautics and Space Information Sciences

NASA Technical Reports Server (NTRS)

Flynn, Michael J.

1992-01-01

This report summarizes the research done during 1991/92 under the Center for Aeronautics and Space Information Science (CASIS) program. The topics covered are computer architecture, networking, and neural nets.

Three case studies of the GasNet model in discrete domains.

PubMed

Santos, C L; de Oliveira, P P; Husbands, P; Souza, C R

2001-06-01

A new neural network model - the GasNet - has been recently reported in the literature, which, in addition to the traditional electric type, point-to-point communication between units, also uses communication through a diffilsable chemical modulator. Here we assess the applicability of this model in three different scenarios, the XOR problem, a food gathering task for a simulated robot, and a docking task for a virtual spaceship. All of them represent discrete domains, a contrast with the one where the GasNet was originally introduced, which had an essentially continuous nature. These scenarios are well-known benchmark problems from the literature and, since they exhibit varying degrees of complexity, they impose distinct performance demands on the GasNet. The experiments were primarily intended to better understand the model, by extending the original problem domain where GasNet was introduced. The results reported point at some difficulties with the current GasNet model.

Achieving supercomputer performance for neural net simulation with an array of digital signal processors

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

Muller, U.A.; Baumle, B.; Kohler, P.

1992-10-01

Music, a DSP-based system with a parallel distributed-memory architecture, provides enormous computing power yet retains the flexibility of a general-purpose computer. Reaching a peak performance of 2.7 Gflops at a significantly lower cost, power consumption, and space requirement than conventional supercomputers, Music is well suited to computationally intensive applications such as neural network simulation. 12 refs., 9 figs., 2 tabs.

Do neural nets learn statistical laws behind natural language?

PubMed

Takahashi, Shuntaro; Tanaka-Ishii, Kumiko

2017-01-01

The performance of deep learning in natural language processing has been spectacular, but the reasons for this success remain unclear because of the inherent complexity of deep learning. This paper provides empirical evidence of its effectiveness and of a limitation of neural networks for language engineering. Precisely, we demonstrate that a neural language model based on long short-term memory (LSTM) effectively reproduces Zipf's law and Heaps' law, two representative statistical properties underlying natural language. We discuss the quality of reproducibility and the emergence of Zipf's law and Heaps' law as training progresses. We also point out that the neural language model has a limitation in reproducing long-range correlation, another statistical property of natural language. This understanding could provide a direction for improving the architectures of neural networks.

Optical computing and neural networks; Proceedings of the Meeting, National Chiao Tung Univ., Hsinchu, Taiwan, Dec. 16, 17, 1992

NASA Technical Reports Server (NTRS)

Hsu, Ken-Yuh (Editor); Liu, Hua-Kuang (Editor)

1992-01-01

The present conference discusses optical neural networks, photorefractive nonlinear optics, optical pattern recognition, digital and analog processors, and holography and its applications. Attention is given to bifurcating optical information processing, neural structures in digital halftoning, an exemplar-based optical neural net classifier for color pattern recognition, volume storage in photorefractive disks, and microlaser-based compact optical neuroprocessors. Also treated are the optical implementation of a feature-enhanced optical interpattern-associative neural network model and its optical implementation, an optical pattern binary dual-rail logic gate module, a theoretical analysis for holographic associative memories, joint transform correlators, image addition and subtraction via the Talbot effect, and optical wavelet-matched filters. (No individual items are abstracted in this volume)

Optical computing and neural networks; Proceedings of the Meeting, National Chiao Tung Univ., Hsinchu, Taiwan, Dec. 16, 17, 1992

NASA Astrophysics Data System (ADS)

Hsu, Ken-Yuh; Liu, Hua-Kuang

The present conference discusses optical neural networks, photorefractive nonlinear optics, optical pattern recognition, digital and analog processors, and holography and its applications. Attention is given to bifurcating optical information processing, neural structures in digital halftoning, an exemplar-based optical neural net classifier for color pattern recognition, volume storage in photorefractive disks, and microlaser-based compact optical neuroprocessors. Also treated are the optical implementation of a feature-enhanced optical interpattern-associative neural network model and its optical implementation, an optical pattern binary dual-rail logic gate module, a theoretical analysis for holographic associative memories, joint transform correlators, image addition and subtraction via the Talbot effect, and optical wavelet-matched filters. (No individual items are abstracted in this volume)

Do neural nets learn statistical laws behind natural language?

PubMed Central

Takahashi, Shuntaro

2017-01-01

The performance of deep learning in natural language processing has been spectacular, but the reasons for this success remain unclear because of the inherent complexity of deep learning. This paper provides empirical evidence of its effectiveness and of a limitation of neural networks for language engineering. Precisely, we demonstrate that a neural language model based on long short-term memory (LSTM) effectively reproduces Zipf’s law and Heaps’ law, two representative statistical properties underlying natural language. We discuss the quality of reproducibility and the emergence of Zipf’s law and Heaps’ law as training progresses. We also point out that the neural language model has a limitation in reproducing long-range correlation, another statistical property of natural language. This understanding could provide a direction for improving the architectures of neural networks. PMID:29287076

Automation of Some Operations of a Wind Tunnel Using Artificial Neural Networks

NASA Technical Reports Server (NTRS)

Decker, Arthur J.; Buggele, Alvin E.

1996-01-01

Artificial neural networks were used successfully to sequence operations in a small, recently modernized, supersonic wind tunnel at NASA-Lewis Research Center. The neural nets generated correct estimates of shadowgraph patterns, pressure sensor readings and mach numbers for conditions occurring shortly after startup and extending to fully developed flow. Artificial neural networks were trained and tested for estimating: sensor readings from shadowgraph patterns, shadowgraph patterns from shadowgraph patterns and sensor readings from sensor readings. The 3.81 by 10 in. (0.0968 by 0.254 m) tunnel was operated with its mach 2.0 nozzle, and shadowgraph was recorded near the nozzle exit. These results support the thesis that artificial neural networks can be combined with current workstation technology to automate wind tunnel operations.

Visualizing the spinal neuronal dynamics of locomotion

NASA Astrophysics Data System (ADS)

Subramanian, Kalpathi R.; Bashor, D. P.; Miller, M. T.; Foster, J. A.

2004-06-01

Modern imaging and simulation techniques have enhanced system-level understanding of neural function. In this article, we present an application of interactive visualization to understanding neuronal dynamics causing locomotion of a single hip joint, based on pattern generator output of the spinal cord. Our earlier work visualized cell-level responses of multiple neuronal populations. However, the spatial relationships were abstract, making communication with colleagues difficult. We propose two approaches to overcome this: (1) building a 3D anatomical model of the spinal cord with neurons distributed inside, animated by the simulation and (2) adding limb movements predicted by neuronal activity. The new system was tested using a cat walking central pattern generator driving a pair of opposed spinal motoneuron pools. Output of opposing motoneuron pools was combined into a single metric, called "Net Neural Drive", which generated angular limb movement in proportion to its magnitude. Net neural drive constitutes a new description of limb movement control. The combination of spatial and temporal information in the visualizations elegantly conveys the neural activity of the output elements (motoneurons), as well as the resulting movement. The new system encompasses five biological levels of organization from ion channels to observed behavior. The system is easily scalable, and provides an efficient interactive platform for rapid hypothesis testing.

Identification and interpretation of patterns in rocket engine data: Artificial intelligence and neural network approaches

NASA Technical Reports Server (NTRS)

Ali, Moonis; Whitehead, Bruce; Gupta, Uday K.; Ferber, Harry

1989-01-01

This paper describes an expert system which is designed to perform automatic data analysis, identify anomalous events, and determine the characteristic features of these events. We have employed both artificial intelligence and neural net approaches in the design of this expert system. The artificial intelligence approach is useful because it provides (1) the use of human experts' knowledge of sensor behavior and faulty engine conditions in interpreting data; (2) the use of engine design knowledge and physical sensor locations in establishing relationships among the events of multiple sensors; (3) the use of stored analysis of past data of faulty engine conditions; and (4) the use of knowledge-based reasoning in distinguishing sensor failure from actual faults. The neural network approach appears promising because neural nets (1) can be trained on extremely noisy data and produce classifications which are more robust under noisy conditions than other classification techniques; (2) avoid the necessity of noise removal by digital filtering and therefore avoid the need to make assumptions about frequency bands or other signal characteristics of anomalous behavior; (3) can, in effect, generate their own feature detectors based on the characteristics of the sensor data used in training; and (4) are inherently parallel and therefore are potentially implementable in special-purpose parallel hardware.

Correlational Neural Networks.

PubMed

Chandar, Sarath; Khapra, Mitesh M; Larochelle, Hugo; Ravindran, Balaraman

2016-02-01

Common representation learning (CRL), wherein different descriptions (or views) of the data are embedded in a common subspace, has been receiving a lot of attention recently. Two popular paradigms here are canonical correlation analysis (CCA)-based approaches and autoencoder (AE)-based approaches. CCA-based approaches learn a joint representation by maximizing correlation of the views when projected to the common subspace. AE-based methods learn a common representation by minimizing the error of reconstructing the two views. Each of these approaches has its own advantages and disadvantages. For example, while CCA-based approaches outperform AE-based approaches for the task of transfer learning, they are not as scalable as the latter. In this work, we propose an AE-based approach, correlational neural network (CorrNet), that explicitly maximizes correlation among the views when projected to the common subspace. Through a series of experiments, we demonstrate that the proposed CorrNet is better than AE and CCA with respect to its ability to learn correlated common representations. We employ CorrNet for several cross-language tasks and show that the representations learned using it perform better than the ones learned using other state-of-the-art approaches.

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.

Theory of mind in schizophrenia: exploring neural mechanisms of belief attribution.

PubMed

Lee, Junghee; Quintana, Javier; Nori, Poorang; Green, Michael F

2011-01-01

Although previous behavioral studies have shown that schizophrenia patients have impaired theory of mind (ToM), the neural mechanisms associated with this impairment are poorly understood. This study aimed to identify the neural mechanisms of ToM in schizophrenia, using functional magnetic resonance imaging (fMRI) with a belief attribution task. In the scanner, 12 schizophrenia patients and 13 healthy control subjects performed the belief attribution task with three conditions: a false belief condition, a false photograph condition, and a simple reading condition. For the false belief versus simple reading conditions, schizophrenia patients showed reduced neural activation in areas including the temporoparietal junction (TPJ) and medial prefrontal cortex (MPFC) compared with controls. Further, during the false belief versus false photograph conditions, we observed increased activations in the TPJ and the MPFC in healthy controls, but not in schizophrenia patients. For the false photograph versus simple reading condition, both groups showed comparable neural activations. Schizophrenia patients showed reduced task-related activation in the TPJ and the MPFC during the false belief condition compared with controls, but not for the false photograph condition. This pattern suggests that reduced activation in these regions is associated with, and specific to, impaired ToM in schizophrenia.

Simple techniques for improving deep neural network outcomes on commodity hardware

NASA Astrophysics Data System (ADS)

Colina, Nicholas Christopher A.; Perez, Carlos E.; Paraan, Francis N. C.

2017-08-01

We benchmark improvements in the performance of deep neural networks (DNN) on the MNIST data test upon imple-menting two simple modifications to the algorithm that have little overhead computational cost. First is GPU parallelization on a commodity graphics card, and second is initializing the DNN with random orthogonal weight matrices prior to optimization. Eigenspectra analysis of the weight matrices reveal that the initially orthogonal matrices remain nearly orthogonal after training. The probability distributions from which these orthogonal matrices are drawn are also shown to significantly affect the performance of these deep neural networks.

Information at the edge of chaos in fluid neural networks

NASA Astrophysics Data System (ADS)

Solé, Ricard V.; Miramontes, Octavio

1995-01-01

Fluid neural networks, defined as neural nets of mobile elements with random activation, are studied by means of several approaches. They are proposed as a theoretical framework for a wide class of systems as insect societies, collectives of robots or the immune system. The critical properties of this model are also analysed, showing the existence of a critical boundary in parameter space where maximum information transfer occurs. In this sense, this boundary is in fact an example of the “edge of chaos” in systems like those described in our approach. Recent experiments with ant colonies seem to confirm our result.

Programmable Analog Memory Resistors For Electronic Neural Networks

NASA Technical Reports Server (NTRS)

Ramesham, Rajeshuni; Thakoor, Sarita; Daud, Taher; Thakoor, Anilkumar P.

1990-01-01

Electrical resistance of new solid-state device altered repeatedly by suitable control signals, yet remains at steady value when control signal removed. Resistance set at low value ("on" state), high value ("off" state), or at any convenient intermediate value and left there until new value desired. Circuits of this type particularly useful in nonvolatile, associative electronic memories based on models of neural networks. Such programmable analog memory resistors ideally suited as synaptic interconnects in "self-learning" neural nets. Operation of device depends on electrochromic property of WO3, which when pure is insulator. Potential uses include nonvolatile, erasable, electronically programmable read-only memories.

Two-Dimensional High-Lift Aerodynamic Optimization Using Neural Networks

NASA Technical Reports Server (NTRS)

Greenman, Roxana M.

1998-01-01

The high-lift performance of a multi-element airfoil was optimized by using neural-net predictions that were trained using a computational data set. The numerical data was generated using a two-dimensional, incompressible, Navier-Stokes algorithm with the Spalart-Allmaras turbulence model. Because it is difficult to predict maximum lift for high-lift systems, an empirically-based maximum lift criteria was used in this study to determine both the maximum lift and the angle at which it occurs. The 'pressure difference rule,' which states that the maximum lift condition corresponds to a certain pressure difference between the peak suction pressure and the pressure at the trailing edge of the element, was applied and verified with experimental observations for this configuration. Multiple input, single output networks were trained using the NASA Ames variation of the Levenberg-Marquardt algorithm for each of the aerodynamic coefficients (lift, drag and moment). The artificial neural networks were integrated with a gradient-based optimizer. Using independent numerical simulations and experimental data for this high-lift configuration, it was shown that this design process successfully optimized flap deflection, gap, overlap, and angle of attack to maximize lift. Once the neural nets were trained and integrated with the optimizer, minimal additional computer resources were required to perform optimization runs with different initial conditions and parameters. Applying the neural networks within the high-lift rigging optimization process reduced the amount of computational time and resources by 44% compared with traditional gradient-based optimization procedures for multiple optimization runs.

Simulation of an array-based neural net model

NASA Technical Reports Server (NTRS)

Barnden, John A.

1987-01-01

Research in cognitive science suggests that much of cognition involves the rapid manipulation of complex data structures. However, it is very unclear how this could be realized in neural networks or connectionist systems. A core question is: how could the interconnectivity of items in an abstract-level data structure be neurally encoded? The answer appeals mainly to positional relationships between activity patterns within neural arrays, rather than directly to neural connections in the traditional way. The new method was initially devised to account for abstract symbolic data structures, but it also supports cognitively useful spatial analogue, image-like representations. As the neural model is based on massive, uniform, parallel computations over 2D arrays, the massively parallel processor is a convenient tool for simulation work, although there are complications in using the machine to the fullest advantage. An MPP Pascal simulation program for a small pilot version of the model is running.

Neural networks for vertical microcode compaction

NASA Astrophysics Data System (ADS)

Chu, Pong P.

1992-09-01

Neural networks provide an alternative way to solve complex optimization problems. Instead of performing a program of instructions sequentially as in a traditional computer, neural network model explores many competing hypotheses simultaneously using its massively parallel net. The paper shows how to use the neural network approach to perform vertical micro-code compaction for a micro-programmed control unit. The compaction procedure includes two basic steps. The first step determines the compatibility classes and the second step selects a minimal subset to cover the control signals. Since the selection process is an NP- complete problem, to find an optimal solution is impractical. In this study, we employ a customized neural network to obtain the minimal subset. We first formalize this problem, and then define an `energy function' and map it to a two-layer fully connected neural network. The modified network has two types of neurons and can always obtain a valid solution.

Exploring the neural bases of goal-directed motor behavior using fully resolved simulations

NASA Astrophysics Data System (ADS)

Patel, Namu; Patankar, Neelesh A.

2016-11-01

Undulatory swimming is an ideal problem for understanding the neural architecture for motor control and movement; a vertebrate's robust morphology and adaptive locomotive gait allows the swimmer to navigate complex environments. Simple mathematical models for neurally activated muscle contractions have been incorporated into a swimmer immersed in fluid. Muscle contractions produce bending moments which determine the swimming kinematics. The neurobiology of goal-directed locomotion is explored using fast, efficient, and fully resolved constraint-based immersed boundary simulations. Hierarchical control systems tune the strength, frequency, and duty cycle for neural activation waves to produce multifarious swimming gaits or synergies. Simulation results are used to investigate why the basal ganglia and other control systems may command a particular neural pattern to accomplish a task. Using simple neural models, the effect of proprioceptive feedback on refining the body motion is demonstrated. Lastly, the ability for a learned swimmer to successfully navigate a complex environment is tested. This work is supported by NSF CBET 1066575 and NSF CMMI 0941674.

Background considerations in the analysis of PIXE spectra by Artificial Neural Systems.

NASA Astrophysics Data System (ADS)

Correa, R.; Morales, J. R.; Requena, I.; Miranda, J.; Barrera, V. A.

2016-05-01

In order to study the importance of background in PIXE spectra to determine elemental concentrations in atmospheric aerosols using artificial neural systems ANS, two independently trained ANS were constructed, one which considered as input the net number of counts in the peak, and another which included the background. In the training and validation phases thirty eight spectra of aerosols collected in Santiago, Chile, were used. In both cases the elemental concentration values were similar. This fact was due to the intrinsic characteristic of ANS operating with normalized values of the net and total number of counts under the peaks, something that was verified in the analysis of 172 spectra obtained from aerosols collected in Mexico city. Therefore, networks operating under the mode which include background can reduce time and cost when dealing with large number of samples.

Machine-learning in astronomy

NASA Astrophysics Data System (ADS)

Hobson, Michael; Graff, Philip; Feroz, Farhan; Lasenby, Anthony

2014-05-01

Machine-learning methods may be used to perform many tasks required in the analysis of astronomical data, including: data description and interpretation, pattern recognition, prediction, classification, compression, inference and many more. An intuitive and well-established approach to machine learning is the use of artificial neural networks (NNs), which consist of a group of interconnected nodes, each of which processes information that it receives and then passes this product on to other nodes via weighted connections. In particular, I discuss the first public release of the generic neural network training algorithm, called SkyNet, and demonstrate its application to astronomical problems focusing on its use in the BAMBI package for accelerated Bayesian inference in cosmology, and the identification of gamma-ray bursters. The SkyNet and BAMBI packages, which are fully parallelised using MPI, are available at http://www.mrao.cam.ac.uk/software/.

Sensitivity and Calibration of Non-Destructive Evaluation Method That Uses Neural-Net Processing of Characteristic Fringe Patterns

NASA Technical Reports Server (NTRS)

Decker, Arthur J.; Weiland, Kenneth E.

2003-01-01

This paper answers some performance and calibration questions about a non-destructive-evaluation (NDE) procedure that uses artificial neural networks to detect structural damage or other changes from sub-sampled characteristic patterns. The method shows increasing sensitivity as the number of sub-samples increases from 108 to 6912. The sensitivity of this robust NDE method is not affected by noisy excitations of the first vibration mode. A calibration procedure is proposed and demonstrated where the output of a trained net can be correlated with the outputs of the point sensors used for vibration testing. The calibration procedure is based on controlled changes of fastener torques. A heterodyne interferometer is used as a displacement sensor for a demonstration of the challenges to be handled in using standard point sensors for calibration.

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.

Computer graphics testbed to simulate and test vision systems for space applications

NASA Technical Reports Server (NTRS)

Cheatham, John B.

1991-01-01

Artificial intelligence concepts are applied to robotics. Artificial neural networks, expert systems and laser imaging techniques for autonomous space robots are being studied. A computer graphics laser range finder simulator developed by Wu has been used by Weiland and Norwood to study use of artificial neural networks for path planning and obstacle avoidance. Interest is expressed in applications of CLIPS, NETS, and Fuzzy Control. These applications are applied to robot navigation.

DeepMoon: Convolutional neural network trainer to identify moon craters

NASA Astrophysics Data System (ADS)

Silburt, Ari; Zhu, Chenchong; Ali-Dib, Mohamad; Menou, Kristen; Jackson, Alan

2018-05-01

DeepMoon trains a convolutional neural net using data derived from a global digital elevation map (DEM) and catalog of craters to recognize craters on the Moon. The TensorFlow-based pipeline code is divided into three parts. The first generates a set images of the Moon randomly cropped from the DEM, with corresponding crater positions and radii. The second trains a convnet using this data, and the third validates the convnet's predictions.

Curved Solids Nets

ERIC Educational Resources Information Center

Cohen, Nitsa

2003-01-01

The transformation of a solid to its net is based on something quite different from simple perceptual impression. It is a mental operation performed by manipulating mental images. The aim of this study was to observe pre-service and in-service teachers' ability to visualize the transformation of a curved solid to its net and vice versa, and to try…

Classification of foods by transferring knowledge from ImageNet dataset

NASA Astrophysics Data System (ADS)

Heravi, Elnaz J.; Aghdam, Hamed H.; Puig, Domenec

2017-03-01

Automatic classification of foods is a way to control food intake and tackle with obesity. However, it is a challenging problem since foods are highly deformable and complex objects. Results on ImageNet dataset have revealed that Convolutional Neural Network has a great expressive power to model natural objects. Nonetheless, it is not trivial to train a ConvNet from scratch for classification of foods. This is due to the fact that ConvNets require large datasets and to our knowledge there is not a large public dataset of food for this purpose. Alternative solution is to transfer knowledge from trained ConvNets to the domain of foods. In this work, we study how transferable are state-of-art ConvNets to the task of food classification. We also propose a method for transferring knowledge from a bigger ConvNet to a smaller ConvNet by keeping its accuracy similar to the bigger ConvNet. Our experiments on UECFood256 datasets show that Googlenet, VGG and residual networks produce comparable results if we start transferring knowledge from appropriate layer. In addition, we show that our method is able to effectively transfer knowledge to the smaller ConvNet using unlabeled samples.

A potential inhibitory function of draxin in regulating mouse trunk neural crest migration.

PubMed

Zhang, Sanbing; Su, Yuhong; Gao, Jinbao; Zhang, Chenbing; Tanaka, Hideaki

2017-01-01

Draxin is a repulsive axon guidance protein that plays important roles in the formation of three commissures in the central nervous system and dorsal interneuron 3 (dI3) in the chick spinal cord. In the present study, we report the expression pattern of mouse draxin in the embryonic mouse trunk spinal cord. In the presence of draxin, the longest net migration length of a migrating mouse trunk neural crest cell was significantly reduced. In addition, the relative number of apolar neural crest cells increased as the draxin treatment time increased. Draxin caused actin cytoskeleton rearrangement in the migrating trunk neural crest cells. Our data suggest that draxin may regulate mouse trunk neural crest cell migration by the rearrangement of cell actin cytoskeleton and by reducing the polarization activity of these cells subsequently.

Are artificial neural networks black boxes?

PubMed

Benitez, J M; Castro, J L; Requena, I

1997-01-01

Artificial neural networks are efficient computing models which have shown their strengths in solving hard problems in artificial intelligence. They have also been shown to be universal approximators. Notwithstanding, one of the major criticisms is their being black boxes, since no satisfactory explanation of their behavior has been offered. In this paper, we provide such an interpretation of neural networks so that they will no longer be seen as black boxes. This is stated after establishing the equality between a certain class of neural nets and fuzzy rule-based systems. This interpretation is built with fuzzy rules using a new fuzzy logic operator which is defined after introducing the concept of f-duality. In addition, this interpretation offers an automated knowledge acquisition procedure.

Use of probabilistic neural networks for emitter correlation

NASA Astrophysics Data System (ADS)

Maloney, P. S.

1990-08-01

The Probabilistic Neural Network (PNN) as described by Specht''3 has been successfully applied to a number of emitter correlation problems involving operational data for training and testing of the neural net work. The PNN has been found to be a reliable classification tool for determining emitter type or even identifying specific emitter platforms given appropriate representative data sets for training con sisting only of parametric data from electronic intelligence (ELINT) reports. Four separate feasibility studies have been conducted to prove the usefulness of PNN in this application area: . Hull-to-emitter correlation (HULTEC) for identification of seagoing emitter platforms . Identification of landbased emitters from airborne sensors . Pulse sorting according to emitter of origin . Emitter typing based on a dynamically learning neural network. 1 .

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.

Neural network based architectures for aerospace applications

NASA Technical Reports Server (NTRS)

Ricart, Richard

1987-01-01

A brief history of the field of neural networks research is given and some simple concepts are described. In addition, some neural network based avionics research and development programs are reviewed. The need for the United States Air Force and NASA to assume a leadership role in supporting this technology is stressed.

Neural Networks for Handwritten English Alphabet Recognition

NASA Astrophysics Data System (ADS)

Perwej, Yusuf; Chaturvedi, Ashish

2011-04-01

This paper demonstrates the use of neural networks for developing a system that can recognize hand-written English alphabets. In this system, each English alphabet is represented by binary values that are used as input to a simple feature extraction system, whose output is fed to our neural network system.

The process of learning in neural net models with Poisson and Gauss connectivities.

PubMed

Sivridis, L; Kotini, A; Anninos, P

2008-01-01

In this study we examined the dynamic behavior of isolated and non-isolated neural networks with chemical markers that follow a Poisson or Gauss distribution of connectivity. The Poisson distribution shows higher activity in comparison to the Gauss distribution although the latter has more connections that obliterated due to randomness. We examined 57 hematoxylin and eosin stained sections from an equal number of autopsy specimens with a diagnosis of "cerebral matter within normal limits". Neural counting was carried out in 5 continuous optic fields, with the use of a simple optical microscope connected to a computer (software programmer Nikon Act-1 vers-2). The number of neurons that corresponded to a surface was equal to 0.15 mm(2). There was a gradual reduction in the number of neurons as age increased. A mean value of 45.8 neurons /0.15 mm(2) was observed within the age range 21-25, 33 neurons /0.15 mm(2) within the age range 41-45, 19.3 neurons /0.15 mm(2) within the age range 56-60 years. After the age of 60 it was observed that the number of neurons per unit area stopped decreasing. A correlation was observed between these experimental findings and the theoretical neural model developed by professor Anninos and his colleagues. Equivalence between the mean numbers of neurons of the above mentioned age groups and the highest possible number of synaptic connections per neuron (highest number of synaptic connections corresponded to the age group 21-25) was created. We then used both inhibitory and excitatory post-synaptic potentials and applied these values to the Poisson and Gauss distributions, whereas the neuron threshold was varied between 3 and 5. According to the obtained phase diagrams, the hysteresis loops decrease as age increases. These findings were significant as the hysteresis loops can be regarded as the basis for short-term memory.

Innovation and application of ANN in Europe demonstrated by Kohonen maps

NASA Technical Reports Server (NTRS)

Goser, Karl

1994-01-01

One of the most important contributions to neural networks comes from Kohonen, Helsinki/Espoo, Finland, who had the idea of self-organizating maps in 1981. He verified his idea by an algorithm of which many applications make use of. The impetus for this idea came from biology, a field where the Europeans have always been very active at several research laboratories. The challenge was to model the self-organization found in the brain. Today one goal is the development of more sophisticated neurons which model the biological neurons more exactly. They should come to a better performance of neural nets with only a few complex neurons instead of many simple ones. A lot of application concepts arise from this idea: Kohonen himself applied it to speech recognition, but the project did not overcome much more than the recognition of the numerals one to ten at that time. A more promising application for self-organizing maps is process control and process monitoring. Several proposals were made which concern parameter classification of semiconductor technologies, design of integrated circuits, and control of chemical processes. Self-organizing maps were applied to robotics. The neural concept was introduced into electric power systems. At Dortmund we are working on a system which has to monitor the quality and the reliability of gears and electrical motors in equipment installed in coal mines. The results are promising and the probability to apply the system in the field is very high. A special feature of the system is that linguistic rules which are embedded in a fuzzy controller analyze the data of the self-organizing map in regard to life expectation of the gears. It seems that the fuzzy technique will introduce the technology of neural networks in a tandem mode. These technologies together with the genetic algorithms start to form the attractive field of computational intelligence.

NeMO-Net & Fluid Lensing: The Neural Multi-Modal Observation & Training Network for Global Coral Reef Assessment Using Fluid Lensing Augmentation of NASA EOS Data

NASA Technical Reports Server (NTRS)

Chirayath, Ved

2018-01-01

We present preliminary results from NASA NeMO-Net, the first neural multi-modal observation and training network for global coral reef assessment. NeMO-Net is an open-source deep convolutional neural network (CNN) and interactive active learning training software in development which will assess the present and past dynamics of coral reef ecosystems. NeMO-Net exploits active learning and data fusion of mm-scale remotely sensed 3D images of coral reefs captured using fluid lensing with the NASA FluidCam instrument, presently the highest-resolution remote sensing benthic imaging technology capable of removing ocean wave distortion, as well as hyperspectral airborne remote sensing data from the ongoing NASA CORAL mission and lower-resolution satellite data to determine coral reef ecosystem makeup globally at unprecedented spatial and temporal scales. Aquatic ecosystems, particularly coral reefs, remain quantitatively misrepresented by low-resolution remote sensing as a result of refractive distortion from ocean waves, optical attenuation, and remoteness. Machine learning classification of coral reefs using FluidCam mm-scale 3D data show that present satellite and airborne remote sensing techniques poorly characterize coral reef percent living cover, morphology type, and species breakdown at the mm, cm, and meter scales. Indeed, current global assessments of coral reef cover and morphology classification based on km-scale satellite data alone can suffer from segmentation errors greater than 40%, capable of change detection only on yearly temporal scales and decameter spatial scales, significantly hindering our understanding of patterns and processes in marine biodiversity at a time when these ecosystems are experiencing unprecedented anthropogenic pressures, ocean acidification, and sea surface temperature rise. NeMO-Net leverages our augmented machine learning algorithm that demonstrates data fusion of regional FluidCam (mm, cm-scale) airborne remote sensing with global low-resolution (m, km-scale) airborne and spaceborne imagery to reduce classification errors up to 80% over regional scales. Such technologies can substantially enhance our ability to assess coral reef ecosystems dynamics.

Mission Driven Scene Understanding: Candidate Model Training and Validation

DTIC Science & Technology

2016-09-01

driven scene understanding. One of the candidate engines that we are evaluating is a convolutional neural network (CNN) program installed on a Windows 10...Theano-AlexNet6,7) installed on a Windows 10 notebook computer. To the best of our knowledge, an implementation of the open-source, Python-based...AlexNet CNN on a Windows notebook computer has not been previously reported. In this report, we present progress toward the proof-of-principle testing

Automatic Detection of Landslides at Stromboli Volcano

NASA Astrophysics Data System (ADS)

Giudicepietro, F.; Esposito, A. M.; D'Auria, L.; Peluso, R.; Martini, M.

2011-12-01

In this work we present an automatic system for the landslide detection at Stromboli volcano that has proved to be effective both during the 2007 effusive eruption and in the recent (2 August 2011) volcanic activity. The study of the landslides at Stromboli is important because they could be considered short-term precursors of effusive eruptions, as seen during the 2007 eruption, and in addition they allow to improve the monitoring of the gravitational instabilities of the Sciara del Fuoco flank. The proposed system uses a two-class MLP (Multi Layer Perceptron) neural network in order to discriminate the landslides from other seismic signals usually recorded at Stromboli, such as explosion-quakes and volcanic tremor. To train and test the network we used a dataset of 537 signals, including 267 landslides and 270 other events (130 explosion-quakes and 140 tremor signals). The net performance is of 98.7%, if averaged over different net configurations, and of 99.5% for the best net performance. Based on the neural network response, the automatic system calculates a Landslide Percentage Index (LPI) defined on the number of signals identified as landslides by the net on a given temporal interval in order to recognize anomalies in the landslide rate. This system was sensitive to the signals produced by the flow of lava front during a recent mild effusive episode on the "La Sciara del Fuoco" slope.

Petri net controllers for distributed robotic systems

NASA Technical Reports Server (NTRS)

Lefebvre, D. R.; Saridis, George N.

1992-01-01

Petri nets are a well established modelling technique for analyzing parallel systems. When coupled with an event-driven operating system, Petri nets can provide an effective means for integrating and controlling the functions of distributed robotic applications. Recent work has shown that Petri net graphs can also serve as remarkably intuitive operator interfaces. In this paper, the advantages of using Petri nets as high-level controllers to coordinate robotic functions are outlined, the considerations for designing Petri net controllers are discussed, and simple Petri net structures for implementing an interface for operator supervision are presented. A detailed example is presented which illustrates these concepts for a sensor-based assembly application.

Selective and Efficient Neural Coding of Communication Signals Depends on Early Acoustic and Social Environment

PubMed Central

Amin, Noopur; Gastpar, Michael; Theunissen, Frédéric E.

2013-01-01

Previous research has shown that postnatal exposure to simple, synthetic sounds can affect the sound representation in the auditory cortex as reflected by changes in the tonotopic map or other relatively simple tuning properties, such as AM tuning. However, their functional implications for neural processing in the generation of ethologically-based perception remain unexplored. Here we examined the effects of noise-rearing and social isolation on the neural processing of communication sounds such as species-specific song, in the primary auditory cortex analog of adult zebra finches. Our electrophysiological recordings reveal that neural tuning to simple frequency-based synthetic sounds is initially established in all the laminae independent of patterned acoustic experience; however, we provide the first evidence that early exposure to patterned sound statistics, such as those found in native sounds, is required for the subsequent emergence of neural selectivity for complex vocalizations and for shaping neural spiking precision in superficial and deep cortical laminae, and for creating efficient neural representations of song and a less redundant ensemble code in all the laminae. Our study also provides the first causal evidence for ‘sparse coding’, such that when the statistics of the stimuli were changed during rearing, as in noise-rearing, that the sparse or optimal representation for species-specific vocalizations disappeared. Taken together, these results imply that a layer-specific differential development of the auditory cortex requires patterned acoustic input, and a specialized and robust sensory representation of complex communication sounds in the auditory cortex requires a rich acoustic and social environment. PMID:23630587

Deep Learning at Chest Radiography: Automated Classification of Pulmonary Tuberculosis by Using Convolutional Neural Networks.

PubMed

Lakhani, Paras; Sundaram, Baskaran

2017-08-01

Purpose To evaluate the efficacy of deep convolutional neural networks (DCNNs) for detecting tuberculosis (TB) on chest radiographs. Materials and Methods Four deidentified HIPAA-compliant datasets were used in this study that were exempted from review by the institutional review board, which consisted of 1007 posteroanterior chest radiographs. The datasets were split into training (68.0%), validation (17.1%), and test (14.9%). Two different DCNNs, AlexNet and GoogLeNet, were used to classify the images as having manifestations of pulmonary TB or as healthy. Both untrained and pretrained networks on ImageNet were used, and augmentation with multiple preprocessing techniques. Ensembles were performed on the best-performing algorithms. For cases where the classifiers were in disagreement, an independent board-certified cardiothoracic radiologist blindly interpreted the images to evaluate a potential radiologist-augmented workflow. Receiver operating characteristic curves and areas under the curve (AUCs) were used to assess model performance by using the DeLong method for statistical comparison of receiver operating characteristic curves. Results The best-performing classifier had an AUC of 0.99, which was an ensemble of the AlexNet and GoogLeNet DCNNs. The AUCs of the pretrained models were greater than that of the untrained models (P < .001). Augmenting the dataset further increased accuracy (P values for AlexNet and GoogLeNet were .03 and .02, respectively). The DCNNs had disagreement in 13 of the 150 test cases, which were blindly reviewed by a cardiothoracic radiologist, who correctly interpreted all 13 cases (100%). This radiologist-augmented approach resulted in a sensitivity of 97.3% and specificity 100%. Conclusion Deep learning with DCNNs can accurately classify TB at chest radiography with an AUC of 0.99. A radiologist-augmented approach for cases where there was disagreement among the classifiers further improved accuracy. © RSNA, 2017.

Theory of mind in schizophrenia: Exploring neural mechanisms of belief attribution

PubMed Central

Lee, Junghee; Quintana, Javier; Nori, Poorang; Green, Michael F.

2014-01-01

Background Although previous behavioral studies have shown that schizophrenia patients have impaired theory of mind (ToM), the neural mechanisms associated with this impairment are poorly understood. This study aimed to identify the neural mechanisms of ToM in schizophrenia using functional magnetic resonance imaging (fMRI) with a Belief Attribution Task. Methods In the scanner, 12 schizophrenia patients and 13 healthy control subjects performed the Belief Attribution Task with 3 conditions: a false belief condition, a false photograph condition, and a simple reading condition. Results For the false belief vs. simple reading conditions, schizophrenia patients showed reduced neural activation in areas including the temporo-parietal junction (TPJ) and medial prefrontal cortex (MPFC) compared with controls. Further, during the false belief vs. false photograph conditions we observed increased activations in the TPJ and the MPFC in healthy controls, but not in schizophrenia patients. For the false photograph vs. simple reading condition, both groups showed comparable neural activations. Conclusions Schizophrenia patients showed reduced task-related activation in the TPJ and the MPFC during the false belief condition compared with controls, but not for the false photograph condition. This pattern suggests that reduced activation in these regions is associated with, and specific to, impaired ToM in schizophrenia. PMID:22050432

Controlling basins of attraction in a neural network-based telemetry monitor

NASA Technical Reports Server (NTRS)

Bell, Benjamin; Eilbert, James L.

1988-01-01

The size of the basins of attraction around fixed points in recurrent neural nets (NNs) can be modified by a training process. Controlling these attractive regions by presenting training data with various amount of noise added to the prototype signal vectors is discussed. Application of this technique to signal processing results in a classification system whose sensitivity can be controlled. This new technique is applied to the classification of temporal sequences in telemetry data.

Forecasting space weather: Can new econometric methods improve accuracy?

NASA Astrophysics Data System (ADS)

Reikard, Gordon

2011-06-01

Space weather forecasts are currently used in areas ranging from navigation and communication to electric power system operations. The relevant forecast horizons can range from as little as 24 h to several days. This paper analyzes the predictability of two major space weather measures using new time series methods, many of them derived from econometrics. The data sets are the A p geomagnetic index and the solar radio flux at 10.7 cm. The methods tested include nonlinear regressions, neural networks, frequency domain algorithms, GARCH models (which utilize the residual variance), state transition models, and models that combine elements of several techniques. While combined models are complex, they can be programmed using modern statistical software. The data frequency is daily, and forecasting experiments are run over horizons ranging from 1 to 7 days. Two major conclusions stand out. First, the frequency domain method forecasts the A p index more accurately than any time domain model, including both regressions and neural networks. This finding is very robust, and holds for all forecast horizons. Combining the frequency domain method with other techniques yields a further small improvement in accuracy. Second, the neural network forecasts the solar flux more accurately than any other method, although at short horizons (2 days or less) the regression and net yield similar results. The neural net does best when it includes measures of the long-term component in the data.

Damage Detection Using Holography and Interferometry

NASA Technical Reports Server (NTRS)

Decker, Arthur J.

2003-01-01

This paper reviews classical approaches to damage detection using laser holography and interferometry. The paper then details the modern uses of electronic holography and neural-net-processed characteristic patterns to detect structural damage. The design of the neural networks and the preparation of the training sets are discussed. The use of a technique to optimize the training sets, called folding, is explained. Then a training procedure is detailed that uses the holography-measured vibration modes of the undamaged structures to impart damage-detection sensitivity to the neural networks. The inspections of an optical strain gauge mounting plate and an International Space Station cold plate are presented as examples.

A neural network simulation package in CLIPS

NASA Technical Reports Server (NTRS)

Bhatnagar, Himanshu; Krolak, Patrick D.; Mcgee, Brenda J.; Coleman, John

1990-01-01

The intrinsic similarity between the firing of a rule and the firing of a neuron has been captured in this research to provide a neural network development system within an existing production system (CLIPS). A very important by-product of this research has been the emergence of an integrated technique of using rule based systems in conjunction with the neural networks to solve complex problems. The systems provides a tool kit for an integrated use of the two techniques and is also extendible to accommodate other AI techniques like the semantic networks, connectionist networks, and even the petri nets. This integrated technique can be very useful in solving complex AI problems.

Depletion of perineuronal nets enhances recognition memory and long-term depression in the perirhinal cortex

PubMed Central

Romberg, Carola; Yang, Sujeong; Melani, Riccardo; Andrews, Melissa R.; Horner, Alexa E.; Spillantini, Maria G.; Bussey, Timothy J.; Fawcett, James W.; Pizzorusso, Tommaso; Saksida, Lisa M.

2013-01-01

Perineuronal nets are extracellular matrix structures surrounding cortical neuronal cell bodies and proximal dendrites, and are involved in the control of brain plasticity and the closure of critical periods. Expression of the link protein Crtl1/Hapln1 in neurons has recently been identified as the key event triggering the formation of perineuronal nets. Here we show that the genetic attenuation of perineuronal nets in adult brain Crtl1 knockout mice enhances long term object recognition memory and facilitates long-term depression in the perirhinal cortex, a neural correlate of object recognition memory. Identical prolongation of memory follows localised digestion of perineuronal nets with chondroitinase ABC, an enzyme that degrades the chondroitin sulphate proteoglycans (CSPGs) components of PNNs. The memory-enhancing effect of chondroitinase ABC treatment attenuated over time, suggesting that regeneration of PNNs gradually restored control plasticity levels. Our findings indicate that perineuronal nets regulate both memory and experience-driven synaptic plasticity in adulthood. PMID:23595763

Creating Weather System Ensembles Through Synergistic Process Modeling and Machine Learning

NASA Astrophysics Data System (ADS)

Chen, B.; Posselt, D. J.; Nguyen, H.; Wu, L.; Su, H.; Braverman, A. J.

2017-12-01

Earth's weather and climate are sensitive to a variety of control factors (e.g., initial state, forcing functions, etc). Characterizing the response of the atmosphere to a change in initial conditions or model forcing is critical for weather forecasting (ensemble prediction) and climate change assessment. Input - response relationships can be quantified by generating an ensemble of multiple (100s to 1000s) realistic realizations of weather and climate states. Atmospheric numerical models generate simulated data through discretized numerical approximation of the partial differential equations (PDEs) governing the underlying physics. However, the computational expense of running high resolution atmospheric state models makes generation of more than a few simulations infeasible. Here, we discuss an experiment wherein we approximate the numerical PDE solver within the Weather Research and Forecasting (WRF) Model using neural networks trained on a subset of model run outputs. Once trained, these neural nets can produce large number of realization of weather states from a small number of deterministic simulations with speeds that are orders of magnitude faster than the underlying PDE solver. Our neural network architecture is inspired by the governing partial differential equations. These equations are location-invariant, and consist of first and second derivations. As such, we use a 3x3 lon-lat grid of atmospheric profiles as the predictor in the neural net to provide the network the information necessary to compute the first and second moments. Results indicate that the neural network algorithm can approximate the PDE outputs with high degree of accuracy (less than 1% error), and that this error increases as a function of the prediction time lag.

An Activity for Demonstrating the Concept of a Neural Circuit

ERIC Educational Resources Information Center

Kreiner, David S.

2012-01-01

College students in two sections of a general psychology course participated in a demonstration of a simple neural circuit. The activity was based on a neural circuit that Jeffress proposed for localizing sounds. Students in one section responded to a questionnaire prior to participating in the activity, while students in the other section…

Third Conference on Artificial Intelligence for Space Applications, part 2

NASA Technical Reports Server (NTRS)

Denton, Judith S. (Compiler); Freeman, Michael S. (Compiler); Vereen, Mary (Compiler)

1988-01-01

Topics relative to the application of artificial intelligence to space operations are discussed. New technologies for space station automation, design data capture, computer vision, neural nets, automatic programming, and real time applications are discussed.

Effect of Palagonite Dust Deposition on the Automated Detection of Carbonate Vis/NIR Spectra

NASA Technical Reports Server (NTRS)

Gilmore, Martha S.; Merrill, Matthew D.; Castano, Rebecca; Bornstein, Benjamin; Greenwood, James

2004-01-01

Currently Mars missions can collect more data than can be returned. Future rovers of increased mission lifetime will benefit from onboard autonomous data processing systems to guide the selection, measurement and return of scientifically important data. One approach is to train a neural net to recognize spectral reflectance characteristics of minerals of interest. We have developed a carbonate detector using a neural net algorithm trained on 10,000 synthetic Vis/NIR (350-2500 nm) spectra. The detector was able to correctly identify carbonates in the spectra of 30 carbonate and noncarbonate field samples with 100% success. However, Martian dust coatings strongly affect the spectral characteristics of surface rocks potentially masking the underlying substrate rock. In this experiment, we measure Vis/NIR spectra of calcite coated with different thicknesses of palagonite dust and evaluate the performance of the carbonate detector.

A Computational Intelligence (CI) Approach to the Precision Mars Lander Problem

NASA Technical Reports Server (NTRS)

Birge, Brian; Walberg, Gerald

2002-01-01

A Mars precision landing requires a landed footprint of no more than 100 meters. Obstacles to reducing the landed footprint include trajectory dispersions due to initial atmospheric entry conditions such as entry angle, parachute deployment height, environment parameters such as wind, atmospheric density, parachute deployment dynamics, unavoidable injection error or propagated error from launch, etc. Computational Intelligence (CI) techniques such as Artificial Neural Nets and Particle Swarm Optimization have been shown to have great success with other control problems. The research period extended previous work on investigating applicability of the computational intelligent approaches. The focus of this investigation was on Particle Swarm Optimization and basic Neural Net architectures. The research investigating these issues was performed for the grant cycle from 5/15/01 to 5/15/02. Matlab 5.1 and 6.0 along with NASA's POST were the primary computational tools.

Confidence limits for data mining models of options prices

NASA Astrophysics Data System (ADS)

Healy, J. V.; Dixon, M.; Read, B. J.; Cai, F. F.

2004-12-01

Non-parametric methods such as artificial neural nets can successfully model prices of financial options, out-performing the Black-Scholes analytic model (Eur. Phys. J. B 27 (2002) 219). However, the accuracy of such approaches is usually expressed only by a global fitting/error measure. This paper describes a robust method for determining prediction intervals for models derived by non-linear regression. We have demonstrated it by application to a standard synthetic example (29th Annual Conference of the IEEE Industrial Electronics Society, Special Session on Intelligent Systems, pp. 1926-1931). The method is used here to obtain prediction intervals for option prices using market data for LIFFE “ESX” FTSE 100 index options ( http://www.liffe.com/liffedata/contracts/month_onmonth.xls). We avoid special neural net architectures and use standard regression procedures to determine local error bars. The method is appropriate for target data with non constant variance (or volatility).

Norepinephrine transporter heterozygous knockout mice exhibit altered transport and behavior.

PubMed

Fentress, H M; Klar, R; Krueger, J J; Sabb, T; Redmon, S N; Wallace, N M; Shirey-Rice, J K; Hahn, M K

2013-11-01

The norepinephrine (NE) transporter (NET) regulates synaptic NE availability for noradrenergic signaling in the brain and sympathetic nervous system. Although genetic variation leading to a loss of NET expression has been implicated in psychiatric and cardiovascular disorders, complete NET deficiency has not been found in people, limiting the utility of NET knockout mice as a model for genetically driven NET dysfunction. Here, we investigate NET expression in NET heterozygous knockout male mice (NET(+/-) ), demonstrating that they display an approximately 50% reduction in NET protein levels. Surprisingly, these mice display no significant deficit in NET activity assessed in hippocampal and cortical synaptosomes. We found that this compensation in NET activity was due to enhanced activity of surface-resident transporters, as opposed to surface recruitment of NET protein or compensation through other transport mechanisms, including serotonin, dopamine or organic cation transporters. We hypothesize that loss of NET protein in the NET(+/-) mouse establishes an activated state of existing surface NET proteins. The NET(+/-) mice exhibit increased anxiety in the open field and light-dark box and display deficits in reversal learning in the Morris water maze. These data suggest that recovery of near basal activity in NET(+/-) mice appears to be insufficient to limit anxiety responses or support cognitive performance that might involve noradrenergic neurotransmission. The NET(+/-) mice represent a unique model to study the loss and resultant compensatory changes in NET that may be relevant to behavior and physiology in human NET deficiency disorders. © 2013 John Wiley & Sons Ltd and International Behavioural and Neural Genetics Society.

A deep learning method for early screening of lung cancer

NASA Astrophysics Data System (ADS)

Zhang, Kunpeng; Jiang, Huiqin; Ma, Ling; Gao, Jianbo; Yang, Xiaopeng

2018-04-01

Lung cancer is the leading cause of cancer-related deaths among men. In this paper, we propose a pulmonary nodule detection method for early screening of lung cancer based on the improved AlexNet model. In order to maintain the same image quality as the existing B/S architecture PACS system, we convert the original CT image into JPEG format image by analyzing the DICOM file firstly. Secondly, in view of the large size and complex background of CT chest images, we design the convolution neural network on basis of AlexNet model and sparse convolution structure. At last we train our models on the software named DIGITS which is provided by NVIDIA. The main contribution of this paper is to apply the convolutional neural network for the early screening of lung cancer and improve the screening accuracy by combining the AlexNet model with the sparse convolution structure. We make a series of experiments on the chest CT images using the proposed method, of which the sensitivity and specificity indicates that the method presented in this paper can effectively improve the accuracy of early screening of lung cancer and it has certain clinical significance at the same time.

Neural network classification of questionable EGRET events

NASA Astrophysics Data System (ADS)

Meetre, C. A.; Norris, J. P.

1992-02-01

High energy gamma rays (greater than 20 MeV) pair producing in the spark chamber of the Energetic Gamma Ray Telescope Experiment (EGRET) give rise to a characteristic but highly variable 3-D locus of spark sites, which must be processed to decide whether the event is to be included in the database. A significant fraction (about 15 percent or 104 events/day) of the candidate events cannot be categorized (accept/reject) by an automated rule-based procedure; they are therefore tagged, and must be examined and classified manually by a team of expert analysts. We describe a feedforward, back-propagation neural network approach to the classification of the questionable events. The algorithm computes a set of coefficients using representative exemplars drawn from the preclassified set of questionable events. These coefficients map a given input event into a decision vector that, ideally, describes the correct disposition of the event. The net's accuracy is then tested using a different subset of preclassified events. Preliminary results demonstrate the net's ability to correctly classify a large proportion of the events for some categories of questionables. Current work includes the use of much larger training sets to improve the accuracy of the net.

Bone age detection via carpogram analysis using convolutional neural networks

NASA Astrophysics Data System (ADS)

Torres, Felipe; Bravo, María. Alejandra; Salinas, Emmanuel; Triana, Gustavo; Arbeláez, Pablo

2017-11-01

Bone age assessment is a critical factor for determining delayed development in children, which can be a sign of pathologies such as endocrine diseases, growth abnormalities, chromosomal, neurological and congenital disorders among others. In this paper we present BoneNet, a methodology to assess automatically the skeletal maturity state in pediatric patients based on Convolutional Neural Networks. We train and evaluate our algorithm on a database of X-Ray images provided by the hospital Fundacion Santa Fe de Bogot ´ a with around 1500 images of patients between the ages 1 to 18. ´ We compare two different architectures to classify the given data in order to explore the generality of our method. To accomplish this, we define multiple binary age assessment problems, dividing the data by bone age and differentiating the patients by their gender. Thus, exploring several parameters, we develop BoneNet. Our approach is holistic, efficient, and modular, since it is possible for the specialists to use all the networks combined to determine how is the skeletal maturity of a patient. BoneNet achieves over 90% accuracy for most of the critical age thresholds, when differentiating the images between over or under a given age.

Neural network classification of questionable EGRET events

NASA Technical Reports Server (NTRS)

Meetre, C. A.; Norris, J. P.

1992-01-01

High energy gamma rays (greater than 20 MeV) pair producing in the spark chamber of the Energetic Gamma Ray Telescope Experiment (EGRET) give rise to a characteristic but highly variable 3-D locus of spark sites, which must be processed to decide whether the event is to be included in the database. A significant fraction (about 15 percent or 10(exp 4) events/day) of the candidate events cannot be categorized (accept/reject) by an automated rule-based procedure; they are therefore tagged, and must be examined and classified manually by a team of expert analysts. We describe a feedforward, back-propagation neural network approach to the classification of the questionable events. The algorithm computes a set of coefficients using representative exemplars drawn from the preclassified set of questionable events. These coefficients map a given input event into a decision vector that, ideally, describes the correct disposition of the event. The net's accuracy is then tested using a different subset of preclassified events. Preliminary results demonstrate the net's ability to correctly classify a large proportion of the events for some categories of questionables. Current work includes the use of much larger training sets to improve the accuracy of the net.

Modeling shared resources with generalized synchronization within a Petri net bottom-up approach.

PubMed

Ferrarini, L; Trioni, M

1996-01-01

This paper proposes a simple and effective way to represent shared resources in manufacturing systems within a Petri net model previously developed. Such a model relies on the bottom-up and modular approach to synthesis and analysis. The designer may define elementary tasks and then connect them with one another with three kinds of connections: self-loops, inhibitor arcs and simple synchronizations. A theoretical framework has been established for the analysis of liveness and reversibility of such models. The generalized synchronization, here formalized, represents an extension of the simple synchronization, allowing the merging of suitable subnets among elementary tasks. It is proved that under suitable, but not restrictive, hypotheses the generalized synchronization may be substituted for a simple one, thus being compatible with all the developed theoretical body.

Wavelet-based higher-order neural networks for mine detection in thermal IR imagery

NASA Astrophysics Data System (ADS)

Baertlein, Brian A.; Liao, Wen-Jiao

2000-08-01

An image processing technique is described for the detection of miens in RI imagery. The proposed technique is based on a third-order neural network, which processes the output of a wavelet packet transform. The technique is inherently invariant to changes in signature position, rotation and scaling. The well-known memory limitations that arise with higher-order neural networks are addressed by (1) the data compression capabilities of wavelet packets, (2) protections of the image data into a space of similar triangles, and (3) quantization of that 'triangle space'. Using these techniques, image chips of size 28 by 28, which would require 0(109) neural net weights, are processed by a network having 0(102) weights. ROC curves are presented for mine detection in real and simulated imagery.

Path optimisation of a mobile robot using an artificial neural network controller

NASA Astrophysics Data System (ADS)

Singh, M. K.; Parhi, D. R.

2011-01-01

This article proposed a novel approach for design of an intelligent controller for an autonomous mobile robot using a multilayer feed forward neural network, which enables the robot to navigate in a real world dynamic environment. The inputs to the proposed neural controller consist of left, right and front obstacle distance with respect to its position and target angle. The output of the neural network is steering angle. A four layer neural network has been designed to solve the path and time optimisation problem of mobile robots, which deals with the cognitive tasks such as learning, adaptation, generalisation and optimisation. A back propagation algorithm is used to train the network. This article also analyses the kinematic design of mobile robots for dynamic movements. The simulation results are compared with experimental results, which are satisfactory and show very good agreement. The training of the neural nets and the control performance analysis has been done in a real experimental setup.

Elk3 is essential for the progression from progenitor to definitive neural crest cell

PubMed Central

Rogers, Crystal D.; Phillips, Jacquelyn L.; Bronner, Marianne E.

2013-01-01

Elk3/Net/Sap2 (here referred to as Elk3) is an Ets ternary complex transcriptional repressor known for its involvement in angiogenesis during embryonic development. Although Elk3 is expressed in various tissues, additional roles for the protein outside of vasculature development have yet to be reported. Here, we characterize the early spatiotemporal expression pattern of Elk3 in the avian embryo using whole mount in situ hybridization and quantitative RT-PCR and examine the effects of its loss of function on neural crest development. At early stages, Elk3 is expressed in the head folds, head mesenchyme, intersomitic vessels, and migratory cranial neural crest (NC) cells. Loss of the Elk3 protein results in the retention of Pax7+ precursors in the dorsal neural tube that fail to upregulate neural crest specifier genes, FoxD3, Sox10 and Snail2, resulting in embryos with severe migration defects. The results putatively place Elk3 downstream of neural plate border genes, but upstream of neural crest specifier genes in the neural crest gene regulatory network (NC-GRN), suggesting that it is critical for the progression from progenitor to definitive neural crest cell. PMID:23266330

Illusory Motion Reproduced by Deep Neural Networks Trained for Prediction

PubMed Central

Watanabe, Eiji; Kitaoka, Akiyoshi; Sakamoto, Kiwako; Yasugi, Masaki; Tanaka, Kenta

2018-01-01

The cerebral cortex predicts visual motion to adapt human behavior to surrounding objects moving in real time. Although the underlying mechanisms are still unknown, predictive coding is one of the leading theories. Predictive coding assumes that the brain's internal models (which are acquired through learning) predict the visual world at all times and that errors between the prediction and the actual sensory input further refine the internal models. In the past year, deep neural networks based on predictive coding were reported for a video prediction machine called PredNet. If the theory substantially reproduces the visual information processing of the cerebral cortex, then PredNet can be expected to represent the human visual perception of motion. In this study, PredNet was trained with natural scene videos of the self-motion of the viewer, and the motion prediction ability of the obtained computer model was verified using unlearned videos. We found that the computer model accurately predicted the magnitude and direction of motion of a rotating propeller in unlearned videos. Surprisingly, it also represented the rotational motion for illusion images that were not moving physically, much like human visual perception. While the trained network accurately reproduced the direction of illusory rotation, it did not detect motion components in negative control pictures wherein people do not perceive illusory motion. This research supports the exciting idea that the mechanism assumed by the predictive coding theory is one of basis of motion illusion generation. Using sensory illusions as indicators of human perception, deep neural networks are expected to contribute significantly to the development of brain research. PMID:29599739

Illusory Motion Reproduced by Deep Neural Networks Trained for Prediction.

PubMed

Watanabe, Eiji; Kitaoka, Akiyoshi; Sakamoto, Kiwako; Yasugi, Masaki; Tanaka, Kenta

2018-01-01

The cerebral cortex predicts visual motion to adapt human behavior to surrounding objects moving in real time. Although the underlying mechanisms are still unknown, predictive coding is one of the leading theories. Predictive coding assumes that the brain's internal models (which are acquired through learning) predict the visual world at all times and that errors between the prediction and the actual sensory input further refine the internal models. In the past year, deep neural networks based on predictive coding were reported for a video prediction machine called PredNet. If the theory substantially reproduces the visual information processing of the cerebral cortex, then PredNet can be expected to represent the human visual perception of motion. In this study, PredNet was trained with natural scene videos of the self-motion of the viewer, and the motion prediction ability of the obtained computer model was verified using unlearned videos. We found that the computer model accurately predicted the magnitude and direction of motion of a rotating propeller in unlearned videos. Surprisingly, it also represented the rotational motion for illusion images that were not moving physically, much like human visual perception. While the trained network accurately reproduced the direction of illusory rotation, it did not detect motion components in negative control pictures wherein people do not perceive illusory motion. This research supports the exciting idea that the mechanism assumed by the predictive coding theory is one of basis of motion illusion generation. Using sensory illusions as indicators of human perception, deep neural networks are expected to contribute significantly to the development of brain research.

Using L-M BP Algorithm Forecase the 305 Days Production of First-Breed Dairy

NASA Astrophysics Data System (ADS)

Wei, Xiaoli; Qi, Guoqiang; Shen, Weizheng; Jian, Sun

Aiming at the shortage of conventional BP algorithm, a BP neural net works improved by L-M algorithm is put forward. On the basis of the network, a Prediction model for 305 day's milk productions was set up. Traditional methods finish these data must spend at least 305 days, But this model can forecast first-breed dairy's 305 days milk production ahead of 215 days. The validity of the improved BP neural network predictive model was validated through the experiments.

A neural net-based approach to software metrics

NASA Technical Reports Server (NTRS)

Boetticher, G.; Srinivas, Kankanahalli; Eichmann, David A.

1992-01-01

Software metrics provide an effective method for characterizing software. Metrics have traditionally been composed through the definition of an equation. This approach is limited by the fact that all the interrelationships among all the parameters be fully understood. This paper explores an alternative, neural network approach to modeling metrics. Experiments performed on two widely accepted metrics, McCabe and Halstead, indicate that the approach is sound, thus serving as the groundwork for further exploration into the analysis and design of software metrics.

Probabilistic and Other Neural Nets in Multi-Hole Probe Calibration and Flow Angularity Pattern Recognition

NASA Technical Reports Server (NTRS)

Baskaran, Subbiah; Ramachandran, Narayanan; Noever, David

1998-01-01

The use of probabilistic (PNN) and multilayer feed forward (MLFNN) neural networks are investigated for calibration of multi-hole pressure probes and the prediction of associated flow angularity patterns in test flow fields. Both types of networks are studied in detail for their calibration and prediction characteristics. The current formalism can be applied to any multi-hole probe, however the test results for the most commonly used five-hole Cone and Prism probe types alone are reported in this article.

A self-organizing neural network for the traveling salesman problem that is competitive with simulated annealing.

PubMed

Budinich, M

1996-02-15

Unsupervised learning applied to an unstructured neural network can give approximate solutions to the traveling salesman problem. For 50 cities in the plane this algorithm performs like the elastic net of Durbin and Willshaw (1987) and it improves when increasing the number of cities to get better than simulated annealing for problems with more than 500 cities. In all the tests this algorithm requires a fraction of the time taken by simulated annealing.

Third Conference on Artificial Intelligence for Space Applications, part 1

NASA Technical Reports Server (NTRS)

Denton, Judith S. (Compiler); Freeman, Michael S. (Compiler); Vereen, Mary (Compiler)

1987-01-01

The application of artificial intelligence to spacecraft and aerospace systems is discussed. Expert systems, robotics, space station automation, fault diagnostics, parallel processing, knowledge representation, scheduling, man-machine interfaces and neural nets are among the topics discussed.

Connectionist Modelling and Education.

ERIC Educational Resources Information Center

Evers, Colin W.

2000-01-01

Provides a detailed, technical introduction to the state of cognitive science research, in particular the rise of the "new cognitive science," especially artificial neural net (ANN) models. Explains one influential ANN model and describes diverse applications and their implications for education. (EV)

Linear analysis of auto-organization in Hebbian neural networks.

PubMed

Carlos Letelier, J; Mpodozis, J

1995-01-01

The self-organization of neurotopies where neural connections follow Hebbian dynamics is framed in terms of linear operator theory. A general and exact equation describing the time evolution of the overall synaptic strength connecting two neural laminae is derived. This linear matricial equation, which is similar to the equations used to describe oscillating systems in physics, is modified by the introduction of non-linear terms, in order to capture self-organizing (or auto-organizing) processes. The behavior of a simple and small system, that contains a non-linearity that mimics a metabolic constraint, is analyzed by computer simulations. The emergence of a simple "order" (or degree of organization) in this low-dimensionality model system is discussed.

Simple artificial neural networks that match probability and exploit and explore when confronting a multiarmed bandit.

PubMed

Dawson, Michael R W; Dupuis, Brian; Spetch, Marcia L; Kelly, Debbie M

2009-08-01

The matching law (Herrnstein 1961) states that response rates become proportional to reinforcement rates; this is related to the empirical phenomenon called probability matching (Vulkan 2000). Here, we show that a simple artificial neural network generates responses consistent with probability matching. This behavior was then used to create an operant procedure for network learning. We use the multiarmed bandit (Gittins 1989), a classic problem of choice behavior, to illustrate that operant training balances exploiting the bandit arm expected to pay off most frequently with exploring other arms. Perceptrons provide a medium for relating results from neural networks, genetic algorithms, animal learning, contingency theory, reinforcement learning, and theories of choice.

Neural-Network Computer Transforms Coordinates

NASA Technical Reports Server (NTRS)

Josin, Gary M.

1990-01-01

Numerical simulation demonstrated ability of conceptual neural-network computer to generalize what it has "learned" from few examples. Ability to generalize achieved with even simple neural network (relatively few neurons) and after exposure of network to only few "training" examples. Ability to obtain fairly accurate mappings after only few training examples used to provide solutions to otherwise intractable mapping problems.

High Aspect-Ratio Neural Probes using Conventional Blade Dicing

NASA Astrophysics Data System (ADS)

Goncalves, S. B.; Ribeiro, J. F.; Silva, A. F.; Correia, J. H.

2016-10-01

Exploring deep neural circuits has triggered the development of long penetrating neural probes. Moreover, driven by brain displacement, the long neural probes require also a high aspect-ratio shafts design. In this paper, a simple and reproducible method of manufacturing long-shafts neural probes using blade dicing technology is presented. Results shows shafts up to 8 mm long and 200 µm wide, features competitive to the current state-of-art, being its outline simply accomplished by a single blade dicing program. Therefore, conventional blade dicing presents itself as a viable option to manufacture long neural probes.

[The Identification of the Origin of Chinese Wolfberry Based on Infrared Spectral Technology and the Artificial Neural Network].

PubMed

Li, Zhong; Liu, Ming-de; Ji, Shou-xiang

2016-03-01

The Fourier Transform Infrared Spectroscopy (FTIR) is established to find the geographic origins of Chinese wolfberry quickly. In the paper, the 45 samples of Chinese wolfberry from different places of Qinghai Province are to be surveyed by FTIR. The original data matrix of FTIR is pretreated with common preprocessing and wavelet transform. Compared with common windows shifting smoothing preprocessing, standard normal variation correction and multiplicative scatter correction, wavelet transform is an effective spectrum data preprocessing method. Before establishing model through the artificial neural networks, the spectra variables are compressed by means of the wavelet transformation so as to enhance the training speed of the artificial neural networks, and at the same time the related parameters of the artificial neural networks model are also discussed in detail. The survey shows even if the infrared spectroscopy data is compressed to 1/8 of its original data, the spectral information and analytical accuracy are not deteriorated. The compressed spectra variables are used for modeling parameters of the backpropagation artificial neural network (BP-ANN) model and the geographic origins of Chinese wolfberry are used for parameters of export. Three layers of neural network model are built to predict the 10 unknown samples by using the MATLAB neural network toolbox design error back propagation network. The number of hidden layer neurons is 5, and the number of output layer neuron is 1. The transfer function of hidden layer is tansig, while the transfer function of output layer is purelin. Network training function is trainl and the learning function of weights and thresholds is learngdm. net. trainParam. epochs=1 000, while net. trainParam. goal = 0.001. The recognition rate of 100% is to be achieved. It can be concluded that the method is quite suitable for the quick discrimination of producing areas of Chinese wolfberry. The infrared spectral analysis technology combined with the artificial neural networks is proved to be a reliable and new method for the identification of the original place of Traditional Chinese Medicine.

An Automation Framework for Neural Nets that Learn

ERIC Educational Resources Information Center

Kilmer, W. L.; Arbib, M. A.

1973-01-01

A discussion of several types of formal neurons, many of whose functions are modifiable by their own input stimuli. The language of finite automata is used to mathematicize the problem of adaptation sufficiently to remove some ambiguities of Brindley's approach. (Author)

A hypercube compact neural network

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

Rostykus, P.L.; Somani, A.K.

1988-09-01

A major problem facing implementation of neural networks is the connection problem. One popular tradeoff is to remove connections. Random disconnection severely degrades the capabilities. The hypercube based Compact Neural Network (CNN) has structured architecture combined with a rearrangement of the memory vectors gives a larger input space and better degradation than a cost equivalent network with more connections. The CNNs are based on a Hopfield network. The changes from the Hopfield net include states of -1 and +1 and when a node was evaluated to 0, it was not biased either positive or negative, instead it resumed its previousmore » state. L = PEs, N = memories and t/sub ij/s is the weights between i and j.« less

White blood cells identification system based on convolutional deep neural learning networks.

PubMed

Shahin, A I; Guo, Yanhui; Amin, K M; Sharawi, Amr A

2017-11-16

White blood cells (WBCs) differential counting yields valued information about human health and disease. The current developed automated cell morphology equipments perform differential count which is based on blood smear image analysis. Previous identification systems for WBCs consist of successive dependent stages; pre-processing, segmentation, feature extraction, feature selection, and classification. There is a real need to employ deep learning methodologies so that the performance of previous WBCs identification systems can be increased. Classifying small limited datasets through deep learning systems is a major challenge and should be investigated. In this paper, we propose a novel identification system for WBCs based on deep convolutional neural networks. Two methodologies based on transfer learning are followed: transfer learning based on deep activation features and fine-tuning of existed deep networks. Deep acrivation featues are extracted from several pre-trained networks and employed in a traditional identification system. Moreover, a novel end-to-end convolutional deep architecture called "WBCsNet" is proposed and built from scratch. Finally, a limited balanced WBCs dataset classification is performed through the WBCsNet as a pre-trained network. During our experiments, three different public WBCs datasets (2551 images) have been used which contain 5 healthy WBCs types. The overall system accuracy achieved by the proposed WBCsNet is (96.1%) which is more than different transfer learning approaches or even the previous traditional identification system. We also present features visualization for the WBCsNet activation which reflects higher response than the pre-trained activated one. a novel WBCs identification system based on deep learning theory is proposed and a high performance WBCsNet can be employed as a pre-trained network. Copyright © 2017. Published by Elsevier B.V.

Obesity-specific neural cost of maintaining gait performance under complex conditions in community-dwelling older adults.

PubMed

Osofundiya, Olufunmilola; Benden, Mark E; Dowdy, Diane; Mehta, Ranjana K

2016-06-01

Recent evidence of obesity-related changes in the prefrontal cortex during cognitive and seated motor activities has surfaced; however, the impact of obesity on neural activity during ambulation remains unclear. The purpose of this study was to determine obesity-specific neural cost of simple and complex ambulation in older adults. Twenty non-obese and obese individuals, 65years and older, performed three tasks varying in the types of complexity of ambulation (simple walking, walking+cognitive dual-task, and precision walking). Maximum oxygenated hemoglobin, a measure of neural activity, was measured bilaterally using a portable functional near infrared spectroscopy system, and gait speed and performance on the complex tasks were also obtained. Complex ambulatory tasks were associated with ~2-3.5 times greater cerebral oxygenation levels and ~30-40% slower gait speeds when compared to the simple walking task. Additionally, obesity was associated with three times greater oxygenation levels, particularly during the precision gait task, despite obese adults demonstrating similar gait speeds and performances on the complex gait tasks as non-obese adults. Compared to existing studies that focus solely on biomechanical outcomes, the present study is one of the first to examine obesity-related differences in neural activity during ambulation in older adults. In order to maintain gait performance, obesity was associated with higher neural costs, and this was augmented during ambulatory tasks requiring greater precision control. These preliminary findings have clinical implications in identifying individuals who are at greater risk of mobility limitations, particularly when performing complex ambulatory tasks. Copyright © 2016 Elsevier Ltd. All rights reserved.

Optimized biogas-fermentation by neural network control.

PubMed

Holubar, P; Zani, L; Hager, M; Fröschl, W; Radak, Z; Braun, R

2003-01-01

In this work several feed-forward back-propagation neural networks (FFBP) were trained in order to model, and subsequently control, methane production in anaerobic digesters. To produce data for the training of the neural nets, four anaerobic continuous stirred tank reactors (CSTR) were operated in steady-state conditions at organic loading rates (Br) of about 2 kg x m(-3) x d(-1) chemical oxygen demand (COD), and disturbed by pulse-like increase of the organic loading rate. For the pulses additional carbon sources were added to the basic feed (surplus- and primary sludge) to simulate cofermentation and to increase the COD. Measured parameters were: gas composition, methane production rate, volatile fatty acid concentration, pH, redox potential, volatile suspended solids and COD of feed and effluent. A hierarchical system of neural nets was developed and embedded in a Decision Support System (DSS). A 3-3-1 FFBP simulated the pH with a regression coefficient of 0.82. A 9-3-3 FFBP simulated the volatile fatty acid concentration in the sludge with a regression coefficient of 0.86. And a 9-3-2 FFBP simulated the gas production and gas composition with a regression coefficient of 0.90 and 0.80 respectively. A lab-scale anaerobic CSTR controlled by this tool was able to maintain a methane concentration of about 60% at a rather high gas production rate of between 5 to 5.6 m3 x m(-3) x d(-1).

Modification of tenascin-R expression following unilateral labyrinthectomy in rats indicates its possible role in neural plasticity of the vestibular neural circuit.

PubMed

Gaal, Botond; Jóhannesson, Einar Örn; Dattani, Amit; Magyar, Agnes; Wéber, Ildikó; Matesz, Clara

2015-09-01

We have previously found that unilateral labyrinthectomy is accompanied by modification of hyaluronan and chondroitin sulfate proteoglycan staining in the lateral vestibular nucleus of rats and the time course of subsequent reorganization of extracellular matrix assembly correlates to the restoration of impaired vestibular function. The tenascin-R has repelling effect on pathfinding during axonal growth/regrowth, and thus inhibits neural circuit repair. By using immunohistochemical method, we studied the modification of tenascin-R expression in the superior, medial, lateral, and descending vestibular nuclei of the rat following unilateral labyrinthectomy. On postoperative day 1, tenascin-R reaction in the perineuronal nets disappeared on the side of labyrinthectomy in the superior, lateral, medial, and rostral part of the descending vestibular nuclei. On survival day 3, the staining intensity of tenascin-R reaction in perineuronal nets recovered on the operated side of the medial vestibular nucleus, whereas it was restored by the time of postoperative day 7 in the superior, lateral and rostral part of the descending vestibular nuclei. The staining intensity of tenascin-R reaction remained unchanged in the caudal part of the descending vestibular nucleus bilaterally. Regional differences in the modification of tenascin-R expression presented here may be associated with different roles of individual vestibular nuclei in the compensatory processes. The decreased expression of the tenascin-R may suggest the extracellular facilitation of plastic modifications in the vestibular neural circuit after lesion of the labyrinthine receptors.

Neural net classification of liver ultrasonogram for quantitative evaluation of diffuse liver disease

NASA Astrophysics Data System (ADS)

Lee, Dong Hyuk; Kim, JongHyo; Kim, Hee C.; Lee, Yong W.; Min, Byong Goo

1997-04-01

There have been a number of studies on the quantitative evaluation of diffuse liver disease by using texture analysis technique. However, the previous studies have been focused on the classification between only normal and abnormal pattern based on textural properties, resulting in lack of clinically useful information about the progressive status of liver disease. Considering our collaborative research experience with clinical experts, we judged that not only texture information but also several shape properties are necessary in order to successfully classify between various states of disease with liver ultrasonogram. Nine image parameters were selected experimentally. One of these was texture parameter and others were shape parameters measured as length, area and curvature. We have developed a neural-net algorithm that classifies liver ultrasonogram into 9 categories of liver disease: 3 main category and 3 sub-steps for each. Nine parameters were collected semi- automatically from the user by using graphical user interface tool, and then processed to give a grade for each parameter. Classifying algorithm consists of two steps. At the first step, each parameter was graded into pre-defined levels using neural network. in the next step, neural network classifier determined disease status using graded nine parameters. We implemented a PC based computer-assist diagnosis workstation and installed it in radiology department of Seoul National University Hospital. Using this workstation we collected 662 cases during 6 months. Some of these were used for training and others were used for evaluating accuracy of the developed algorithm. As a conclusion, a liver ultrasonogram classifying algorithm was developed using both texture and shape parameters and neural network classifier. Preliminary results indicate that the proposed algorithm is useful for evaluation of diffuse liver disease.

Transfer Learning with Convolutional Neural Networks for Classification of Abdominal Ultrasound Images.

PubMed

Cheng, Phillip M; Malhi, Harshawn S

2017-04-01

The purpose of this study is to evaluate transfer learning with deep convolutional neural networks for the classification of abdominal ultrasound images. Grayscale images from 185 consecutive clinical abdominal ultrasound studies were categorized into 11 categories based on the text annotation specified by the technologist for the image. Cropped images were rescaled to 256 × 256 resolution and randomized, with 4094 images from 136 studies constituting the training set, and 1423 images from 49 studies constituting the test set. The fully connected layers of two convolutional neural networks based on CaffeNet and VGGNet, previously trained on the 2012 Large Scale Visual Recognition Challenge data set, were retrained on the training set. Weights in the convolutional layers of each network were frozen to serve as fixed feature extractors. Accuracy on the test set was evaluated for each network. A radiologist experienced in abdominal ultrasound also independently classified the images in the test set into the same 11 categories. The CaffeNet network classified 77.3% of the test set images accurately (1100/1423 images), with a top-2 accuracy of 90.4% (1287/1423 images). The larger VGGNet network classified 77.9% of the test set accurately (1109/1423 images), with a top-2 accuracy of VGGNet was 89.7% (1276/1423 images). The radiologist classified 71.7% of the test set images correctly (1020/1423 images). The differences in classification accuracies between both neural networks and the radiologist were statistically significant (p < 0.001). The results demonstrate that transfer learning with convolutional neural networks may be used to construct effective classifiers for abdominal ultrasound images.

Biological neural networks as model systems for designing future parallel processing computers

NASA Technical Reports Server (NTRS)

Ross, Muriel D.

1991-01-01

One of the more interesting debates of the present day centers on whether human intelligence can be simulated by computer. The author works under the premise that neurons individually are not smart at all. Rather, they are physical units which are impinged upon continuously by other matter that influences the direction of voltage shifts across the units membranes. It is only the action of a great many neurons, billions in the case of the human nervous system, that intelligent behavior emerges. What is required to understand even the simplest neural system is painstaking analysis, bit by bit, of the architecture and the physiological functioning of its various parts. The biological neural network studied, the vestibular utricular and saccular maculas of the inner ear, are among the most simple of the mammalian neural networks to understand and model. While there is still a long way to go to understand even this most simple neural network in sufficient detail for extrapolation to computers and robots, a start was made. Moreover, the insights obtained and the technologies developed help advance the understanding of the more complex neural networks that underlie human intelligence.

Alpha, delta and theta rhythms in a neural net model. Comparison with MEG data.

PubMed

Kotini, A; Anninos, P

2016-01-07

The aim of this study is to provide information regarding the comparison of a neural model to MEG measurements. Our study population consisted of 10 epileptic patients and 10 normal subjects. The epileptic patients had high MEG amplitudes characterized with θ (4-7 Hz) or δ (2-3 Hz) rhythms and absence of α-rhythm (8-13 Hz). The statistical analysis of such activities corresponded to Poisson distribution. Conversely, the MEG from normal subjects had low amplitudes, higher frequencies and presence of α-rhythm (8-13 Hz). Such activities were not synchronized and their distributions were Gauss. These findings were in agreement with our theoretical neural model. The comparison of the neural network with MEG data provides information about the status of brain function in epileptic and normal states. Copyright © 2015 Elsevier Ltd. All rights reserved.

SpikingLab: modelling agents controlled by Spiking Neural Networks in Netlogo.

PubMed

Jimenez-Romero, Cristian; Johnson, Jeffrey

2017-01-01

The scientific interest attracted by Spiking Neural Networks (SNN) has lead to the development of tools for the simulation and study of neuronal dynamics ranging from phenomenological models to the more sophisticated and biologically accurate Hodgkin-and-Huxley-based and multi-compartmental models. However, despite the multiple features offered by neural modelling tools, their integration with environments for the simulation of robots and agents can be challenging and time consuming. The implementation of artificial neural circuits to control robots generally involves the following tasks: (1) understanding the simulation tools, (2) creating the neural circuit in the neural simulator, (3) linking the simulated neural circuit with the environment of the agent and (4) programming the appropriate interface in the robot or agent to use the neural controller. The accomplishment of the above-mentioned tasks can be challenging, especially for undergraduate students or novice researchers. This paper presents an alternative tool which facilitates the simulation of simple SNN circuits using the multi-agent simulation and the programming environment Netlogo (educational software that simplifies the study and experimentation of complex systems). The engine proposed and implemented in Netlogo for the simulation of a functional model of SNN is a simplification of integrate and fire (I&F) models. The characteristics of the engine (including neuronal dynamics, STDP learning and synaptic delay) are demonstrated through the implementation of an agent representing an artificial insect controlled by a simple neural circuit. The setup of the experiment and its outcomes are described in this work.

Pencil-and-Paper Neural Networks: An Undergraduate Laboratory Exercise in Computational Neuroscience

PubMed Central

Crisp, Kevin M.; Sutter, Ellen N.; Westerberg, Jacob A.

2015-01-01

Although it has been more than 70 years since McCulloch and Pitts published their seminal work on artificial neural networks, such models remain primarily in the domain of computer science departments in undergraduate education. This is unfortunate, as simple network models offer undergraduate students a much-needed bridge between cellular neurobiology and processes governing thought and behavior. Here, we present a very simple laboratory exercise in which students constructed, trained and tested artificial neural networks by hand on paper. They explored a variety of concepts, including pattern recognition, pattern completion, noise elimination and stimulus ambiguity. Learning gains were evident in changes in the use of language when writing about information processing in the brain. PMID:26557791

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

Self-organized adaptation of a simple neural circuit enables complex robot behaviour

NASA Astrophysics Data System (ADS)

Steingrube, Silke; Timme, Marc; Wörgötter, Florentin; Manoonpong, Poramate

2010-03-01

Controlling sensori-motor systems in higher animals or complex robots is a challenging combinatorial problem, because many sensory signals need to be simultaneously coordinated into a broad behavioural spectrum. To rapidly interact with the environment, this control needs to be fast and adaptive. Present robotic solutions operate with limited autonomy and are mostly restricted to few behavioural patterns. Here we introduce chaos control as a new strategy to generate complex behaviour of an autonomous robot. In the presented system, 18 sensors drive 18 motors by means of a simple neural control circuit, thereby generating 11 basic behavioural patterns (for example, orienting, taxis, self-protection and various gaits) and their combinations. The control signal quickly and reversibly adapts to new situations and also enables learning and synaptic long-term storage of behaviourally useful motor responses. Thus, such neural control provides a powerful yet simple way to self-organize versatile behaviours in autonomous agents with many degrees of freedom.

Autoassociative memory retrieval and spontaneous activity bumps in small-world networks of integrate-and-fire neurons.

PubMed

Anishchenko, Anastasia; Treves, Alessandro

2006-10-01

The metric structure of synaptic connections is obviously an important factor in shaping the properties of neural networks, in particular the capacity to retrieve memories, with which are endowed autoassociative nets operating via attractor dynamics. Qualitatively, some real networks in the brain could be characterized as 'small worlds', in the sense that the structure of their connections is intermediate between the extremes of an orderly geometric arrangement and of a geometry-independent random mesh. Small worlds can be defined more precisely in terms of their mean path length and clustering coefficient; but is such a precise description useful for a better understanding of how the type of connectivity affects memory retrieval? We have simulated an autoassociative memory network of integrate-and-fire units, positioned on a ring, with the network connectivity varied parametrically between ordered and random. We find that the network retrieves previously stored memory patterns when the connectivity is close to random, and displays the characteristic behavior of ordered nets (localized 'bumps' of activity) when the connectivity is close to ordered. Recent analytical work shows that these two behaviors can coexist in a network of simple threshold-linear units, leading to localized retrieval states. We find that they tend to be mutually exclusive behaviors, however, with our integrate-and-fire units. Moreover, the transition between the two occurs for values of the connectivity parameter which are not simply related to the notion of small worlds.

Tradespace Exploration for the Engineering of Resilient Systems

DTIC Science & Technology

2015-05-01

world scenarios. The types of tools within the SAE set include visualization, decision analysis, and M&S, so it is difficult to categorize this toolset... overpopulated , or questionable. ERS Tradespace Workshop Create predictive models using multiple techniques (e.g., regression, Kriging, neural nets

Scaling Deep Learning Workloads: NVIDIA DGX-1/Pascal and Intel Knights Landing

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

Gawande, Nitin A.; Landwehr, Joshua B.; Daily, Jeffrey A.

Deep Learning (DL) algorithms have become ubiquitous in data analytics. As a result, major computing vendors --- including NVIDIA, Intel, AMD and IBM --- have architectural road-maps influenced by DL workloads. Furthermore, several vendors have recently advertised new computing products as accelerating DL workloads. Unfortunately, it is difficult for data scientists to quantify the potential of these different products. This paper provides a performance and power analysis of important DL workloads on two major parallel architectures: NVIDIA DGX-1 (eight Pascal P100 GPUs interconnected with NVLink) and Intel Knights Landing (KNL) CPUs interconnected with Intel Omni-Path. Our evaluation consists of amore » cross section of convolutional neural net workloads: CifarNet, CaffeNet, AlexNet and GoogleNet topologies using the Cifar10 and ImageNet datasets. The workloads are vendor optimized for each architecture. GPUs provide the highest overall raw performance. Our analysis indicates that although GPUs provide the highest overall performance, the gap can close for some convolutional networks; and KNL can be competitive when considering performance/watt. Furthermore, NVLink is critical to GPU scaling.« less

Framing U-Net via Deep Convolutional Framelets: Application to Sparse-View CT.

PubMed

Han, Yoseob; Ye, Jong Chul

2018-06-01

X-ray computed tomography (CT) using sparse projection views is a recent approach to reduce the radiation dose. However, due to the insufficient projection views, an analytic reconstruction approach using the filtered back projection (FBP) produces severe streaking artifacts. Recently, deep learning approaches using large receptive field neural networks such as U-Net have demonstrated impressive performance for sparse-view CT reconstruction. However, theoretical justification is still lacking. Inspired by the recent theory of deep convolutional framelets, the main goal of this paper is, therefore, to reveal the limitation of U-Net and propose new multi-resolution deep learning schemes. In particular, we show that the alternative U-Net variants such as dual frame and tight frame U-Nets satisfy the so-called frame condition which makes them better for effective recovery of high frequency edges in sparse-view CT. Using extensive experiments with real patient data set, we demonstrate that the new network architectures provide better reconstruction performance.

Advantages of the net benefit regression framework for economic evaluations of interventions in the workplace: a case study of the cost-effectiveness of a collaborative mental health care program for people receiving short-term disability benefits for psychiatric disorders.

PubMed

Hoch, Jeffrey S; Dewa, Carolyn S

2014-04-01

Economic evaluations commonly accompany trials of new treatments or interventions; however, regression methods and their corresponding advantages for the analysis of cost-effectiveness data are not well known. To illustrate regression-based economic evaluation, we present a case study investigating the cost-effectiveness of a collaborative mental health care program for people receiving short-term disability benefits for psychiatric disorders. We implement net benefit regression to illustrate its strengths and limitations. Net benefit regression offers a simple option for cost-effectiveness analyses of person-level data. By placing economic evaluation in a regression framework, regression-based techniques can facilitate the analysis and provide simple solutions to commonly encountered challenges. Economic evaluations of person-level data (eg, from a clinical trial) should use net benefit regression to facilitate analysis and enhance results.

Formation of a new archetypal Metal-Organic Framework from a simple monatomic liquid

NASA Astrophysics Data System (ADS)

Metere, Alfredo; Oleynikov, Peter; Dzugutov, Mikhail; O'Keeffe, Michael

2014-12-01

We report a molecular-dynamics simulation of a single-component system of particles interacting via a spherically symmetric potential that is found to form, upon cooling from a liquid state, a low-density porous crystalline phase. Its structure analysis demonstrates that the crystal can be described by a net with a topology that belongs to the class of topologies characteristic of the Metal-Organic Frameworks (MOFs). The observed net is new, and it is now included in the Reticular Chemistry Structure Resource database. The observation that a net topology characteristic of MOF crystals, which are known to be formed by a coordination-driven self-assembly process, can be reproduced by a thermodynamically stable configuration of a simple single-component system of particles opens a possibility of using these models in studies of MOF nets. It also indicates that structures with MOF topology, as well as other low-density porous crystalline structures can possibly be produced in colloidal systems of spherical particles, with an appropriate tuning of interparticle interaction.

Neural correlates of the difference between working memory speed and simple sensorimotor speed: an fMRI study.

PubMed

Takeuchi, Hikaru; Sugiura, Motoaki; Sassa, Yuko; Sekiguchi, Atsushi; Yomogida, Yukihito; Taki, Yasuyuki; Kawashima, Ryuta

2012-01-01

The difference between the speed of simple cognitive processes and the speed of complex cognitive processes has various psychological correlates. However, the neural correlates of this difference have not yet been investigated. In this study, we focused on working memory (WM) for typical complex cognitive processes. Functional magnetic resonance imaging data were acquired during the performance of an N-back task, which is a measure of WM for typical complex cognitive processes. In our N-back task, task speed and memory load were varied to identify the neural correlates responsible for the difference between the speed of simple cognitive processes (estimated from the 0-back task) and the speed of WM. Our findings showed that this difference was characterized by the increased activation in the right dorsolateral prefrontal cortex (DLPFC) and the increased functional interaction between the right DLPFC and right superior parietal lobe. Furthermore, the local gray matter volume of the right DLPFC was correlated with participants' accuracy during fast WM tasks, which in turn correlated with a psychometric measure of participants' intelligence. Our findings indicate that the right DLPFC and its related network are responsible for the execution of the fast cognitive processes involved in WM. Identified neural bases may underlie the psychometric differences between the speed with which subjects perform simple cognitive tasks and the speed with which subjects perform more complex cognitive tasks, and explain the previous traditional psychological findings.

Neural net target-tracking system using structured laser patterns

NASA Astrophysics Data System (ADS)

Cho, Jae-Wan; Lee, Yong-Bum; Lee, Nam-Ho; Park, Soon-Yong; Lee, Jongmin; Choi, Gapchu; Baek, Sunghyun; Park, Dong-Sun

1996-06-01

In this paper, we describe a robot endeffector tracking system using sensory information from recently-announced structured pattern laser diodes, which can generate images with several different types of structured pattern. The neural network approach is employed to recognize the robot endeffector covering the situation of three types of motion: translation, scaling and rotation. Features for the neural network to detect the position of the endeffector are extracted from the preprocessed images. Artificial neural networks are used to store models and to match with unknown input features recognizing the position of the robot endeffector. Since a minimal number of samples are used for different directions of the robot endeffector in the system, an artificial neural network with the generalization capability can be utilized for unknown input features. A feedforward neural network with the generalization capability can be utilized for unknown input features. A feedforward neural network trained with the back propagation learning is used to detect the position of the robot endeffector. Another feedforward neural network module is used to estimate the motion from a sequence of images and to control movements of the robot endeffector. COmbining the tow neural networks for recognizing the robot endeffector and estimating the motion with the preprocessing stage, the whole system keeps tracking of the robot endeffector effectively.

Extraction of Built-Up Areas Using Convolutional Neural Networks and Transfer Learning from SENTINEL-2 Satellite Images

NASA Astrophysics Data System (ADS)

Bramhe, V. S.; Ghosh, S. K.; Garg, P. K.

2018-04-01

With rapid globalization, the extent of built-up areas is continuously increasing. Extraction of features for classifying built-up areas that are more robust and abstract is a leading research topic from past many years. Although, various studies have been carried out where spatial information along with spectral features has been utilized to enhance the accuracy of classification. Still, these feature extraction techniques require a large number of user-specific parameters and generally application specific. On the other hand, recently introduced Deep Learning (DL) techniques requires less number of parameters to represent more abstract aspects of the data without any manual effort. Since, it is difficult to acquire high-resolution datasets for applications that require large scale monitoring of areas. Therefore, in this study Sentinel-2 image has been used for built-up areas extraction. In this work, pre-trained Convolutional Neural Networks (ConvNets) i.e. Inception v3 and VGGNet are employed for transfer learning. Since these networks are trained on generic images of ImageNet dataset which are having very different characteristics from satellite images. Therefore, weights of networks are fine-tuned using data derived from Sentinel-2 images. To compare the accuracies with existing shallow networks, two state of art classifiers i.e. Gaussian Support Vector Machine (SVM) and Back-Propagation Neural Network (BP-NN) are also implemented. Both SVM and BP-NN gives 84.31 % and 82.86 % overall accuracies respectively. Inception-v3 and VGGNet gives 89.43 % of overall accuracy using fine-tuned VGGNet and 92.10 % when using Inception-v3. The results indicate high accuracy of proposed fine-tuned ConvNets on a 4-channel Sentinel-2 dataset for built-up area extraction.

Study on the Classification of GAOFEN-3 Polarimetric SAR Images Using Deep Neural Network

NASA Astrophysics Data System (ADS)

Zhang, J.; Zhang, J.; Zhao, Z.

2018-04-01

Polarimetric Synthetic Aperture Radar (POLSAR) imaging principle determines that the image quality will be affected by speckle noise. So the recognition accuracy of traditional image classification methods will be reduced by the effect of this interference. Since the date of submission, Deep Convolutional Neural Network impacts on the traditional image processing methods and brings the field of computer vision to a new stage with the advantages of a strong ability to learn deep features and excellent ability to fit large datasets. Based on the basic characteristics of polarimetric SAR images, the paper studied the types of the surface cover by using the method of Deep Learning. We used the fully polarimetric SAR features of different scales to fuse RGB images to the GoogLeNet model based on convolution neural network Iterative training, and then use the trained model to test the classification of data validation.First of all, referring to the optical image, we mark the surface coverage type of GF-3 POLSAR image with 8m resolution, and then collect the samples according to different categories. To meet the GoogLeNet model requirements of 256 × 256 pixel image input and taking into account the lack of full-resolution SAR resolution, the original image should be pre-processed in the process of resampling. In this paper, POLSAR image slice samples of different scales with sampling intervals of 2 m and 1 m to be trained separately and validated by the verification dataset. Among them, the training accuracy of GoogLeNet model trained with resampled 2-m polarimetric SAR image is 94.89 %, and that of the trained SAR image with resampled 1 m is 92.65 %.

Use of genetic programming, logistic regression, and artificial neural nets to predict readmission after coronary artery bypass surgery.

PubMed

Engoren, Milo; Habib, Robert H; Dooner, John J; Schwann, Thomas A

2013-08-01

As many as 14 % of patients undergoing coronary artery bypass surgery are readmitted within 30 days. Readmission is usually the result of morbidity and may lead to death. The purpose of this study is to develop and compare statistical and genetic programming models to predict readmission. Patients were divided into separate Construction and Validation populations. Using 88 variables, logistic regression, genetic programs, and artificial neural nets were used to develop predictive models. Models were first constructed and tested on the Construction populations, then validated on the Validation population. Areas under the receiver operator characteristic curves (AU ROC) were used to compare the models. Two hundred and two patients (7.6 %) in the 2,644 patient Construction group and 216 (8.0 %) of the 2,711 patient Validation group were re-admitted within 30 days of CABG surgery. Logistic regression predicted readmission with AU ROC = .675 ± .021 in the Construction group. Genetic programs significantly improved the accuracy, AU ROC = .767 ± .001, p < .001). Artificial neural nets were less accurate with AU ROC = 0.597 ± .001 in the Construction group. Predictive accuracy of all three techniques fell in the Validation group. However, the accuracy of genetic programming (AU ROC = .654 ± .001) was still trivially but statistically non-significantly better than that of the logistic regression (AU ROC = .644 ± .020, p = .61). Genetic programming and logistic regression provide alternative methods to predict readmission that are similarly accurate.

Projection decomposition algorithm for dual-energy computed tomography via deep neural network.

PubMed

Xu, Yifu; Yan, Bin; Chen, Jian; Zeng, Lei; Li, Lei

2018-03-15

Dual-energy computed tomography (DECT) has been widely used to improve identification of substances from different spectral information. Decomposition of the mixed test samples into two materials relies on a well-calibrated material decomposition function. This work aims to establish and validate a data-driven algorithm for estimation of the decomposition function. A deep neural network (DNN) consisting of two sub-nets is proposed to solve the projection decomposition problem. The compressing sub-net, substantially a stack auto-encoder (SAE), learns a compact representation of energy spectrum. The decomposing sub-net with a two-layer structure fits the nonlinear transform between energy projection and basic material thickness. The proposed DNN not only delivers image with lower standard deviation and higher quality in both simulated and real data, and also yields the best performance in cases mixed with photon noise. Moreover, DNN costs only 0.4 s to generate a decomposition solution of 360 × 512 size scale, which is about 200 times faster than the competing algorithms. The DNN model is applicable to the decomposition tasks with different dual energies. Experimental results demonstrated the strong function fitting ability of DNN. Thus, the Deep learning paradigm provides a promising approach to solve the nonlinear problem in DECT.

Neuromorphic learning of continuous-valued mappings from noise-corrupted data. Application to real-time adaptive control

NASA Technical Reports Server (NTRS)

Troudet, Terry; Merrill, Walter C.

1990-01-01

The ability of feed-forward neural network architectures to learn continuous valued mappings in the presence of noise was demonstrated in relation to parameter identification and real-time adaptive control applications. An error function was introduced to help optimize parameter values such as number of training iterations, observation time, sampling rate, and scaling of the control signal. The learning performance depended essentially on the degree of embodiment of the control law in the training data set and on the degree of uniformity of the probability distribution function of the data that are presented to the net during sequence. When a control law was corrupted by noise, the fluctuations of the training data biased the probability distribution function of the training data sequence. Only if the noise contamination is minimized and the degree of embodiment of the control law is maximized, can a neural net develop a good representation of the mapping and be used as a neurocontroller. A multilayer net was trained with back-error-propagation to control a cart-pole system for linear and nonlinear control laws in the presence of data processing noise and measurement noise. The neurocontroller exhibited noise-filtering properties and was found to operate more smoothly than the teacher in the presence of measurement noise.

Trading spaces: building three-dimensional nets from two-dimensional tilings

PubMed Central

Castle, Toen; Evans, Myfanwy E.; Hyde, Stephen T.; Ramsden, Stuart; Robins, Vanessa

2012-01-01

We construct some examples of finite and infinite crystalline three-dimensional nets derived from symmetric reticulations of homogeneous two-dimensional spaces: elliptic (S2), Euclidean (E2) and hyperbolic (H2) space. Those reticulations are edges and vertices of simple spherical, planar and hyperbolic tilings. We show that various projections of the simplest symmetric tilings of those spaces into three-dimensional Euclidean space lead to topologically and geometrically complex patterns, including multiple interwoven nets and tangled nets that are otherwise difficult to generate ab initio in three dimensions. PMID:24098839

Analysis of Salinity Intrusion in the San Francisco Bay-Delta Using a GA-Optimized Neural Net, and Application of the Model to Prediction in the Elkhorn Slough Habitat

NASA Astrophysics Data System (ADS)

Thompson, D. E.; Rajkumar, T.

2002-12-01

The San Francisco Bay Delta is a large hydrodynamic complex that incorporates the Sacramento and San Joaquin Estuaries, the Suisan Marsh, and the San Francisco Bay proper. Competition exists for the use of this extensive water system both from the fisheries industry, the agricultural industry, and from the marine and estuarine animal species within the Delta. As tidal fluctuations occur, more saline water pushes upstream allowing fish to migrate beyond the Suisan Marsh for breeding and habitat occupation. However, the agriculture industry does not want extensive salinity intrusion to impact water quality for human and plant consumption. The balance is regulated by pumping stations located along the estuaries and reservoirs whereby flushing of fresh water keeps the saline intrusion at bay. The pumping schedule is driven by data collected at various locations within the Bay Delta and by numerical models that predict the salinity intrusion as part of a larger model of the system. The Interagency Ecological Program (IEP) for the San Francisco Bay / Sacramento-San Joaquin Estuary collects, monitors, and archives the data, and the Department of Water Resources provides a numerical model simulation (DSM2) from which predictions are made that drive the pumping schedule. A problem with DSM2 is that the numerical simulation takes roughly 16 hours to complete a prediction. We have created a neural net, optimized with a genetic algorithm, that takes as input the archived data from multiple gauging stations and predicts stage, salinity, and flow at the Carquinez Straits (at the downstream end of the Suisan Marsh). This model seems to be robust in its predictions and operates much faster than the current numerical DSM2 model. Because the Bay-Delta is strongly tidally driven, we used both Principal Component Analysis and Fast Fourier Transforms to discover dominant features within the IEP data. We then filtered out the dominant tidal forcing to discover non-primary tidal effects, and used this to enhance the neural network by mapping input-output relationships in a more efficient manner. Furthermore, the neural network implicitly incorporates both the hydrodynamic and water quality models into a single predictive system. Although our model has not yet been enhanced to demonstrate improve pumping schedules, it has the possibility to support better decision-making procedures that may then be implemented by State agencies if desired. Our intention is now to use our calibrated Bay-Delta neural model in the smaller Elkhorn Slough complex near Monterey Bay where no such hydrodynamic model currently exists. At the Elkhorn Slough, we are fusing the neural net model of tidally-driven flow with in situ flow data and airborne and satellite remote sensing data. These further constrain the behavior of the model in predicting the longer-term health and future of this vital estuary. In particular, we are using visible data to explore the effects of the sediment plume that wastes into Monterey Bay, and infrared data and thermal emissivities to characterize the plant habitat along the margins of the Slough as salinity intrusion and sediment removal change the boundary of the estuary. The details of the Bay-Delta neural net model and its application to the Elkhorn Slough are presented in this paper.

The Zebrafish Brain in Research and Teaching: A Simple in Vivo and in Vitro Model for the Study of Spontaneous Neural Activity

ERIC Educational Resources Information Center

Vargas, R.; Johannesdottir, I. P.; Sigurgeirsson, B.; Porsteinsson, H.; Karlsson, K. AE.

2011-01-01

Recently, the zebrafish ("Danio rerio") has been established as a key animal model in neuroscience. Behavioral, genetic, and immunohistochemical techniques have been used to describe the connectivity of diverse neural circuits. However, few studies have used zebrafish to understand the function of cerebral structures or to study neural circuits.…

Complex versus simple models: ion-channel cardiac toxicity prediction.

PubMed

Mistry, Hitesh B

2018-01-01

There is growing interest in applying detailed mathematical models of the heart for ion-channel related cardiac toxicity prediction. However, a debate as to whether such complex models are required exists. Here an assessment in the predictive performance between two established large-scale biophysical cardiac models and a simple linear model B net was conducted. Three ion-channel data-sets were extracted from literature. Each compound was designated a cardiac risk category using two different classification schemes based on information within CredibleMeds. The predictive performance of each model within each data-set for each classification scheme was assessed via a leave-one-out cross validation. Overall the B net model performed equally as well as the leading cardiac models in two of the data-sets and outperformed both cardiac models on the latest. These results highlight the importance of benchmarking complex versus simple models but also encourage the development of simple models.

Modeling of cortical signals using echo state networks

NASA Astrophysics Data System (ADS)

Zhou, Hanying; Wang, Yongji; Huang, Jiangshuai

2009-10-01

Diverse modeling frameworks have been utilized with the ultimate goal of translating brain cortical signals into prediction of visible behavior. The inputs to these models are usually multidimensional neural recordings collected from relevant regions of a monkey's brain while the outputs are the associated behavior which is typically the 2-D or 3-D hand position of a primate. Here our task is to set up a proper model in order to figure out the move trajectories by input the neural signals which are simultaneously collected in the experiment. In this paper, we propose to use Echo State Networks (ESN) to map the neural firing activities into hand positions. ESN is a newly developed recurrent neural network(RNN) model. Besides its dynamic property and short term memory just as other recurrent neural networks have, it has a special echo state property which endows it with the ability to model nonlinear dynamic systems powerfully. What distinguished it from transitional recurrent neural networks most significantly is its special learning method. In this paper we train this net with a refined version of its typical training method and get a better model.

NEURAL NET ANALYSIS OF SALINITY IN THE SACRAMENTO BAY/DELTA SYSTEM. (R825285)

EPA Science Inventory

The perspectives, information and conclusions conveyed in research project abstracts, progress reports, final reports, journal abstracts and journal publications convey the viewpoints of the principal investigator and may not represent the views and policies of ORD and EPA. Concl...

Survey of Neural Net Paradigms for Specification of Discrete Networks.

DTIC Science & Technology

1988-01-31

special applications, such as 3-d imaging, scene segmentation, temporal imaging models, nor phonological analysis of speech. The cost of problem...Nov. 1985. ., .U U - - A 1 Bibliography Berge, Claude, "Principles of Combinatorics", Academic Press, 1971 Fischer, Roland, " Deconstructing Reality

Comparison of polynomial approximations and artificial neural nets for response surfaces in engineering optimization

NASA Technical Reports Server (NTRS)

Carpenter, William C.

1991-01-01

Engineering optimization problems involve minimizing some function subject to constraints. In areas such as aircraft optimization, the constraint equations may be from numerous disciplines such as transfer of information between these disciplines and the optimization algorithm. They are also suited to problems which may require numerous re-optimizations such as in multi-objective function optimization or to problems where the design space contains numerous local minima, thus requiring repeated optimizations from different initial designs. Their use has been limited, however, by the fact that development of response surfaces randomly selected or preselected points in the design space. Thus, they have been thought to be inefficient compared to algorithms to the optimum solution. A development has taken place in the last several years which may effect the desirability of using response surfaces. It may be possible that artificial neural nets are more efficient in developing response surfaces than polynomial approximations which have been used in the past. This development is the concern of the work.

Retrieved Products from Simulated Hyperspectral Observations of a Hurricane

NASA Technical Reports Server (NTRS)

Susskind, Joel; Kouvaris, Louis; Iredell, Lena; Blaisdell, John

2015-01-01

Retrievals were run using the AIRS Science Team Version-6 AIRS Only retrieval algorithm, which generates a Neural-Net first guess (T(sub s))(sup 0), (T(p))(sup 0), and (q(p))(sup 0) as a function of observed AIRS radiances. AIRS Science Team Neural-Net coefficients performed very well beneath 300 mb using the simulated radiances. This means the simulated radiances are very realistic. First guess and retrieved values of T(p) above 300 mb were biased cold, but both represented the model spatial structure very well. QC'd T(p) and q(p) retrievals for all experiments had similar accuracies compared to their own truth fields, and were roughly consistent with results obtained using real data. Spatial coverage of retrievals, as well as the representativeness of the spatial structure of the storm, improved dramatically with decreasing size of the instrument's FOV. We sent QC'd values of T(p) and q(p) to Bob Atlas at AOML for use as input to OSSE Data Assimilation experiments.

Localization of lung fields in HRCT images using a deep convolution neural network

NASA Astrophysics Data System (ADS)

Kumar, Abhishek; Agarwala, Sunita; Dhara, Ashis Kumar; Mukhopadhyay, Sudipta; Nandi, Debashis; Garg, Mandeep; Khandelwal, Niranjan; Kalra, Naveen

2018-02-01

Lung field segmentation is a prerequisite step for the development of a computer-aided diagnosis system for interstitial lung diseases observed in chest HRCT images. Conventional methods of lung field segmentation rely on a large gray value contrast between lung fields and surrounding tissues. These methods fail on lung HRCT images with dense and diffused pathology. An efficient prepro- cessing could improve the accuracy of segmentation of pathological lung field in HRCT images. In this paper, a convolution neural network is used for localization of lung fields in HRCT images. The proposed method provides an optimal bounding box enclosing the lung fields irrespective of the presence of diffuse pathology. The performance of the proposed algorithm is validated on 330 lung HRCT images obtained from MedGift database on ZF and VGG networks. The model achieves a mean average precision of 0.94 with ZF net and a slightly better performance giving a mean average precision of 0.95 in case of VGG net.

Applications of neural networks to landmark detection in 3-D surface data

NASA Astrophysics Data System (ADS)

Arndt, Craig M.

1992-09-01

The problem of identifying key landmarks in 3-dimensional surface data is of considerable interest in solving a number of difficult real-world tasks, including object recognition and image processing. The specific problem that we address in this research is to identify the specific landmarks (anatomical) in human surface data. This is a complex task, currently performed visually by an expert human operator. In order to replace these human operators and increase reliability of the data acquisition, we need to develop a computer algorithm which will utilize the interrelations between the 3-dimensional data to identify the landmarks of interest. The current presentation describes a method for designing, implementing, training, and testing a custom architecture neural network which will perform the landmark identification task. We discuss the performance of the net in relationship to human performance on the same task and how this net has been integrated with other AI and traditional programming methods to produce a powerful analysis tool for computer anthropometry.

Implementation of a pulse coupled neural network in FPGA.

PubMed

Waldemark, J; Millberg, M; Lindblad, T; Waldemark, K; Becanovic, V

2000-06-01

The Pulse Coupled neural network, PCNN, is a biologically inspired neural net and it can be used in various image analysis applications, e.g. time-critical applications in the field of image pre-processing like segmentation, filtering, etc. a VHDL implementation of the PCNN targeting FPGA was undertaken and the results presented here. The implementation contains many interesting features. By pipelining the PCNN structure a very high throughput of 55 million neuron iterations per second could be achieved. By making the coefficients re-configurable during operation, a complete recognition system could be implemented on one, or maybe two, chip(s). Reconsidering the ranges and resolutions of the constants may save a lot of hardware, since the higher resolution requires larger multipliers, adders, memories etc.

Programmable synaptic devices for electronic neural nets

NASA Technical Reports Server (NTRS)

Moopenn, A.; Thakoor, A. P.

1990-01-01

The architecture, design, and operational characteristics of custom VLSI and thin film synaptic devices are described. The devices include CMOS-based synaptic chips containing 1024 reprogrammable synapses with a 6-bit dynamic range, and nonvolatile, write-once, binary synaptic arrays based on memory switching in hydrogenated amorphous silicon films. Their suitability for embodiment of fully parallel and analog neural hardware is discussed. Specifically, a neural network solution to an assignment problem of combinatorial global optimization, implemented in fully parallel hardware using the synaptic chips, is described. The network's ability to provide optimal and near optimal solutions over a time scale of few neuron time constants has been demonstrated and suggests a speedup improvement of several orders of magnitude over conventional search methods.

Gas Classification Using Deep Convolutional Neural Networks.

PubMed

Peng, Pai; Zhao, Xiaojin; Pan, Xiaofang; Ye, Wenbin

2018-01-08

In this work, we propose a novel Deep Convolutional Neural Network (DCNN) tailored for gas classification. Inspired by the great success of DCNN in the field of computer vision, we designed a DCNN with up to 38 layers. In general, the proposed gas neural network, named GasNet, consists of: six convolutional blocks, each block consist of six layers; a pooling layer; and a fully-connected layer. Together, these various layers make up a powerful deep model for gas classification. Experimental results show that the proposed DCNN method is an effective technique for classifying electronic nose data. We also demonstrate that the DCNN method can provide higher classification accuracy than comparable Support Vector Machine (SVM) methods and Multiple Layer Perceptron (MLP).

Gas Classification Using Deep Convolutional Neural Networks

PubMed Central

Peng, Pai; Zhao, Xiaojin; Pan, Xiaofang; Ye, Wenbin

2018-01-01

In this work, we propose a novel Deep Convolutional Neural Network (DCNN) tailored for gas classification. Inspired by the great success of DCNN in the field of computer vision, we designed a DCNN with up to 38 layers. In general, the proposed gas neural network, named GasNet, consists of: six convolutional blocks, each block consist of six layers; a pooling layer; and a fully-connected layer. Together, these various layers make up a powerful deep model for gas classification. Experimental results show that the proposed DCNN method is an effective technique for classifying electronic nose data. We also demonstrate that the DCNN method can provide higher classification accuracy than comparable Support Vector Machine (SVM) methods and Multiple Layer Perceptron (MLP). PMID:29316723

Introduction to a system for implementing neural net connections on SIMD architectures

NASA Technical Reports Server (NTRS)

Tomboulian, Sherryl

1988-01-01

Neural networks have attracted much interest recently, and using parallel architectures to simulate neural networks is a natural and necessary application. The SIMD model of parallel computation is chosen, because systems of this type can be built with large numbers of processing elements. However, such systems are not naturally suited to generalized communication. A method is proposed that allows an implementation of neural network connections on massively parallel SIMD architectures. The key to this system is an algorithm permitting the formation of arbitrary connections between the neurons. A feature is the ability to add new connections quickly. It also has error recovery ability and is robust over a variety of network topologies. Simulations of the general connection system, and its implementation on the Connection Machine, indicate that the time and space requirements are proportional to the product of the average number of connections per neuron and the diameter of the interconnection network.

Introduction to a system for implementing neural net connections on SIMD architectures

NASA Technical Reports Server (NTRS)

Tomboulian, Sherryl

1988-01-01

Neural networks have attracted much interest recently, and using parallel architectures to simulate neural networks is a natural and necessary application. The SIMD model of parallel computation is chosen, because systems of this type can be built with large numbers of processing elements. However, such systems are not naturally suited to generalized elements. A method is proposed that allows an implementation of neural network connections on massively parallel SIMD architectures. The key to this system is an algorithm permitting the formation of arbitrary connections between the neurons. A feature is the ability to add new connections quickly. It also has error recovery ability and is robust over a variety of network topologies. Simulations of the general connection system, and its implementation on the Connection Machine, indicate that the time and space requirements are proportional to the product of the average number of connections per neuron and the diameter of the interconnection network.

Use of statistical and neural net approaches in predicting toxicity of chemicals.

PubMed

Basak, S C; Grunwald, G D; Gute, B D; Balasubramanian, K; Opitz, D

2000-01-01

Hierarchical quantitative structure-activity relationships (H-QSAR) have been developed as a new approach in constructing models for estimating physicochemical, biomedicinal, and toxicological properties of interest. This approach uses increasingly more complex molecular descriptors in a graduated approach to model building. In this study, statistical and neural network methods have been applied to the development of H-QSAR models for estimating the acute aquatic toxicity (LC50) of 69 benzene derivatives to Pimephales promelas (fathead minnow). Topostructural, topochemical, geometrical, and quantum chemical indices were used as the four levels of the hierarchical method. It is clear from both the statistical and neural network models that topostructural indices alone cannot adequately model this set of congeneric chemicals. Not surprisingly, topochemical indices greatly increase the predictive power of both statistical and neural network models. Quantum chemical indices also add significantly to the modeling of this set of acute aquatic toxicity data.

A structural study of the complex between neuroepithelial cell transforming gene 1 (Net1) and RhoA reveals a potential anticancer drug hot spot.

PubMed

Petit, Alain-Pierre; Garcia-Petit, Christel; Bueren-Calabuig, Juan A; Vuillard, Laurent M; Ferry, Gilles; Boutin, Jean A

2018-06-08

The GTPase RhoA is a major player in many different regulatory pathways. RhoA catalyzes GTP hydrolysis, and its catalysis is accelerated when RhoA forms heterodimers with proteins of the guanine nucleotide exchange factor (GEF) family. Neuroepithelial cell transforming gene 1 (Net1) is a RhoA-interacting GEF implicated in cancer, but the structural features supporting the RhoA/Net1 interaction are unknown. Taking advantage of a simple production and purification process, here we solved the structure of a RhoA/Net1 heterodimer with X-ray crystallography at 2-Å resolution. Using a panel of several techniques, including molecular dynamics simulations, we characterized the RhoA/Net1 interface. Moreover, deploying an extremely simple peptide-based scanning approach, we found that short peptides (penta- to nonapeptides) derived from the protein/protein interaction region of RhoA could disrupt the RhoA/Net1 interaction and thereby diminish the rate of nucleotide exchange. The most inhibitory peptide, EVKHF, spanning residues 102-106 in the RhoA sequence, displayed an IC 50 of ∼100 μm without further modifications. The peptides identified here could be useful in further investigations of the RhoA/Net1 interaction region. We propose that our structural and functional insights might inform chemical approaches for transforming the pentapeptide into an optimized pseudopeptide that antagonizes Net1-mediated RhoA activation with therapeutic anticancer potential. © 2018 by The American Society for Biochemistry and Molecular Biology, Inc.

Competing dopamine neurons drive oviposition choice for ethanol in Drosophila.

PubMed

Azanchi, Reza; Kaun, Karla R; Heberlein, Ulrike

2013-12-24

The neural circuits that mediate behavioral choice evaluate and integrate information from the environment with internal demands and then initiate a behavioral response. Even circuits that support simple decisions remain poorly understood. In Drosophila melanogaster, oviposition on a substrate containing ethanol enhances fitness; however, little is known about the neural mechanisms mediating this important choice behavior. Here, we characterize the neural modulation of this simple choice and show that distinct subsets of dopaminergic neurons compete to either enhance or inhibit egg-laying preference for ethanol-containing food. Moreover, activity in α'β' neurons of the mushroom body and a subset of ellipsoid body ring neurons (R2) is required for this choice. We propose a model where competing dopaminergic systems modulate oviposition preference to adjust to changes in natural oviposition substrates.

Underlying neural mechanisms of mirror therapy: Implications for motor rehabilitation in stroke.

PubMed

Arya, Kamal Narayan

2016-01-01

Mirror therapy (MT) is a valuable method for enhancing motor recovery in poststroke hemiparesis. The technique utilizes the mirror-illusion created by the movement of sound limb that is perceived as the paretic limb. MT is a simple and economical technique than can stimulate the brain noninvasively. The intervention unquestionably has neural foundation. But the underlying neural mechanisms inducing motor recovery are still unclear. In this review, the neural-modulation due to MT has been explored. Multiple areas of the brain such as the occipital lobe, dorsal frontal area and corpus callosum are involved during the simple MT regime. Bilateral premotor cortex, primary motor cortex, primary somatosensory cortex, and cerebellum also get reorganized to enhance the function of the damaged brain. The motor areas of the lesioned hemisphere receive visuo-motor processing information through the parieto-occipital lobe. The damaged motor cortex responds variably to the MT and may augment true motor recovery. Mirror neurons may also play a possible role in the cortico-stimulatory mechanisms occurring due to the MT.

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

New milk protein-derived peptides with potential antimicrobial activity: an approach based on bioinformatic studies.

PubMed

Dziuba, Bartłomiej; Dziuba, Marta

2014-08-20

New peptides with potential antimicrobial activity, encrypted in milk protein sequences, were searched for with the use of bioinformatic tools. The major milk proteins were hydrolyzed in silico by 28 enzymes. The obtained peptides were characterized by the following parameters: molecular weight, isoelectric point, composition and number of amino acid residues, net charge at pH 7.0, aliphatic index, instability index, Boman index, and GRAVY index, and compared with those calculated for known 416 antimicrobial peptides including 59 antimicrobial peptides (AMPs) from milk proteins listed in the BIOPEP database. A simple analysis of physico-chemical properties and the values of biological activity indicators were insufficient to select potentially antimicrobial peptides released in silico from milk proteins by proteolytic enzymes. The final selection was made based on the results of multidimensional statistical analysis such as support vector machines (SVM), random forest (RF), artificial neural networks (ANN) and discriminant analysis (DA) available in the Collection of Anti-Microbial Peptides (CAMP database). Eleven new peptides with potential antimicrobial activity were selected from all peptides released during in silico proteolysis of milk proteins.

New Milk Protein-Derived Peptides with Potential Antimicrobial Activity: An Approach Based on Bioinformatic Studies

PubMed Central

Dziuba, Bartłomiej; Dziuba, Marta

2014-01-01

New peptides with potential antimicrobial activity, encrypted in milk protein sequences, were searched for with the use of bioinformatic tools. The major milk proteins were hydrolyzed in silico by 28 enzymes. The obtained peptides were characterized by the following parameters: molecular weight, isoelectric point, composition and number of amino acid residues, net charge at pH 7.0, aliphatic index, instability index, Boman index, and GRAVY index, and compared with those calculated for known 416 antimicrobial peptides including 59 antimicrobial peptides (AMPs) from milk proteins listed in the BIOPEP database. A simple analysis of physico-chemical properties and the values of biological activity indicators were insufficient to select potentially antimicrobial peptides released in silico from milk proteins by proteolytic enzymes. The final selection was made based on the results of multidimensional statistical analysis such as support vector machines (SVM), random forest (RF), artificial neural networks (ANN) and discriminant analysis (DA) available in the Collection of Anti-Microbial Peptides (CAMP database). Eleven new peptides with potential antimicrobial activity were selected from all peptides released during in silico proteolysis of milk proteins. PMID:25141106

Forecasting volatility with neural regression: a contribution to model adequacy.

PubMed

Refenes, A N; Holt, W T

2001-01-01

Neural nets' usefulness for forecasting is limited by problems of overfitting and the lack of rigorous procedures for model identification, selection and adequacy testing. This paper describes a methodology for neural model misspecification testing. We introduce a generalization of the Durbin-Watson statistic for neural regression and discuss the general issues of misspecification testing using residual analysis. We derive a generalized influence matrix for neural estimators which enables us to evaluate the distribution of the statistic. We deploy Monte Carlo simulation to compare the power of the test for neural and linear regressors. While residual testing is not a sufficient condition for model adequacy, it is nevertheless a necessary condition to demonstrate that the model is a good approximation to the data generating process, particularly as neural-network estimation procedures are susceptible to partial convergence. The work is also an important step toward developing rigorous procedures for neural model identification, selection and adequacy testing which have started to appear in the literature. We demonstrate its applicability in the nontrivial problem of forecasting implied volatility innovations using high-frequency stock index options. Each step of the model building process is validated using statistical tests to verify variable significance and model adequacy with the results confirming the presence of nonlinear relationships in implied volatility innovations.

Using neural networks and Dyna algorithm for integrated planning, reacting and learning in systems

NASA Technical Reports Server (NTRS)

Lima, Pedro; Beard, Randal

1992-01-01

The traditional AI answer to the decision making problem for a robot is planning. However, planning is usually CPU-time consuming, depending on the availability and accuracy of a world model. The Dyna system generally described in earlier work, uses trial and error to learn a world model which is simultaneously used to plan reactions resulting in optimal action sequences. It is an attempt to integrate planning, reactive, and learning systems. The architecture of Dyna is presented. The different blocks are described. There are three main components of the system. The first is the world model used by the robot for internal world representation. The input of the world model is the current state and the action taken in the current state. The output is the corresponding reward and resulting state. The second module in the system is the policy. The policy observes the current state and outputs the action to be executed by the robot. At the beginning of program execution, the policy is stochastic and through learning progressively becomes deterministic. The policy decides upon an action according to the output of an evaluation function, which is the third module of the system. The evaluation function takes the following as input: the current state of the system, the action taken in that state, the resulting state, and a reward generated by the world which is proportional to the current distance from the goal state. Originally, the work proposed was as follows: (1) to implement a simple 2-D world where a 'robot' is navigating around obstacles, to learn the path to a goal, by using lookup tables; (2) to substitute the world model and Q estimate function Q by neural networks; and (3) to apply the algorithm to a more complex world where the use of a neural network would be fully justified. In this paper, the system design and achieved results will be described. First we implement the world model with a neural network and leave Q implemented as a look up table. Next, we use a lookup table for the world model and implement the Q function with a neural net. Time limitations prevented the combination of these two approaches. The final section discusses the results and gives clues for future work.

Comparisons of a Quantum Annealing and Classical Computer Neural Net Approach for Inferring Global Annual CO2 Fluxes over Land

NASA Astrophysics Data System (ADS)

Halem, M.; Radov, A.; Singh, D.

2017-12-01

Investigations of mid to high latitude atmospheric CO2 show growing amplitudes in seasonal variations over the past several decades. Recent high-resolution satellite measurements of CO2 concentration are now available for three years from the Orbiting Carbon Observatory-2. The Atmospheric Radiation Measurement (ARM) program of DOE has been making long-term CO2-flux measurements (in addition to CO2 concentration and an array of other meteorological quantities) at several towers and mobile sites located around the globe at half-hour frequencies. Recent papers have shown CO2 fluxes inferred by assimilating CO2 observations into ecosystem models are largely inconsistent with station observations. An investigation of how the biosphere has reacted to changes in atmospheric CO2 is essential to our understanding of potential climate-vegetation feedbacks. Thus, new approaches for calculating CO2-flux for assimilation into land surface models are necessary for improving the prediction of annual carbon uptake. In this study, we calculate and compare the predicted CO2 fluxes results employing a Feed Forward Backward Propagation Neural Network model on two architectures, (i) an IBM Minsky Computer node and (ii) a hybrid version of the ARC D-Wave quantum annealing computer. We compare the neural net results of predictions of CO2 flux from ARM station data for three different DOE ecosystem sites; an arid plains near Oklahoma City, a northern arctic site at Barrows AL, and a tropical rainforest site in the Amazon. Training times and predictive results for the calculating annual CO2 flux for the two architectures for each of the three sites are presented. Comparative results of predictions as measured by RMSE and MAE are discussed. Plots and correlations of observed vs predicted CO2 flux are also presented for all three sites. We show the estimated training times for quantum and classical calculations when extended to calculating global annual Carbon Uptake over land. We also examine the efficiency, dependability and resilience of the quantum neural net approach relative to classical computer systems in predicting annual CO2 flux globally.

Representation of the Characteristics of Piezoelectric Fiber Composites with Neural Networks

NASA Astrophysics Data System (ADS)

Yapici, A.; Bickraj, K.; Yenilmez, A.; Li, M.; Tansel, I. N.; Martin, S. A.; Pereira, C. M.; Roth, L. E.

2007-03-01

Ideal sensors for the future should be economical, efficient, highly intelligent, and capable of obtaining their operation power from the environment. The use of piezoelectric fiber composites coupled with a low power microprocessor and backpropagation type neural networks is proposed for the development of a simple sensor to estimate the characteristics of harmonic forces. Three neural networks were used for the estimation of amplitude, gain and variation of the load in the time domain. The average estimation errors of the neural networks were less than 8% in all of the studied cases.

The Topographical Mapping in Drosophila Central Complex Network and Its Signal Routing

PubMed Central

Chang, Po-Yen; Su, Ta-Shun; Shih, Chi-Tin; Lo, Chung-Chuan

2017-01-01

Neural networks regulate brain functions by routing signals. Therefore, investigating the detailed organization of a neural circuit at the cellular levels is a crucial step toward understanding the neural mechanisms of brain functions. To study how a complicated neural circuit is organized, we analyzed recently published data on the neural circuit of the Drosophila central complex, a brain structure associated with a variety of functions including sensory integration and coordination of locomotion. We discovered that, except for a small number of “atypical” neuron types, the network structure formed by the identified 194 neuron types can be described by only a few simple mathematical rules. Specifically, the topological mapping formed by these neurons can be reconstructed by applying a generation matrix on a small set of initial neurons. By analyzing how information flows propagate with or without the atypical neurons, we found that while the general pattern of signal propagation in the central complex follows the simple topological mapping formed by the “typical” neurons, some atypical neurons can substantially re-route the signal pathways, implying specific roles of these neurons in sensory signal integration. The present study provides insights into the organization principle and signal integration in the central complex. PMID:28443014

The Role of Competitive Inhibition and Top-Down Feedback in Binding during Object Recognition

PubMed Central

Wyatte, Dean; Herd, Seth; Mingus, Brian; O’Reilly, Randall

2012-01-01

How does the brain bind together visual features that are processed concurrently by different neurons into a unified percept suitable for processes such as object recognition? Here, we describe how simple, commonly accepted principles of neural processing can interact over time to solve the brain’s binding problem. We focus on mechanisms of neural inhibition and top-down feedback. Specifically, we describe how inhibition creates competition among neural populations that code different features, effectively suppressing irrelevant information, and thus minimizing illusory conjunctions. Top-down feedback contributes to binding in a similar manner, but by reinforcing relevant features. Together, inhibition and top-down feedback contribute to a competitive environment that ensures only the most appropriate features are bound together. We demonstrate this overall proposal using a biologically realistic neural model of vision that processes features across a hierarchy of interconnected brain areas. Finally, we argue that temporal synchrony plays only a limited role in binding – it does not simultaneously bind multiple objects, but does aid in creating additional contrast between relevant and irrelevant features. Thus, our overall theory constitutes a solution to the binding problem that relies only on simple neural principles without any binding-specific processes. PMID:22719733

From modulated Hebbian plasticity to simple behavior learning through noise and weight saturation.

PubMed

Soltoggio, Andrea; Stanley, Kenneth O

2012-10-01

Synaptic plasticity is a major mechanism for adaptation, learning, and memory. Yet current models struggle to link local synaptic changes to the acquisition of behaviors. The aim of this paper is to demonstrate a computational relationship between local Hebbian plasticity and behavior learning by exploiting two traditionally unwanted features: neural noise and synaptic weight saturation. A modulation signal is employed to arbitrate the sign of plasticity: when the modulation is positive, the synaptic weights saturate to express exploitative behavior; when it is negative, the weights converge to average values, and neural noise reconfigures the network's functionality. This process is demonstrated through simulating neural dynamics in the autonomous emergence of fearful and aggressive navigating behaviors and in the solution to reward-based problems. The neural model learns, memorizes, and modifies different behaviors that lead to positive modulation in a variety of settings. The algorithm establishes a simple relationship between local plasticity and behavior learning by demonstrating the utility of noise and weight saturation. Moreover, it provides a new tool to simulate adaptive behavior, and contributes to bridging the gap between synaptic changes and behavior in neural computation. Copyright © 2012 Elsevier Ltd. All rights reserved.

Goal-Directed Decision Making with Spiking Neurons.

PubMed

Friedrich, Johannes; Lengyel, Máté

2016-02-03

Behavioral and neuroscientific data on reward-based decision making point to a fundamental distinction between habitual and goal-directed action selection. The formation of habits, which requires simple updating of cached values, has been studied in great detail, and the reward prediction error theory of dopamine function has enjoyed prominent success in accounting for its neural bases. In contrast, the neural circuit mechanisms of goal-directed decision making, requiring extended iterative computations to estimate values online, are still unknown. Here we present a spiking neural network that provably solves the difficult online value estimation problem underlying goal-directed decision making in a near-optimal way and reproduces behavioral as well as neurophysiological experimental data on tasks ranging from simple binary choice to sequential decision making. Our model uses local plasticity rules to learn the synaptic weights of a simple neural network to achieve optimal performance and solves one-step decision-making tasks, commonly considered in neuroeconomics, as well as more challenging sequential decision-making tasks within 1 s. These decision times, and their parametric dependence on task parameters, as well as the final choice probabilities match behavioral data, whereas the evolution of neural activities in the network closely mimics neural responses recorded in frontal cortices during the execution of such tasks. Our theory provides a principled framework to understand the neural underpinning of goal-directed decision making and makes novel predictions for sequential decision-making tasks with multiple rewards. Goal-directed actions requiring prospective planning pervade decision making, but their circuit-level mechanisms remain elusive. We show how a model circuit of biologically realistic spiking neurons can solve this computationally challenging problem in a novel way. The synaptic weights of our network can be learned using local plasticity rules such that its dynamics devise a near-optimal plan of action. By systematically comparing our model results to experimental data, we show that it reproduces behavioral decision times and choice probabilities as well as neural responses in a rich set of tasks. Our results thus offer the first biologically realistic account for complex goal-directed decision making at a computational, algorithmic, and implementational level. Copyright © 2016 the authors 0270-6474/16/361529-18$15.00/0.

Goal-Directed Decision Making with Spiking Neurons

PubMed Central

Lengyel, Máté

2016-01-01

Behavioral and neuroscientific data on reward-based decision making point to a fundamental distinction between habitual and goal-directed action selection. The formation of habits, which requires simple updating of cached values, has been studied in great detail, and the reward prediction error theory of dopamine function has enjoyed prominent success in accounting for its neural bases. In contrast, the neural circuit mechanisms of goal-directed decision making, requiring extended iterative computations to estimate values online, are still unknown. Here we present a spiking neural network that provably solves the difficult online value estimation problem underlying goal-directed decision making in a near-optimal way and reproduces behavioral as well as neurophysiological experimental data on tasks ranging from simple binary choice to sequential decision making. Our model uses local plasticity rules to learn the synaptic weights of a simple neural network to achieve optimal performance and solves one-step decision-making tasks, commonly considered in neuroeconomics, as well as more challenging sequential decision-making tasks within 1 s. These decision times, and their parametric dependence on task parameters, as well as the final choice probabilities match behavioral data, whereas the evolution of neural activities in the network closely mimics neural responses recorded in frontal cortices during the execution of such tasks. Our theory provides a principled framework to understand the neural underpinning of goal-directed decision making and makes novel predictions for sequential decision-making tasks with multiple rewards. SIGNIFICANCE STATEMENT Goal-directed actions requiring prospective planning pervade decision making, but their circuit-level mechanisms remain elusive. We show how a model circuit of biologically realistic spiking neurons can solve this computationally challenging problem in a novel way. The synaptic weights of our network can be learned using local plasticity rules such that its dynamics devise a near-optimal plan of action. By systematically comparing our model results to experimental data, we show that it reproduces behavioral decision times and choice probabilities as well as neural responses in a rich set of tasks. Our results thus offer the first biologically realistic account for complex goal-directed decision making at a computational, algorithmic, and implementational level. PMID:26843636

Global Potential Net Prmary Production Predicted from Vegetation Class, Precipitation, and Temperature

USDA-ARS?s Scientific Manuscript database

Net Primary Production (NPP), the difference between CO2 fixed by photosynthesis and CO2 lost to autotrophic respiration, is one of the most important components of the carbon cycle. Our goal was to develop a simple regression model to estimate global NPP using climate and land cover data. Approxima...

Formation of a new archetypal Metal-Organic Framework from a simple monatomic liquid

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

Metere, Alfredo, E-mail: alfredo.metere@mmk.su.se; Oleynikov, Peter; Dzugutov, Mikhail

2014-12-21

We report a molecular-dynamics simulation of a single-component system of particles interacting via a spherically symmetric potential that is found to form, upon cooling from a liquid state, a low-density porous crystalline phase. Its structure analysis demonstrates that the crystal can be described by a net with a topology that belongs to the class of topologies characteristic of the Metal-Organic Frameworks (MOFs). The observed net is new, and it is now included in the Reticular Chemistry Structure Resource database. The observation that a net topology characteristic of MOF crystals, which are known to be formed by a coordination-driven self-assembly process,more » can be reproduced by a thermodynamically stable configuration of a simple single-component system of particles opens a possibility of using these models in studies of MOF nets. It also indicates that structures with MOF topology, as well as other low-density porous crystalline structures can possibly be produced in colloidal systems of spherical particles, with an appropriate tuning of interparticle interaction.« less

Sensory Gain Outperforms Efficient Readout Mechanisms in Predicting Attention-Related Improvements in Behavior

PubMed Central

Ester, Edward F.; Deering, Sean

2014-01-01

Spatial attention has been postulated to facilitate perceptual processing via several different mechanisms. For instance, attention can amplify neural responses in sensory areas (sensory gain), mediate neural variability (noise modulation), or alter the manner in which sensory signals are selectively read out by postsensory decision mechanisms (efficient readout). Even in the context of simple behavioral tasks, it is unclear how well each of these mechanisms can account for the relationship between attention-modulated changes in behavior and neural activity because few studies have systematically mapped changes between stimulus intensity, attentional focus, neural activity, and behavioral performance. Here, we used a combination of psychophysics, event-related potentials (ERPs), and quantitative modeling to explicitly link attention-related changes in perceptual sensitivity with changes in the ERP amplitudes recorded from human observers. Spatial attention led to a multiplicative increase in the amplitude of an early sensory ERP component (the P1, peaking ∼80–130 ms poststimulus) and in the amplitude of the late positive deflection component (peaking ∼230–330 ms poststimulus). A simple model based on signal detection theory demonstrates that these multiplicative gain changes were sufficient to account for attention-related improvements in perceptual sensitivity, without a need to invoke noise modulation. Moreover, combining the observed multiplicative gain with a postsensory readout mechanism resulted in a significantly poorer description of the observed behavioral data. We conclude that, at least in the context of relatively simple visual discrimination tasks, spatial attention modulates perceptual sensitivity primarily by modulating the gain of neural responses during early sensory processing PMID:25274817

The Variance Reaction Time Model

ERIC Educational Resources Information Center

Sikstrom, Sverker

2004-01-01

The variance reaction time model (VRTM) is proposed to account for various recognition data on reaction time, the mirror effect, receiver-operating-characteristic (ROC) curves, etc. The model is based on simple and plausible assumptions within a neural network: VRTM is a two layer neural network where one layer represents items and one layer…

Newly developed double neural network concept for reliable fast plasma position control

NASA Astrophysics Data System (ADS)

Jeon, Young-Mu; Na, Yong-Su; Kim, Myung-Rak; Hwang, Y. S.

2001-01-01

Neural network is considered as a parameter estimation tool in plasma controls for next generation tokamak such as ITER. The neural network has been reported to be so accurate and fast for plasma equilibrium identification that it may be applied to the control of complex tokamak plasmas. For this application, the reliability of the conventional neural network needs to be improved. In this study, a new idea of double neural network is developed to achieve this. The new idea has been applied to simple plasma position identification of KSTAR tokamak for feasibility test. Characteristics of the concept show higher reliability and fault tolerance even in severe faulty conditions, which may make neural network applicable to plasma control reliably and widely in future tokamaks.

(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.

Beyond Molecular Codes: Simple Rules to Wire Complex Brains

PubMed Central

Hassan, Bassem A.; Hiesinger, P. Robin

2015-01-01

Summary Molecular codes, like postal zip codes, are generally considered a robust way to ensure the specificity of neuronal target selection. However, a code capable of unambiguously generating complex neural circuits is difficult to conceive. Here, we re-examine the notion of molecular codes in the light of developmental algorithms. We explore how molecules and mechanisms that have been considered part of a code may alternatively implement simple pattern formation rules sufficient to ensure wiring specificity in neural circuits. This analysis delineates a pattern-based framework for circuit construction that may contribute to our understanding of brain wiring. PMID:26451480

A Regularized Neural Net Approach for Retrieval of Atmospheric and Surface Temperatures with the IASI Instrument

NASA Technical Reports Server (NTRS)

Aires, F.; Chedin, A.; Scott, N. A.; Rossow, W. B.; Hansen, James E. (Technical Monitor)

2001-01-01

Abstract In this paper, a fast atmospheric and surface temperature retrieval algorithm is developed for the high resolution Infrared Atmospheric Sounding Interferometer (IASI) space-borne instrument. This algorithm is constructed on the basis of a neural network technique that has been regularized by introduction of a priori information. The performance of the resulting fast and accurate inverse radiative transfer model is presented for a large divE:rsified dataset of radiosonde atmospheres including rare events. Two configurations are considered: a tropical-airmass specialized scheme and an all-air-masses scheme.

NetMHC-3.0: accurate web accessible predictions of human, mouse and monkey MHC class I affinities for peptides of length 8-11.

PubMed

Lundegaard, Claus; Lamberth, Kasper; Harndahl, Mikkel; Buus, Søren; Lund, Ole; Nielsen, Morten

2008-07-01

NetMHC-3.0 is trained on a large number of quantitative peptide data using both affinity data from the Immune Epitope Database and Analysis Resource (IEDB) and elution data from SYFPEITHI. The method generates high-accuracy predictions of major histocompatibility complex (MHC): peptide binding. The predictions are based on artificial neural networks trained on data from 55 MHC alleles (43 Human and 12 non-human), and position-specific scoring matrices (PSSMs) for additional 67 HLA alleles. As only the MHC class I prediction server is available, predictions are possible for peptides of length 8-11 for all 122 alleles. artificial neural network predictions are given as actual IC(50) values whereas PSSM predictions are given as a log-odds likelihood scores. The output is optionally available as download for easy post-processing. The training method underlying the server is the best available, and has been used to predict possible MHC-binding peptides in a series of pathogen viral proteomes including SARS, Influenza and HIV, resulting in an average of 75-80% confirmed MHC binders. Here, the performance is further validated and benchmarked using a large set of newly published affinity data, non-redundant to the training set. The server is free of use and available at: http://www.cbs.dtu.dk/services/NetMHC.

Deep Learning Applications for Predicting Pharmacological Properties of Drugs and Drug Repurposing Using Transcriptomic Data.

PubMed

Aliper, Alexander; Plis, Sergey; Artemov, Artem; Ulloa, Alvaro; Mamoshina, Polina; Zhavoronkov, Alex

2016-07-05

Deep learning is rapidly advancing many areas of science and technology with multiple success stories in image, text, voice and video recognition, robotics, and autonomous driving. In this paper we demonstrate how deep neural networks (DNN) trained on large transcriptional response data sets can classify various drugs to therapeutic categories solely based on their transcriptional profiles. We used the perturbation samples of 678 drugs across A549, MCF-7, and PC-3 cell lines from the LINCS Project and linked those to 12 therapeutic use categories derived from MeSH. To train the DNN, we utilized both gene level transcriptomic data and transcriptomic data processed using a pathway activation scoring algorithm, for a pooled data set of samples perturbed with different concentrations of the drug for 6 and 24 hours. In both pathway and gene level classification, DNN achieved high classification accuracy and convincingly outperformed the support vector machine (SVM) model on every multiclass classification problem, however, models based on pathway level data performed significantly better. For the first time we demonstrate a deep learning neural net trained on transcriptomic data to recognize pharmacological properties of multiple drugs across different biological systems and conditions. We also propose using deep neural net confusion matrices for drug repositioning. This work is a proof of principle for applying deep learning to drug discovery and development.

Deep learning applications for predicting pharmacological properties of drugs and drug repurposing using transcriptomic data

PubMed Central

Aliper, Alexander; Plis, Sergey; Artemov, Artem; Ulloa, Alvaro; Mamoshina, Polina; Zhavoronkov, Alex

2016-01-01

Deep learning is rapidly advancing many areas of science and technology with multiple success stories in image, text, voice and video recognition, robotics and autonomous driving. In this paper we demonstrate how deep neural networks (DNN) trained on large transcriptional response data sets can classify various drugs to therapeutic categories solely based on their transcriptional profiles. We used the perturbation samples of 678 drugs across A549, MCF‐7 and PC‐3 cell lines from the LINCS project and linked those to 12 therapeutic use categories derived from MeSH. To train the DNN, we utilized both gene level transcriptomic data and transcriptomic data processed using a pathway activation scoring algorithm, for a pooled dataset of samples perturbed with different concentrations of the drug for 6 and 24 hours. In both gene and pathway level classification, DNN convincingly outperformed support vector machine (SVM) model on every multiclass classification problem, however, models based on a pathway level classification perform better. For the first time we demonstrate a deep learning neural net trained on transcriptomic data to recognize pharmacological properties of multiple drugs across different biological systems and conditions. We also propose using deep neural net confusion matrices for drug repositioning. This work is a proof of principle for applying deep learning to drug discovery and development. PMID:27200455

Analysis and recognition of 5′ UTR intron splice sites in human pre-mRNA

PubMed Central

Eden, E.; Brunak, S.

2004-01-01

Prediction of splice sites in non-coding regions of genes is one of the most challenging aspects of gene structure recognition. We perform a rigorous analysis of such splice sites embedded in human 5′ untranslated regions (UTRs), and investigate correlations between this class of splice sites and other features found in the adjacent exons and introns. By restricting the training of neural network algorithms to ‘pure’ UTRs (not extending partially into protein coding regions), we for the first time investigate the predictive power of the splicing signal proper, in contrast to conventional splice site prediction, which typically relies on the change in sequence at the transition from protein coding to non-coding. By doing so, the algorithms were able to pick up subtler splicing signals that were otherwise masked by ‘coding’ noise, thus enhancing significantly the prediction of 5′ UTR splice sites. For example, the non-coding splice site predicting networks pick up compositional and positional bias in the 3′ ends of non-coding exons and 5′ non-coding intron ends, where cytosine and guanine are over-represented. This compositional bias at the true UTR donor sites is also visible in the synaptic weights of the neural networks trained to identify UTR donor sites. Conventional splice site prediction methods perform poorly in UTRs because the reading frame pattern is absent. The NetUTR method presented here performs 2–3-fold better compared with NetGene2 and GenScan in 5′ UTRs. We also tested the 5′ UTR trained method on protein coding regions, and discovered, surprisingly, that it works quite well (although it cannot compete with NetGene2). This indicates that the local splicing pattern in UTRs and coding regions is largely the same. The NetUTR method is made publicly available at www.cbs.dtu.dk/services/NetUTR. PMID:14960723

Coral reef metabolism and carbon chemistry dynamics of a coral reef flat

NASA Astrophysics Data System (ADS)

Albright, Rebecca; Benthuysen, Jessica; Cantin, Neal; Caldeira, Ken; Anthony, Ken

2015-05-01

Global carbon emissions continue to acidify the oceans, motivating growing concern for the ability of coral reefs to maintain net positive calcification rates. Efforts to develop robust relationships between coral reef calcification and carbonate parameters such as aragonite saturation state (Ωarag) aim to facilitate meaningful predictions of how reef calcification will change in the face of ocean acidification. Here we investigate natural trends in carbonate chemistry of a coral reef flat over diel cycles and relate these trends to benthic carbon fluxes by quantifying net community calcification and net community production. We find that, despite an apparent dependence of calcification on Ωarag seen in a simple pairwise relationship, if the dependence of net calcification on net photosynthesis is accounted for, knowing Ωarag does not add substantial explanatory value. This suggests that, over short time scales, the control of Ωarag on net calcification is weak relative to factors governing net photosynthesis.

Evaluating predictive modeling’s potential to improve teleretinal screening participation in urban safety net clinics

PubMed Central

Ogunyemi, Omolola; Teklehaimanot, Senait; Patty, Lauren; Moran, Erin; George, Sheba

2013-01-01

Introduction Screening guidelines for diabetic patients recommend yearly eye examinations to detect diabetic retinopathy and other forms of diabetic eye disease. However, annual screening rates for retinopathy in US urban safety net settings remain low. Methods Using data gathered from a study of teleretinal screening in six urban safety net clinics, we assessed whether predictive modeling could be of value in identifying patients at risk of developing retinopathy. We developed and examined the accuracy of two predictive modeling approaches for diabetic retinopathy in a sample of 513 diabetic individuals, using routinely available clinical variables from retrospective medical record reviews. Bayesian networks and radial basis function (neural) networks were learned using ten-fold cross-validation. Results The predictive models were modestly predictive with the best model having an AUC of 0.71. Discussion Using routinely available clinical variables to predict patients at risk of developing retinopathy and to target them for annual eye screenings may be of some usefulness to safety net clinics. PMID:23920536

Evaluating predictive modeling's potential to improve teleretinal screening participation in urban safety net clinics.

PubMed

Ogunyemi, Omolola; Teklehaimanot, Senait; Patty, Lauren; Moran, Erin; George, Sheba

2013-01-01

Screening guidelines for diabetic patients recommend yearly eye examinations to detect diabetic retinopathy and other forms of diabetic eye disease. However, annual screening rates for retinopathy in US urban safety net settings remain low. Using data gathered from a study of teleretinal screening in six urban safety net clinics, we assessed whether predictive modeling could be of value in identifying patients at risk of developing retinopathy. We developed and examined the accuracy of two predictive modeling approaches for diabetic retinopathy in a sample of 513 diabetic individuals, using routinely available clinical variables from retrospective medical record reviews. Bayesian networks and radial basis function (neural) networks were learned using ten-fold cross-validation. The predictive models were modestly predictive with the best model having an AUC of 0.71. Using routinely available clinical variables to predict patients at risk of developing retinopathy and to target them for annual eye screenings may be of some usefulness to safety net clinics.

Tools for Atmospheric Radiative Transfer: Streamer and FluxNet. Revised

NASA Technical Reports Server (NTRS)

Key, Jeffrey R.; Schweiger, Axel J.

1998-01-01

Two tools for the solution of radiative transfer problems are presented. Streamer is a highly flexible medium spectral resolution radiative transfer model based on the plane-parallel theory of radiative transfer. Capable of computing either fluxes or radiances, it is suitable for studying radiative processes at the surface or within the atmosphere and for the development of remote-sensing algorithms. FluxNet is a fast neural network-based implementation of Streamer for computing surface fluxes. It allows for a sophisticated treatment of radiative processes in the analysis of large data sets and potential integration into geophysical models where computational efficiency is an issue. Documentation and tools for the development of alternative versions of Fluxnet are available. Collectively, Streamer and FluxNet solve a wide variety of problems related to radiative transfer: Streamer provides the detail and sophistication needed to perform basic research on most aspects of complex radiative processes while the efficiency and simplicity of FluxNet make it ideal for operational use.

Neural network for solving convex quadratic bilevel programming problems.

PubMed

He, Xing; Li, Chuandong; Huang, Tingwen; Li, Chaojie

2014-03-01

In this paper, using the idea of successive approximation, we propose a neural network to solve convex quadratic bilevel programming problems (CQBPPs), which is modeled by a nonautonomous differential inclusion. Different from the existing neural network for CQBPP, the model has the least number of state variables and simple structure. Based on the theory of nonsmooth analysis, differential inclusions and Lyapunov-like method, the limit equilibrium points sequence of the proposed neural networks can approximately converge to an optimal solution of CQBPP under certain conditions. Finally, simulation results on two numerical examples and the portfolio selection problem show the effectiveness and performance of the proposed neural network. Copyright © 2013 Elsevier Ltd. All rights reserved.

Comparison between Frame-Constrained Fix-Pixel-Value and Frame-Free Spiking-Dynamic-Pixel ConvNets for Visual Processing

PubMed Central

Farabet, Clément; Paz, Rafael; Pérez-Carrasco, Jose; Zamarreño-Ramos, Carlos; Linares-Barranco, Alejandro; LeCun, Yann; Culurciello, Eugenio; Serrano-Gotarredona, Teresa; Linares-Barranco, Bernabe

2012-01-01

Most scene segmentation and categorization architectures for the extraction of features in images and patches make exhaustive use of 2D convolution operations for template matching, template search, and denoising. Convolutional Neural Networks (ConvNets) are one example of such architectures that can implement general-purpose bio-inspired vision systems. In standard digital computers 2D convolutions are usually expensive in terms of resource consumption and impose severe limitations for efficient real-time applications. Nevertheless, neuro-cortex inspired solutions, like dedicated Frame-Based or Frame-Free Spiking ConvNet Convolution Processors, are advancing real-time visual processing. These two approaches share the neural inspiration, but each of them solves the problem in different ways. Frame-Based ConvNets process frame by frame video information in a very robust and fast way that requires to use and share the available hardware resources (such as: multipliers, adders). Hardware resources are fixed- and time-multiplexed by fetching data in and out. Thus memory bandwidth and size is important for good performance. On the other hand, spike-based convolution processors are a frame-free alternative that is able to perform convolution of a spike-based source of visual information with very low latency, which makes ideal for very high-speed applications. However, hardware resources need to be available all the time and cannot be time-multiplexed. Thus, hardware should be modular, reconfigurable, and expansible. Hardware implementations in both VLSI custom integrated circuits (digital and analog) and FPGA have been already used to demonstrate the performance of these systems. In this paper we present a comparison study of these two neuro-inspired solutions. A brief description of both systems is presented and also discussions about their differences, pros and cons. PMID:22518097

Agile convolutional neural network for pulmonary nodule classification using CT images.

PubMed

Zhao, Xinzhuo; Liu, Liyao; Qi, Shouliang; Teng, Yueyang; Li, Jianhua; Qian, Wei

2018-04-01

To distinguish benign from malignant pulmonary nodules using CT images is critical for their precise diagnosis and treatment. A new Agile convolutional neural network (CNN) framework is proposed to conquer the challenges of a small-scale medical image database and the small size of the nodules, and it improves the performance of pulmonary nodule classification using CT images. A hybrid CNN of LeNet and AlexNet is constructed through combining the layer settings of LeNet and the parameter settings of AlexNet. A dataset with 743 CT image nodule samples is built up based on the 1018 CT scans of LIDC to train and evaluate the Agile CNN model. Through adjusting the parameters of the kernel size, learning rate, and other factors, the effect of these parameters on the performance of the CNN model is investigated, and an optimized setting of the CNN is obtained finally. After finely optimizing the settings of the CNN, the estimation accuracy and the area under the curve can reach 0.822 and 0.877, respectively. The accuracy of the CNN is significantly dependent on the kernel size, learning rate, training batch size, dropout, and weight initializations. The best performance is achieved when the kernel size is set to [Formula: see text], the learning rate is 0.005, the batch size is 32, and dropout and Gaussian initialization are used. This competitive performance demonstrates that our proposed CNN framework and the optimization strategy of the CNN parameters are suitable for pulmonary nodule classification characterized by small medical datasets and small targets. The classification model might help diagnose and treat pulmonary nodules effectively.

Comparison between Frame-Constrained Fix-Pixel-Value and Frame-Free Spiking-Dynamic-Pixel ConvNets for Visual Processing.

PubMed

Farabet, Clément; Paz, Rafael; Pérez-Carrasco, Jose; Zamarreño-Ramos, Carlos; Linares-Barranco, Alejandro; Lecun, Yann; Culurciello, Eugenio; Serrano-Gotarredona, Teresa; Linares-Barranco, Bernabe

2012-01-01

Most scene segmentation and categorization architectures for the extraction of features in images and patches make exhaustive use of 2D convolution operations for template matching, template search, and denoising. Convolutional Neural Networks (ConvNets) are one example of such architectures that can implement general-purpose bio-inspired vision systems. In standard digital computers 2D convolutions are usually expensive in terms of resource consumption and impose severe limitations for efficient real-time applications. Nevertheless, neuro-cortex inspired solutions, like dedicated Frame-Based or Frame-Free Spiking ConvNet Convolution Processors, are advancing real-time visual processing. These two approaches share the neural inspiration, but each of them solves the problem in different ways. Frame-Based ConvNets process frame by frame video information in a very robust and fast way that requires to use and share the available hardware resources (such as: multipliers, adders). Hardware resources are fixed- and time-multiplexed by fetching data in and out. Thus memory bandwidth and size is important for good performance. On the other hand, spike-based convolution processors are a frame-free alternative that is able to perform convolution of a spike-based source of visual information with very low latency, which makes ideal for very high-speed applications. However, hardware resources need to be available all the time and cannot be time-multiplexed. Thus, hardware should be modular, reconfigurable, and expansible. Hardware implementations in both VLSI custom integrated circuits (digital and analog) and FPGA have been already used to demonstrate the performance of these systems. In this paper we present a comparison study of these two neuro-inspired solutions. A brief description of both systems is presented and also discussions about their differences, pros and cons.

A Configurable Event-Driven Convolutional Node with Rate Saturation Mechanism for Modular ConvNet Systems Implementation.

PubMed

Camuñas-Mesa, Luis A; Domínguez-Cordero, Yaisel L; Linares-Barranco, Alejandro; Serrano-Gotarredona, Teresa; Linares-Barranco, Bernabé

2018-01-01

Convolutional Neural Networks (ConvNets) are a particular type of neural network often used for many applications like image recognition, video analysis or natural language processing. They are inspired by the human brain, following a specific organization of the connectivity pattern between layers of neurons known as receptive field. These networks have been traditionally implemented in software, but they are becoming more computationally expensive as they scale up, having limitations for real-time processing of high-speed stimuli. On the other hand, hardware implementations show difficulties to be used for different applications, due to their reduced flexibility. In this paper, we propose a fully configurable event-driven convolutional node with rate saturation mechanism that can be used to implement arbitrary ConvNets on FPGAs. This node includes a convolutional processing unit and a routing element which allows to build large 2D arrays where any multilayer structure can be implemented. The rate saturation mechanism emulates the refractory behavior in biological neurons, guaranteeing a minimum separation in time between consecutive events. A 4-layer ConvNet with 22 convolutional nodes trained for poker card symbol recognition has been implemented in a Spartan6 FPGA. This network has been tested with a stimulus where 40 poker cards were observed by a Dynamic Vision Sensor (DVS) in 1 s time. Different slow-down factors were applied to characterize the behavior of the system for high speed processing. For slow stimulus play-back, a 96% recognition rate is obtained with a power consumption of 0.85 mW. At maximum play-back speed, a traffic control mechanism downsamples the input stimulus, obtaining a recognition rate above 63% when less than 20% of the input events are processed, demonstrating the robustness of the network.

A Configurable Event-Driven Convolutional Node with Rate Saturation Mechanism for Modular ConvNet Systems Implementation

PubMed Central

Camuñas-Mesa, Luis A.; Domínguez-Cordero, Yaisel L.; Linares-Barranco, Alejandro; Serrano-Gotarredona, Teresa; Linares-Barranco, Bernabé

2018-01-01

Convolutional Neural Networks (ConvNets) are a particular type of neural network often used for many applications like image recognition, video analysis or natural language processing. They are inspired by the human brain, following a specific organization of the connectivity pattern between layers of neurons known as receptive field. These networks have been traditionally implemented in software, but they are becoming more computationally expensive as they scale up, having limitations for real-time processing of high-speed stimuli. On the other hand, hardware implementations show difficulties to be used for different applications, due to their reduced flexibility. In this paper, we propose a fully configurable event-driven convolutional node with rate saturation mechanism that can be used to implement arbitrary ConvNets on FPGAs. This node includes a convolutional processing unit and a routing element which allows to build large 2D arrays where any multilayer structure can be implemented. The rate saturation mechanism emulates the refractory behavior in biological neurons, guaranteeing a minimum separation in time between consecutive events. A 4-layer ConvNet with 22 convolutional nodes trained for poker card symbol recognition has been implemented in a Spartan6 FPGA. This network has been tested with a stimulus where 40 poker cards were observed by a Dynamic Vision Sensor (DVS) in 1 s time. Different slow-down factors were applied to characterize the behavior of the system for high speed processing. For slow stimulus play-back, a 96% recognition rate is obtained with a power consumption of 0.85 mW. At maximum play-back speed, a traffic control mechanism downsamples the input stimulus, obtaining a recognition rate above 63% when less than 20% of the input events are processed, demonstrating the robustness of the network. PMID:29515349

Binary patterns encoded convolutional neural networks for texture recognition and remote sensing scene classification

NASA Astrophysics Data System (ADS)

Anwer, Rao Muhammad; Khan, Fahad Shahbaz; van de Weijer, Joost; Molinier, Matthieu; Laaksonen, Jorma

2018-04-01

Designing discriminative powerful texture features robust to realistic imaging conditions is a challenging computer vision problem with many applications, including material recognition and analysis of satellite or aerial imagery. In the past, most texture description approaches were based on dense orderless statistical distribution of local features. However, most recent approaches to texture recognition and remote sensing scene classification are based on Convolutional Neural Networks (CNNs). The de facto practice when learning these CNN models is to use RGB patches as input with training performed on large amounts of labeled data (ImageNet). In this paper, we show that Local Binary Patterns (LBP) encoded CNN models, codenamed TEX-Nets, trained using mapped coded images with explicit LBP based texture information provide complementary information to the standard RGB deep models. Additionally, two deep architectures, namely early and late fusion, are investigated to combine the texture and color information. To the best of our knowledge, we are the first to investigate Binary Patterns encoded CNNs and different deep network fusion architectures for texture recognition and remote sensing scene classification. We perform comprehensive experiments on four texture recognition datasets and four remote sensing scene classification benchmarks: UC-Merced with 21 scene categories, WHU-RS19 with 19 scene classes, RSSCN7 with 7 categories and the recently introduced large scale aerial image dataset (AID) with 30 aerial scene types. We demonstrate that TEX-Nets provide complementary information to standard RGB deep model of the same network architecture. Our late fusion TEX-Net architecture always improves the overall performance compared to the standard RGB network on both recognition problems. Furthermore, our final combination leads to consistent improvement over the state-of-the-art for remote sensing scene classification.

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.

Neurophysiology and Neuroanatomy of Reflexive and Volitional Saccades: Evidence from Studies of Humans

ERIC Educational Resources Information Center

McDowell, Jennifer E.; Dyckman, Kara A.; Austin, Benjamin P.; Clementz, Brett A.

2008-01-01

This review provides a summary of the contributions made by human functional neuroimaging studies to the understanding of neural correlates of saccadic control. The generation of simple visually guided saccades (redirections of gaze to a visual stimulus or pro-saccades) and more complex volitional saccades require similar basic neural circuitry…

Linking NASA Data with Environmental Exposures and Health Outcomes in Theater of War

DTIC Science & Technology

2012-10-01

variations of tropospheric aerosols." Journal of the Atmospheric Sciences 60(1): 119-136. Brown, M., D. Lary, et al. (2006). "Using neural nets to...A. Tanskanen, et al. (2007). "Aerosols and surface UV products from ozone monitoring instrument observations: An overview." Journal of Geophysical

Log Defect Recognition Using CT-images and Neural Net Classifiers

Treesearch

Daniel L. Schmoldt; Pei Li; A. Lynn Abbott

1995-01-01

Although several approaches have been introduced to automatically identify internal log defects using computed tomography (CT) imagery, most of these have been feasibility efforts and consequently have had several limitations: (1) reports of classification accuracy are largely subjective, not statistical, (2) there has been no attempt to achieve real-time operation,...

Deep neural networks show an equivalent and often superior performance to dermatologists in onychomycosis diagnosis: Automatic construction of onychomycosis datasets by region-based convolutional deep neural network.

PubMed

Han, Seung Seog; Park, Gyeong Hun; Lim, Woohyung; Kim, Myoung Shin; Na, Jung Im; Park, Ilwoo; Chang, Sung Eun

2018-01-01

Although there have been reports of the successful diagnosis of skin disorders using deep learning, unrealistically large clinical image datasets are required for artificial intelligence (AI) training. We created datasets of standardized nail images using a region-based convolutional neural network (R-CNN) trained to distinguish the nail from the background. We used R-CNN to generate training datasets of 49,567 images, which we then used to fine-tune the ResNet-152 and VGG-19 models. The validation datasets comprised 100 and 194 images from Inje University (B1 and B2 datasets, respectively), 125 images from Hallym University (C dataset), and 939 images from Seoul National University (D dataset). The AI (ensemble model; ResNet-152 + VGG-19 + feedforward neural networks) results showed test sensitivity/specificity/ area under the curve values of (96.0 / 94.7 / 0.98), (82.7 / 96.7 / 0.95), (92.3 / 79.3 / 0.93), (87.7 / 69.3 / 0.82) for the B1, B2, C, and D datasets. With a combination of the B1 and C datasets, the AI Youden index was significantly (p = 0.01) higher than that of 42 dermatologists doing the same assessment manually. For B1+C and B2+ D dataset combinations, almost none of the dermatologists performed as well as the AI. By training with a dataset comprising 49,567 images, we achieved a diagnostic accuracy for onychomycosis using deep learning that was superior to that of most of the dermatologists who participated in this study.

Tooth labeling in cone-beam CT using deep convolutional neural network for forensic identification

NASA Astrophysics Data System (ADS)

Miki, Yuma; Muramatsu, Chisako; Hayashi, Tatsuro; Zhou, Xiangrong; Hara, Takeshi; Katsumata, Akitoshi; Fujita, Hiroshi

2017-03-01

In large disasters, dental record plays an important role in forensic identification. However, filing dental charts for corpses is not an easy task for general dentists. Moreover, it is laborious and time-consuming work in cases of large scale disasters. We have been investigating a tooth labeling method on dental cone-beam CT images for the purpose of automatic filing of dental charts. In our method, individual tooth in CT images are detected and classified into seven tooth types using deep convolutional neural network. We employed the fully convolutional network using AlexNet architecture for detecting each tooth and applied our previous method using regular AlexNet for classifying the detected teeth into 7 tooth types. From 52 CT volumes obtained by two imaging systems, five images each were randomly selected as test data, and the remaining 42 cases were used as training data. The result showed the tooth detection accuracy of 77.4% with the average false detection of 5.8 per image. The result indicates the potential utility of the proposed method for automatic recording of dental information.

Automated and real-time segmentation of suspicious breast masses using convolutional neural network

PubMed Central

Gregory, Adriana; Denis, Max; Meixner, Duane D.; Bayat, Mahdi; Whaley, Dana H.; Fatemi, Mostafa; Alizad, Azra

2018-01-01

In this work, a computer-aided tool for detection was developed to segment breast masses from clinical ultrasound (US) scans. The underlying Multi U-net algorithm is based on convolutional neural networks. Under the Mayo Clinic Institutional Review Board protocol, a prospective study of the automatic segmentation of suspicious breast masses was performed. The cohort consisted of 258 female patients who were clinically identified with suspicious breast masses and underwent clinical US scan and breast biopsy. The computer-aided detection tool effectively segmented the breast masses, achieving a mean Dice coefficient of 0.82, a true positive fraction (TPF) of 0.84, and a false positive fraction (FPF) of 0.01. By avoiding positioning of an initial seed, the algorithm is able to segment images in real time (13–55 ms per image), and can have potential clinical applications. The algorithm is at par with a conventional seeded algorithm, which had a mean Dice coefficient of 0.84 and performs significantly better (P< 0.0001) than the original U-net algorithm. PMID:29768415

The Development of Animal Behavior: From Lorenz to Neural Nets

NASA Astrophysics Data System (ADS)

Bolhuis, Johan J.

In the study of behavioral development both causal and functional approaches have been used, and they often overlap. The concept of ontogenetic adaptations suggests that each developmental phase involves unique adaptations to the environment of the developing animal. The functional concept of optimal outbreeding has led to further experimental evidence and theoretical models concerning the role of sexual imprinting in the evolutionary process of sexual selection. From a causal perspective it has been proposed that behavioral ontogeny involves the development of various kinds of perceptual, motor, and central mechanisms and the formation of connections among them. This framework has been tested for a number of complex behavior systems such as hunger and dustbathing. Imprinting is often seen as a model system for behavioral development in general. Recent advances in imprinting research have been the result of an interdisciplinary effort involving ethology, neuroscience, and experimental psychology, with a continual interplay between these approaches. The imprinting results are consistent with Lorenz' early intuitive suggestions and are also reflected in the architecture of recent neural net models.

Yarn-dyed fabric defect classification based on convolutional neural network

NASA Astrophysics Data System (ADS)

Jing, Junfeng; Dong, Amei; Li, Pengfei; Zhang, Kaibing

2017-09-01

Considering that manual inspection of the yarn-dyed fabric can be time consuming and inefficient, we propose a yarn-dyed fabric defect classification method by using a convolutional neural network (CNN) based on a modified AlexNet. CNN shows powerful ability in performing feature extraction and fusion by simulating the learning mechanism of human brain. The local response normalization layers in AlexNet are replaced by the batch normalization layers, which can enhance both the computational efficiency and classification accuracy. In the training process of the network, the characteristics of the defect are extracted step by step and the essential features of the image can be obtained from the fusion of the edge details with several convolution operations. Then the max-pooling layers, the dropout layers, and the fully connected layers are employed in the classification model to reduce the computation cost and extract more precise features of the defective fabric. Finally, the results of the defect classification are predicted by the softmax function. The experimental results show promising performance with an acceptable average classification rate and strong robustness on yarn-dyed fabric defect classification.

Yarn-dyed fabric defect classification based on convolutional neural network

NASA Astrophysics Data System (ADS)

Jing, Junfeng; Dong, Amei; Li, Pengfei

2017-07-01

Considering that the manual inspection of the yarn-dyed fabric can be time consuming and less efficient, a convolutional neural network (CNN) solution based on the modified AlexNet structure for the classification of the yarn-dyed fabric defect is proposed. CNN has powerful ability of feature extraction and feature fusion which can simulate the learning mechanism of the human brain. In order to enhance computational efficiency and detection accuracy, the local response normalization (LRN) layers in AlexNet are replaced by the batch normalization (BN) layers. In the process of the network training, through several convolution operations, the characteristics of the image are extracted step by step, and the essential features of the image can be obtained from the edge features. And the max pooling layers, the dropout layers, the fully connected layers are also employed in the classification model to reduce the computation cost and acquire more precise features of fabric defect. Finally, the results of the defect classification are predicted by the softmax function. The experimental results show the capability of defect classification via the modified Alexnet model and indicate its robustness.

EnzyNet: enzyme classification using 3D convolutional neural networks on spatial representation

PubMed Central

Amidi, Afshine; Megalooikonomou, Vasileios; Paragios, Nikos

2018-01-01

During the past decade, with the significant progress of computational power as well as ever-rising data availability, deep learning techniques became increasingly popular due to their excellent performance on computer vision problems. The size of the Protein Data Bank (PDB) has increased more than 15-fold since 1999, which enabled the expansion of models that aim at predicting enzymatic function via their amino acid composition. Amino acid sequence, however, is less conserved in nature than protein structure and therefore considered a less reliable predictor of protein function. This paper presents EnzyNet, a novel 3D convolutional neural networks classifier that predicts the Enzyme Commission number of enzymes based only on their voxel-based spatial structure. The spatial distribution of biochemical properties was also examined as complementary information. The two-layer architecture was investigated on a large dataset of 63,558 enzymes from the PDB and achieved an accuracy of 78.4% by exploiting only the binary representation of the protein shape. Code and datasets are available at https://github.com/shervinea/enzynet. PMID:29740518

EnzyNet: enzyme classification using 3D convolutional neural networks on spatial representation.

PubMed

Amidi, Afshine; Amidi, Shervine; Vlachakis, Dimitrios; Megalooikonomou, Vasileios; Paragios, Nikos; Zacharaki, Evangelia I

2018-01-01

During the past decade, with the significant progress of computational power as well as ever-rising data availability, deep learning techniques became increasingly popular due to their excellent performance on computer vision problems. The size of the Protein Data Bank (PDB) has increased more than 15-fold since 1999, which enabled the expansion of models that aim at predicting enzymatic function via their amino acid composition. Amino acid sequence, however, is less conserved in nature than protein structure and therefore considered a less reliable predictor of protein function. This paper presents EnzyNet, a novel 3D convolutional neural networks classifier that predicts the Enzyme Commission number of enzymes based only on their voxel-based spatial structure. The spatial distribution of biochemical properties was also examined as complementary information. The two-layer architecture was investigated on a large dataset of 63,558 enzymes from the PDB and achieved an accuracy of 78.4% by exploiting only the binary representation of the protein shape. Code and datasets are available at https://github.com/shervinea/enzynet.

Accelerator diagnosis and control by Neural Nets

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

Spencer, J.E.

1989-01-01

Neural Nets (NN) have been described as a solution looking for a problem. In the last conference, Artificial Intelligence (AI) was considered in the accelerator context. While good for local surveillance and control, its use for large complex systems (LCS) was much more restricted. By contrast, NN provide a good metaphor for LCS. It can be argued that they are logically equivalent to multi-loop feedback/forward control of faulty systems, and therefore provide an ideal adaptive control system. Thus, where AI may be good for maintaining a 'golden orbit,' NN should be good for obtaining it via a quantitative approach tomore » 'look and adjust' methods like operator tweaking which use pattern recognition to deal with hardware and software limitations, inaccuracies or errors as well as imprecise knowledge or understanding of effects like annealing and hysteresis. Further, insights from NN allow one to define feasibility conditions for LCS in terms of design constraints and tolerances. Hardware and software implications are discussed and several LCS of current interest are compared and contrasted. 15 refs., 5 figs.« less

Neural correlate of Internet use in patients undergoing psychological treatment for Internet addiction.

PubMed

Lai, Carlo; Altavilla, Daniela; Mazza, Marianna; Scappaticci, Silvia; Tambelli, Renata; Aceto, Paola; Luciani, Massimiliano; Corvino, Stefano; Martinelli, David; Alimonti, Flaminia; Tonioni, Federico

2017-06-01

The new version of Diagnostic and Statistical Manual of Mental Disorders (DSM-5th) proposed the Internet Gaming Disorder for the diagnosis of Internet addiction (IA) considering the neurobiological evidence of the craving. The aim was to test the neural correlate in response to the Internet cue in patients with IA. Sixteen males with IA diagnosis (clinical group) and 14 healthy male (control group) were recruited for an experimental visual task composed of Internet images and emotional images. During the visual presentation of Internet cue, electroencefalographic data were recorded using Net Station 4.5.1 with a 256-channels HydroCel Geodesic Sensor Net. Event-related potential (ERP) components and low-resolution electromagnetic tomography (sLoreta) were analysed. sLoreta analyses showed that patients from the clinical group presented a higher primary somatosensorial cortex and lower paralimbic, temporal and orbito-frontal activation in response to both Internet and emotional images compared to those of the control group. These results suggest that clinically recognized pathological use of Internet could be linked to dissociative symptoms.

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.

Fitting neuron models to spike trains.

PubMed

Rossant, Cyrille; Goodman, Dan F M; Fontaine, Bertrand; Platkiewicz, Jonathan; Magnusson, Anna K; Brette, Romain

2011-01-01

Computational modeling is increasingly used to understand the function of neural circuits in systems neuroscience. These studies require models of individual neurons with realistic input-output properties. Recently, it was found that spiking models can accurately predict the precisely timed spike trains produced by cortical neurons in response to somatically injected currents, if properly fitted. This requires fitting techniques that are efficient and flexible enough to easily test different candidate models. We present a generic solution, based on the Brian simulator (a neural network simulator in Python), which allows the user to define and fit arbitrary neuron models to electrophysiological recordings. It relies on vectorization and parallel computing techniques to achieve efficiency. We demonstrate its use on neural recordings in the barrel cortex and in the auditory brainstem, and confirm that simple adaptive spiking models can accurately predict the response of cortical neurons. Finally, we show how a complex multicompartmental model can be reduced to a simple effective spiking model.

A neural circuit mechanism for regulating vocal variability during song learning in zebra finches.

PubMed

Garst-Orozco, Jonathan; Babadi, Baktash; Ölveczky, Bence P

2014-12-15

Motor skill learning is characterized by improved performance and reduced motor variability. The neural mechanisms that couple skill level and variability, however, are not known. The zebra finch, a songbird, presents a unique opportunity to address this question because production of learned song and induction of vocal variability are instantiated in distinct circuits that converge on a motor cortex analogue controlling vocal output. To probe the interplay between learning and variability, we made intracellular recordings from neurons in this area, characterizing how their inputs from the functionally distinct pathways change throughout song development. We found that inputs that drive stereotyped song-patterns are strengthened and pruned, while inputs that induce variability remain unchanged. A simple network model showed that strengthening and pruning of action-specific connections reduces the sensitivity of motor control circuits to variable input and neural 'noise'. This identifies a simple and general mechanism for learning-related regulation of motor variability.

Comparisons of neural networks to standard techniques for image classification and correlation

NASA Technical Reports Server (NTRS)

Paola, Justin D.; Schowengerdt, Robert A.

1994-01-01

Neural network techniques for multispectral image classification and spatial pattern detection are compared to the standard techniques of maximum-likelihood classification and spatial correlation. The neural network produced a more accurate classification than maximum-likelihood of a Landsat scene of Tucson, Arizona. Some of the errors in the maximum-likelihood classification are illustrated using decision region and class probability density plots. As expected, the main drawback to the neural network method is the long time required for the training stage. The network was trained using several different hidden layer sizes to optimize both the classification accuracy and training speed, and it was found that one node per class was optimal. The performance improved when 3x3 local windows of image data were entered into the net. This modification introduces texture into the classification without explicit calculation of a texture measure. Larger windows were successfully used for the detection of spatial features in Landsat and Magellan synthetic aperture radar imagery.

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.

Pulse-coupled neural nets: translation, rotation, scale, distortion, and intensity signal invariance for images.

PubMed

Johnson, J L

1994-09-10

The linking-field neural network model of Eckhorn et al. [Neural Comput. 2, 293-307 (1990)] was introduced to explain the experimentally observed synchronous activity among neural assemblies in the cat cortex induced by feature-dependent visual activity. The model produces synchronous bursts of pulses from neurons with similar activity, effectively grouping them by phase and pulse frequency. It gives a basic new function: grouping by similarity. The synchronous bursts are obtained in the limit of strong linking strengths. The linking-field model in the limit of moderate-to-weak linking characterized by few if any multiple bursts is investigated. In this limit dynamic, locally periodic traveling waves exist whose time signal encodes the geometrical structure of a two-dimensional input image. The signal can be made insensitive to translation, scale, rotation, distortion, and intensity. The waves transmit information beyond the physical interconnect distance. The model is implemented in an optical hybrid demonstration system. Results of the simulations and the optical system are presented.

Efficient Embedded Decoding of Neural Network Language Models in a Machine Translation System.

PubMed

Zamora-Martinez, Francisco; Castro-Bleda, Maria Jose

2018-02-22

Neural Network Language Models (NNLMs) are a successful approach to Natural Language Processing tasks, such as Machine Translation. We introduce in this work a Statistical Machine Translation (SMT) system which fully integrates NNLMs in the decoding stage, breaking the traditional approach based on [Formula: see text]-best list rescoring. The neural net models (both language models (LMs) and translation models) are fully coupled in the decoding stage, allowing to more strongly influence the translation quality. Computational issues were solved by using a novel idea based on memorization and smoothing of the softmax constants to avoid their computation, which introduces a trade-off between LM quality and computational cost. These ideas were studied in a machine translation task with different combinations of neural networks used both as translation models and as target LMs, comparing phrase-based and [Formula: see text]-gram-based systems, showing that the integrated approach seems more promising for [Formula: see text]-gram-based systems, even with nonfull-quality NNLMs.

Adaptive Neural Networks for Automatic Negotiation

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

Sakas, D. P.; Vlachos, D. S.; Simos, T. E.

The use of fuzzy logic and fuzzy neural networks has been found effective for the modelling of the uncertain relations between the parameters of a negotiation procedure. The problem with these configurations is that they are static, that is, any new knowledge from theory or experiment lead to the construction of entirely new models. To overcome this difficulty, we apply in this work, an adaptive neural topology to model the negotiation process. Finally a simple simulation is carried in order to test the new method.

Institutional Effects in a Simple Model of Educational Production

ERIC Educational Resources Information Center

Bishop, John H.; Wobmann, Ludger

2004-01-01

This paper presents a model of educational production that tries to make sense of recent evidence on effects of institutional arrangements on student performance. In a simple principal-agent framework, students choose their learning effort to maximize their net benefits, while the government chooses educational spending to maximize its net…

A model of interval timing by neural integration.

PubMed

Simen, Patrick; Balci, Fuat; de Souza, Laura; Cohen, Jonathan D; Holmes, Philip

2011-06-22

We show that simple assumptions about neural processing lead to a model of interval timing as a temporal integration process, in which a noisy firing-rate representation of time rises linearly on average toward a response threshold over the course of an interval. Our assumptions include: that neural spike trains are approximately independent Poisson processes, that correlations among them can be largely cancelled by balancing excitation and inhibition, that neural populations can act as integrators, and that the objective of timed behavior is maximal accuracy and minimal variance. The model accounts for a variety of physiological and behavioral findings in rodents, monkeys, and humans, including ramping firing rates between the onset of reward-predicting cues and the receipt of delayed rewards, and universally scale-invariant response time distributions in interval timing tasks. It furthermore makes specific, well-supported predictions about the skewness of these distributions, a feature of timing data that is usually ignored. The model also incorporates a rapid (potentially one-shot) duration-learning procedure. Human behavioral data support the learning rule's predictions regarding learning speed in sequences of timed responses. These results suggest that simple, integration-based models should play as prominent a role in interval timing theory as they do in theories of perceptual decision making, and that a common neural mechanism may underlie both types of behavior.

Random noise effects in pulse-mode digital multilayer neural networks.

PubMed

Kim, Y C; Shanblatt, M A

1995-01-01

A pulse-mode digital multilayer neural network (DMNN) based on stochastic computing techniques is implemented with simple logic gates as basic computing elements. The pulse-mode signal representation and the use of simple logic gates for neural operations lead to a massively parallel yet compact and flexible network architecture, well suited for VLSI implementation. Algebraic neural operations are replaced by stochastic processes using pseudorandom pulse sequences. The distributions of the results from the stochastic processes are approximated using the hypergeometric distribution. Synaptic weights and neuron states are represented as probabilities and estimated as average pulse occurrence rates in corresponding pulse sequences. A statistical model of the noise (error) is developed to estimate the relative accuracy associated with stochastic computing in terms of mean and variance. Computational differences are then explained by comparison to deterministic neural computations. DMNN feedforward architectures are modeled in VHDL using character recognition problems as testbeds. Computational accuracy is analyzed, and the results of the statistical model are compared with the actual simulation results. Experiments show that the calculations performed in the DMNN are more accurate than those anticipated when Bernoulli sequences are assumed, as is common in the literature. Furthermore, the statistical model successfully predicts the accuracy of the operations performed in the DMNN.

Neural Decoding and "Inner" Psychophysics: A Distance-to-Bound Approach for Linking Mind, Brain, and Behavior.

PubMed

Ritchie, J Brendan; Carlson, Thomas A

2016-01-01

A fundamental challenge for cognitive neuroscience is characterizing how the primitives of psychological theory are neurally implemented. Attempts to meet this challenge are a manifestation of what Fechner called "inner" psychophysics: the theory of the precise mapping between mental quantities and the brain. In his own time, inner psychophysics remained an unrealized ambition for Fechner. We suggest that, today, multivariate pattern analysis (MVPA), or neural "decoding," methods provide a promising starting point for developing an inner psychophysics. A cornerstone of these methods are simple linear classifiers applied to neural activity in high-dimensional activation spaces. We describe an approach to inner psychophysics based on the shared architecture of linear classifiers and observers under decision boundary models such as signal detection theory. Under this approach, distance from a decision boundary through activation space, as estimated by linear classifiers, can be used to predict reaction time in accordance with signal detection theory, and distance-to-bound models of reaction time. Our "neural distance-to-bound" approach is potentially quite general, and simple to implement. Furthermore, our recent work on visual object recognition suggests it is empirically viable. We believe the approach constitutes an important step along the path to an inner psychophysics that links mind, brain, and behavior.

Reward-Modulated Hebbian Plasticity as Leverage for Partially Embodied Control in Compliant Robotics

PubMed Central

Burms, Jeroen; Caluwaerts, Ken; Dambre, Joni

2015-01-01

In embodied computation (or morphological computation), part of the complexity of motor control is offloaded to the body dynamics. We demonstrate that a simple Hebbian-like learning rule can be used to train systems with (partial) embodiment, and can be extended outside of the scope of traditional neural networks. To this end, we apply the learning rule to optimize the connection weights of recurrent neural networks with different topologies and for various tasks. We then apply this learning rule to a simulated compliant tensegrity robot by optimizing static feedback controllers that directly exploit the dynamics of the robot body. This leads to partially embodied controllers, i.e., hybrid controllers that naturally integrate the computations that are performed by the robot body into a neural network architecture. Our results demonstrate the universal applicability of reward-modulated Hebbian learning. Furthermore, they demonstrate the robustness of systems trained with the learning rule. This study strengthens our belief that compliant robots should or can be seen as computational units, instead of dumb hardware that needs a complex controller. This link between compliant robotics and neural networks is also the main reason for our search for simple universal learning rules for both neural networks and robotics. PMID:26347645

Efficient probabilistic inference in generic neural networks trained with non-probabilistic feedback.

PubMed

Orhan, A Emin; Ma, Wei Ji

2017-07-26

Animals perform near-optimal probabilistic inference in a wide range of psychophysical tasks. Probabilistic inference requires trial-to-trial representation of the uncertainties associated with task variables and subsequent use of this representation. Previous work has implemented such computations using neural networks with hand-crafted and task-dependent operations. We show that generic neural networks trained with a simple error-based learning rule perform near-optimal probabilistic inference in nine common psychophysical tasks. In a probabilistic categorization task, error-based learning in a generic network simultaneously explains a monkey's learning curve and the evolution of qualitative aspects of its choice behavior. In all tasks, the number of neurons required for a given level of performance grows sublinearly with the input population size, a substantial improvement on previous implementations of probabilistic inference. The trained networks develop a novel sparsity-based probabilistic population code. Our results suggest that probabilistic inference emerges naturally in generic neural networks trained with error-based learning rules.Behavioural tasks often require probability distributions to be inferred about task specific variables. Here, the authors demonstrate that generic neural networks can be trained using a simple error-based learning rule to perform such probabilistic computations efficiently without any need for task specific operations.

Deep Convolutional Neural Networks for Computer-Aided Detection: CNN Architectures, Dataset Characteristics and Transfer Learning

PubMed Central

Hoo-Chang, Shin; Roth, Holger R.; Gao, Mingchen; Lu, Le; Xu, Ziyue; Nogues, Isabella; Yao, Jianhua; Mollura, Daniel

2016-01-01

Remarkable progress has been made in image recognition, primarily due to the availability of large-scale annotated datasets (i.e. ImageNet) and the revival of deep convolutional neural networks (CNN). CNNs enable learning data-driven, highly representative, layered hierarchical image features from sufficient training data. However, obtaining datasets as comprehensively annotated as ImageNet in the medical imaging domain remains a challenge. There are currently three major techniques that successfully employ CNNs to medical image classification: training the CNN from scratch, using off-the-shelf pre-trained CNN features, and conducting unsupervised CNN pre-training with supervised fine-tuning. Another effective method is transfer learning, i.e., fine-tuning CNN models (supervised) pre-trained from natural image dataset to medical image tasks (although domain transfer between two medical image datasets is also possible). In this paper, we exploit three important, but previously understudied factors of employing deep convolutional neural networks to computer-aided detection problems. We first explore and evaluate different CNN architectures. The studied models contain 5 thousand to 160 million parameters, and vary in numbers of layers. We then evaluate the influence of dataset scale and spatial image context on performance. Finally, we examine when and why transfer learning from pre-trained ImageNet (via fine-tuning) can be useful. We study two specific computeraided detection (CADe) problems, namely thoraco-abdominal lymph node (LN) detection and interstitial lung disease (ILD) classification. We achieve the state-of-the-art performance on the mediastinal LN detection, with 85% sensitivity at 3 false positive per patient, and report the first five-fold cross-validation classification results on predicting axial CT slices with ILD categories. Our extensive empirical evaluation, CNN model analysis and valuable insights can be extended to the design of high performance CAD systems for other medical imaging tasks. PMID:26886976

Deep learning and face recognition: the state of the art

NASA Astrophysics Data System (ADS)

Balaban, Stephen

2015-05-01

Deep Neural Networks (DNNs) have established themselves as a dominant technique in machine learning. DNNs have been top performers on a wide variety of tasks including image classification, speech recognition, and face recognition.1-3 Convolutional neural networks (CNNs) have been used in nearly all of the top performing methods on the Labeled Faces in the Wild (LFW) dataset.3-6 In this talk and accompanying paper, I attempt to provide a review and summary of the deep learning techniques used in the state-of-the-art. In addition, I highlight the need for both larger and more challenging public datasets to benchmark these systems. Despite the ability of DNNs and autoencoders to perform unsupervised feature learning, modern facial recognition pipelines still require domain specific engineering in the form of re-alignment. For example, in Facebook's recent DeepFace paper, a 3D "frontalization" step lies at the beginning of the pipeline. This step creates a 3D face model for the incoming image and then uses a series of affine transformations of the fiducial points to "frontalize" the image. This step enables the DeepFace system to use a neural network architecture with locally connected layers without weight sharing as opposed to standard convolutional layers.6 Deep learning techniques combined with large datasets have allowed research groups to surpass human level performance on the LFW dataset.3, 5 The high accuracy (99.63% for FaceNet at the time of publishing) and utilization of outside data (hundreds of millions of images in the case of Google's FaceNet) suggest that current face verification benchmarks such as LFW may not be challenging enough, nor provide enough data, for current techniques.3, 5 There exist a variety of organizations with mobile photo sharing applications that would be capable of releasing a very large scale and highly diverse dataset of facial images captured on mobile devices. Such an "ImageNet for Face Recognition" would likely receive a warm welcome from researchers and practitioners alike.

Artificial neural network with backpropagation learning to predict mean monthly total ozone in Arosa, Switzerland

NASA Astrophysics Data System (ADS)

Chattopadhyay, Surajit; Bandyopadhyay, Goutami

2007-01-01

Present study deals with the mean monthly total ozone time series over Arosa, Switzerland. The study period is 1932-1971. First of all, the total ozone time series has been identified as a complex system and then Artificial Neural Networks models in the form of Multilayer Perceptron with back propagation learning have been developed. The models are Single-hidden-layer and Two-hidden-layer Perceptrons with sigmoid activation function. After sequential learning with learning rate 0.9 the peak total ozone period (February-May) concentrations of mean monthly total ozone have been predicted by the two neural net models. After training and validation, both of the models are found skillful. But, Two-hidden-layer Perceptron is found to be more adroit in predicting the mean monthly total ozone concentrations over the aforesaid period.

Neuromorphic learning of continuous-valued mappings in the presence of noise: Application to real-time adaptive control

NASA Technical Reports Server (NTRS)

Troudet, Terry; Merrill, Walter C.

1989-01-01

The ability of feed-forward neural net architectures to learn continuous-valued mappings in the presence of noise is demonstrated in relation to parameter identification and real-time adaptive control applications. Factors and parameters influencing the learning performance of such nets in the presence of noise are identified. Their effects are discussed through a computer simulation of the Back-Error-Propagation algorithm by taking the example of the cart-pole system controlled by a nonlinear control law. Adequate sampling of the state space is found to be essential for canceling the effect of the statistical fluctuations and allowing learning to take place.

POPPER, a simple programming language for probabilistic semantic inference in medicine.

PubMed

Robson, Barry

2015-01-01

Our previous reports described the use of the Hyperbolic Dirac Net (HDN) as a method for probabilistic inference from medical data, and a proposed probabilistic medical Semantic Web (SW) language Q-UEL to provide that data. Rather like a traditional Bayes Net, that HDN provided estimates of joint and conditional probabilities, and was static, with no need for evolution due to "reasoning". Use of the SW will require, however, (a) at least the semantic triple with more elaborate relations than conditional ones, as seen in use of most verbs and prepositions, and (b) rules for logical, grammatical, and definitional manipulation that can generate changes in the inference net. Here is described the simple POPPER language for medical inference. It can be automatically written by Q-UEL, or by hand. Based on studies with our medical students, it is believed that a tool like this may help in medical education and that a physician unfamiliar with SW science can understand it. It is here used to explore the considerable challenges of assigning probabilities, and not least what the meaning and utility of inference net evolution would be for a physician. Copyright © 2014 Elsevier Ltd. All rights reserved.

NetCDF4/HDF5 and Linked Data in the Real World - Enriching Geoscientific Metadata without Bloat

NASA Astrophysics Data System (ADS)

Ip, Alex; Car, Nicholas; Druken, Kelsey; Poudjom-Djomani, Yvette; Butcher, Stirling; Evans, Ben; Wyborn, Lesley

2017-04-01

NetCDF4 has become the dominant generic format for many forms of geoscientific data, leveraging (and constraining) the versatile HDF5 container format, while providing metadata conventions for interoperability. However, the encapsulation of detailed metadata within each file can lead to metadata "bloat", and difficulty in maintaining consistency where metadata is replicated to multiple locations. Complex conceptual relationships are also difficult to represent in simple key-value netCDF metadata. Linked Data provides a practical mechanism to address these issues by associating the netCDF files and their internal variables with complex metadata stored in Semantic Web vocabularies and ontologies, while complying with and complementing existing metadata conventions. One of the stated objectives of the netCDF4/HDF5 formats is that they should be self-describing: containing metadata sufficient for cataloguing and using the data. However, this objective can be regarded as only partially-met where details of conventions and definitions are maintained externally to the data files. For example, one of the most widely used netCDF community standards, the Climate and Forecasting (CF) Metadata Convention, maintains standard vocabularies for a broad range of disciplines across the geosciences, but this metadata is currently neither readily discoverable nor machine-readable. We have previously implemented useful Linked Data and netCDF tooling (ncskos) that associates netCDF files, and individual variables within those files, with concepts in vocabularies formulated using the Simple Knowledge Organization System (SKOS) ontology. NetCDF files contain Uniform Resource Identifier (URI) links to terms represented as SKOS Concepts, rather than plain-text representations of those terms, so we can use simple, standardised web queries to collect and use rich metadata for the terms from any Linked Data-presented SKOS vocabulary. Geoscience Australia (GA) manages a large volume of diverse geoscientific data, much of which is being translated from proprietary formats to netCDF at NCI Australia. This data is made available through the NCI National Environmental Research Data Interoperability Platform (NERDIP) for programmatic access and interdisciplinary analysis. The netCDF files contain both scientific data variables (e.g. gravity, magnetic or radiometric values), but also domain-specific operational values (e.g. specific instrument parameters) best described fully in formal vocabularies. Our ncskos codebase provides access to multiple stores of detailed external metadata in a standardised fashion. Geophysical datasets are generated from a "survey" event, and GA maintains corporate databases of all surveys and their associated metadata. It is impractical to replicate the full source survey metadata into each netCDF dataset so, instead, we link the netCDF files to survey metadata using public Linked Data URIs. These URIs link to Survey class objects which we model as a subclass of Activity objects as defined by the PROV Ontology, and we provide URI resolution for them via a custom Linked Data API which draws current survey metadata from GA's in-house databases. We have demonstrated that Linked Data is a practical way to associate netCDF data with detailed, external metadata. This allows us to ensure that catalogued metadata is kept consistent with metadata points-of-truth, and we can infer complex conceptual relationships not possible with netCDF key-value attributes alone.

Norepinephrine transporter inhibition alters the hemodynamic response to hypergravitation.

PubMed

Strempel, Sebastian; Schroeder, Christoph; Hemmersbach, Ruth; Boese, Andrea; Tank, Jens; Diedrich, André; Heer, Martina; Luft, Friedrich C; Jordan, Jens

2008-03-01

Sympathetically mediated tachycardia and vasoconstriction maintain blood pressure during hypergravitational stress, thereby preventing gravitation-induced loss of consciousness. Norepinephrine transporter (NET) inhibition prevents neurally mediated (pre)syncope during gravitational stress imposed by head-up tilt testing. Thus it seems reasonable that NET inhibition could increase tolerance to hypergravitational stress. We performed a double-blind, randomized, placebo-controlled crossover study in 11 healthy men (26 +/- 1 yr, body mass index 24 +/- 1 kg/m2), who ingested the selective NET inhibitor reboxetine (4 mg) or matching placebo 25, 13, and 1 h before testing on separate days. We monitored heart rate, blood pressure, and thoracic impedance in three different body positions (supine, seated, standing) and during a graded centrifuge run (incremental steps of 0.5 g for 3 min each, up to a maximal vertical acceleration load of 3 g). NET inhibition increased supine blood pressure and heart rate. With placebo, blood pressure increased in the seated position and was well maintained during standing. However, with NET inhibition, blood pressure decreased in the seated and standing position. During hypergravitation, blood pressure increased in a graded fashion with placebo. With NET inhibition, the increase in blood pressure during hypergravitation was profoundly diminished. Conversely, the tachycardic responses to sitting, standing, and hypergravitation all were greatly increased with NET inhibition. In contrast to our expectation, short-term NET inhibition did not improve tolerance to hypergravitation. Redistribution of sympathetic activity to the heart or changes in baroreflex responses could explain the excessive tachycardia that we observed.

Neural learning rules for the vestibulo-ocular reflex

NASA Technical Reports Server (NTRS)

Raymond, J. L.; Lisberger, S. G.

1998-01-01

Mechanisms for the induction of motor learning in the vestibulo-ocular reflex (VOR) were evaluated by recording the patterns of neural activity elicited in the cerebellum by a range of stimuli that induce learning. Patterns of climbing-fiber, vestibular, and Purkinje cell simple-spike signals were examined during sinusoidal head movement paired with visual image movement at stimulus frequencies from 0.5 to 10 Hz. A comparison of simple-spike and vestibular signals contained the information required to guide learning only at low stimulus frequencies, and a comparison of climbing-fiber and simple-spike signals contained the information required to guide learning only at high stimulus frequencies. Learning could be guided by comparison of climbing-fiber and vestibular signals at all stimulus frequencies tested, but only if climbing fiber responses were compared with the vestibular signals present 100 msec earlier. Computational analysis demonstrated that this conclusion is valid even if there is a broad range of vestibular signals at the site of plasticity. Simulations also indicated that the comparison of vestibular and climbing-fiber signals across the 100 msec delay must be implemented by a subcellular "eligibility" trace rather than by neural circuits that delay the vestibular inputs to the site of plasticity. The results suggest two alternative accounts of learning in the VOR. Either there are multiple mechanisms of learning that use different combinations of neural signals to drive plasticity, or there is a single mechanism tuned to climbing-fiber activity that follows activity in vestibular pathways by approximately 100 msec.

Framewise phoneme classification with bidirectional LSTM and other neural network architectures.

PubMed

Graves, Alex; Schmidhuber, Jürgen

2005-01-01

In this paper, we present bidirectional Long Short Term Memory (LSTM) networks, and a modified, full gradient version of the LSTM learning algorithm. We evaluate Bidirectional LSTM (BLSTM) and several other network architectures on the benchmark task of framewise phoneme classification, using the TIMIT database. Our main findings are that bidirectional networks outperform unidirectional ones, and Long Short Term Memory (LSTM) is much faster and also more accurate than both standard Recurrent Neural Nets (RNNs) and time-windowed Multilayer Perceptrons (MLPs). Our results support the view that contextual information is crucial to speech processing, and suggest that BLSTM is an effective architecture with which to exploit it.

Synchronization in neural nets

NASA Technical Reports Server (NTRS)

Vidal, Jacques J.; Haggerty, John

1988-01-01

The paper presents an artificial neural network concept (the Synchronizable Oscillator Networks) where the instants of individual firings in the form of point processes constitute the only form of information transmitted between joining neurons. In the model, neurons fire spontaneously and regularly in the absence of perturbation. When interaction is present, the scheduled firings are advanced or delayed by the firing of neighboring neurons. Networks of such neurons become global oscillators which exhibit multiple synchronizing attractors. From arbitrary initial states, energy minimization learning procedures can make the network converge to oscillatory modes that satisfy multi-dimensional constraints. Such networks can directly represent routing and scheduling problems that consist of ordering sequences of events.

Dynamic Adaptive Neural Network Arrays: A Neuromorphic Architecture

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

Disney, Adam; Reynolds, John

2015-01-01

Dynamic Adaptive Neural Network Array (DANNA) is a neuromorphic hardware implementation. It differs from most other neuromorphic projects in that it allows for programmability of structure, and it is trained or designed using evolutionary optimization. This paper describes the DANNA structure, how DANNA is trained using evolutionary optimization, and an application of DANNA to a very simple classification task.

Modeling a Neural Network as a Teaching Tool for the Learning of the Structure-Function Relationship

ERIC Educational Resources Information Center

Salinas, Dino G.; Acevedo, Cristian; Gomez, Christian R.

2010-01-01

The authors describe an activity they have created in which students can visualize a theoretical neural network whose states evolve according to a well-known simple law. This activity provided an uncomplicated approach to a paradigm commonly represented through complex mathematical formulation. From their observations, students learned many basic…

Neural Network Classifier Architectures for Phoneme Recognition. CRC Technical Note No. CRC-TN-92-001.

ERIC Educational Resources Information Center

Treurniet, William

A study applied artificial neural networks, trained with the back-propagation learning algorithm, to modelling phonemes extracted from the DARPA TIMIT multi-speaker, continuous speech data base. A number of proposed network architectures were applied to the phoneme classification task, ranging from the simple feedforward multilayer network to more…

Synchronization criteria for generalized reaction-diffusion neural networks via periodically intermittent control.

PubMed

Gan, Qintao; Lv, Tianshi; Fu, Zhenhua

2016-04-01

In this paper, the synchronization problem for a class of generalized neural networks with time-varying delays and reaction-diffusion terms is investigated concerning Neumann boundary conditions in terms of p-norm. The proposed generalized neural networks model includes reaction-diffusion local field neural networks and reaction-diffusion static neural networks as its special cases. By establishing a new inequality, some simple and useful conditions are obtained analytically to guarantee the global exponential synchronization of the addressed neural networks under the periodically intermittent control. According to the theoretical results, the influences of diffusion coefficients, diffusion space, and control rate on synchronization are analyzed. Finally, the feasibility and effectiveness of the proposed methods are shown by simulation examples, and by choosing different diffusion coefficients, diffusion spaces, and control rates, different controlled synchronization states can be obtained.

NutriNet: A Deep Learning Food and Drink Image Recognition System for Dietary Assessment.

PubMed

Mezgec, Simon; Koroušić Seljak, Barbara

2017-06-27

Automatic food image recognition systems are alleviating the process of food-intake estimation and dietary assessment. However, due to the nature of food images, their recognition is a particularly challenging task, which is why traditional approaches in the field have achieved a low classification accuracy. Deep neural networks have outperformed such solutions, and we present a novel approach to the problem of food and drink image detection and recognition that uses a newly-defined deep convolutional neural network architecture, called NutriNet. This architecture was tuned on a recognition dataset containing 225,953 512 × 512 pixel images of 520 different food and drink items from a broad spectrum of food groups, on which we achieved a classification accuracy of 86 . 72 % , along with an accuracy of 94 . 47 % on a detection dataset containing 130 , 517 images. We also performed a real-world test on a dataset of self-acquired images, combined with images from Parkinson's disease patients, all taken using a smartphone camera, achieving a top-five accuracy of 55 % , which is an encouraging result for real-world images. Additionally, we tested NutriNet on the University of Milano-Bicocca 2016 (UNIMIB2016) food image dataset, on which we improved upon the provided baseline recognition result. An online training component was implemented to continually fine-tune the food and drink recognition model on new images. The model is being used in practice as part of a mobile app for the dietary assessment of Parkinson's disease patients.

Why is there net surface heating over the Antarctic Circumpolar Current?

NASA Astrophysics Data System (ADS)

Czaja, Arnaud; Marshall, John

2015-05-01

Using a combination of atmospheric reanalysis data, climate model outputs and a simple model, key mechanisms controlling net surface heating over the Southern Ocean are identified. All data sources used suggest that, in a streamline-averaged view, net surface heating over the Antarctic Circumpolar Current (ACC) is a result of net accumulation of solar radiation rather than a result of heat gain through turbulent fluxes (the latter systematically cool the upper ocean). It is proposed that the fraction of this net radiative heat gain realized as net ACC heating is set by two factors. First, the sea surface temperature at the southern edge of the ACC. Second, the relative strength of the negative heatflux feedbacks associated with evaporation at the sea surface and advection of heat by the residual flow in the oceanic mixed layer. A large advective feedback and a weak evaporative feedback maximize net ACC heating. It is shown that the present Southern Ocean and its circumpolar current are in this heating regime.

Topological analysis of metabolic networks based on petri net theory.

PubMed

Zevedei-Oancea, Ionela; Schuster, Stefan

2011-01-01

Petri net concepts provide additional tools for the modelling of metabolic networks. Here, the similarities between the counterparts in traditional biochemical modelling and Petri net theory are discussed. For example the stoichiometry matrix of a metabolic network corresponds to the incidence matrix of the Petri net. The flux modes and conservation relations have the T-invariants, respectively, P-invariants as counterparts. We reveal the biological meaning of some notions specific to the Petri net framework (traps, siphons, deadlocks, liveness). We focus on the topological analysis rather than on the analysis of the dynamic behaviour. The treatment of external metabolites is discussed. Some simple theoretical examples are presented for illustration. Also the Petri nets corresponding to some biochemical networks are built to support our results. For example, the role of triose phosphate isomerase (TPI) in Trypanosoma brucei metabolism is evaluated by detecting siphons and traps. All Petri net properties treated in this contribution are exemplified on a system extracted from nucleotide metabolism.

Topological analysis of metabolic networks based on Petri net theory.

PubMed

Zevedei-Oancea, Ionela; Schuster, Stefan

2003-01-01

Petri net concepts provide additional tools for the modelling of metabolic networks. Here, the similarities between the counterparts in traditional biochemical modelling and Petri net theory are discussed. For example the stoichiometry matrix of a metabolic network corresponds to the incidence matrix of the Petri net. The flux modes and conservation relations have the T-invariants, respectively, P-invariants as counterparts. We reveal the biological meaning of some notions specific to the Petri net framework (traps, siphons, deadlocks, liveness). We focus on the topological analysis rather than on the analysis of the dynamic behaviour. The treatment of external metabolites is discussed. Some simple theoretical examples are presented for illustration. Also the Petri nets corresponding to some biochemical networks are built to support our results. For example, the role of triose phosphate isomerase (TPI) in Trypanosoma brucei metabolism is evaluated by detecting siphons and traps. All Petri net properties treated in this contribution are exemplified on a system extracted from nucleotide metabolism.

Cognitive Analysis of Meaning and Acquired Mental Representations as an Alternative Measurement Method Technique to Innovate E-Assessment

ERIC Educational Resources Information Center

Morales-Martinez, Guadalupe Elizabeth; Lopez-Ramirez, Ernesto Octavio; Castro-Campos, Claudia; Villarreal-Treviño, Maria Guadalupe; Gonzales-Trujillo, Claudia Jaquelina

2017-01-01

Empirical directions to innovate e-assessments and to support the theoretical development of e-learning are discussed by presenting a new learning assessment system based on cognitive technology. Specifically, this system encompassing trained neural nets that can discriminate between students who successfully integrated new knowledge course…

Optical Computing Based on Neuronal Models

DTIC Science & Technology

1988-05-01

walking, and cognition are far too complex for existing sequential digital computers. Therefore new architectures, hardware, and algorithms modeled...collective behavior, and iterative processing into optical processing and artificial neurodynamical systems. Another intriguing promise of neural nets is...with architectures, implementations, and programming; and material research s -7- called for. Our future research in neurodynamics will continue to

High level cognitive information processing in neural networks

NASA Technical Reports Server (NTRS)

Barnden, John A.; Fields, Christopher A.

1992-01-01

Two related research efforts were addressed: (1) high-level connectionist cognitive modeling; and (2) local neural circuit modeling. The goals of the first effort were to develop connectionist models of high-level cognitive processes such as problem solving or natural language understanding, and to understand the computational requirements of such models. The goals of the second effort were to develop biologically-realistic model of local neural circuits, and to understand the computational behavior of such models. In keeping with the nature of NASA's Innovative Research Program, all the work conducted under the grant was highly innovative. For instance, the following ideas, all summarized, are contributions to the study of connectionist/neural networks: (1) the temporal-winner-take-all, relative-position encoding, and pattern-similarity association techniques; (2) the importation of logical combinators into connection; (3) the use of analogy-based reasoning as a bridge across the gap between the traditional symbolic paradigm and the connectionist paradigm; and (4) the application of connectionism to the domain of belief representation/reasoning. The work on local neural circuit modeling also departs significantly from the work of related researchers. In particular, its concentration on low-level neural phenomena that could support high-level cognitive processing is unusual within the area of biological local circuit modeling, and also serves to expand the horizons of the artificial neural net field.

Znf703, a novel target of Pax3 and Zic1, regulates hindbrain and neural crest development in Xenopus.

PubMed

Hong, Chang-Soo; Saint-Jeannet, Jean-Pierre

2017-12-01

The transcription factors Pax3 and Zic1 are critical to specify the neural plate border and to promote neural crest formation. In a microarray screen designed to identify genes regulated by Pax3 and Zic1 in Xenopus we isolated Znf703/Nlz1 a transcriptional repressor member of the NET (NocA/Nlz, Elbow, and TLP-1) protein family. At early neurula stage znf703 is expressed in the dorsal ectoderm, spanning the neural plate and neural plate border, with an anterior boundary of expression corresponding to rhombomeres 3 and 4 (r3/r4) in the prospective hindbrain. As a bonafide target of Pax3 and Zic1, znf703 is activated by neural plate border inducing signals, and its expression depends on Pax3 and Zic1 function in the embryo. Znf703 morpholino-mediated knockdown expanded several posterior hindbrain genes, while Znf703 overexpression completely obliterated the expression of these segmental genes, signifying that the transcriptional repressor activity of Znf703 is critical to pattern the hindbrain. Furthermore, snai2 and sox10 expression was severely impaired upon manipulation of Znf703 expression levels in the embryo suggesting that Znf703 participates in neural crest formation downstream of Pax3 and Zic1 in Xenopus. © 2017 Wiley Periodicals, Inc.

Evaluation of Deep Learning Models for Predicting CO2 Flux

NASA Astrophysics Data System (ADS)

Halem, M.; Nguyen, P.; Frankel, D.

2017-12-01

Artificial neural networks have been employed to calculate surface flux measurements from station data because they are able to fit highly nonlinear relations between input and output variables without knowing the detail relationships between the variables. However, the accuracy in performing neural net estimates of CO2 flux from observations of CO2 and other atmospheric variables is influenced by the architecture of the neural model, the availability, and complexity of interactions between physical variables such as wind, temperature, and indirect variables like latent heat, and sensible heat, etc. We evaluate two deep learning models, feed forward and recurrent neural network models to learn how they each respond to the physical measurements, time dependency of the measurements of CO2 concentration, humidity, pressure, temperature, wind speed etc. for predicting the CO2 flux. In this paper, we focus on a) building neural network models for estimating CO2 flux based on DOE data from tower Atmospheric Radiation Measurement data; b) evaluating the impact of choosing the surface variables and model hyper-parameters on the accuracy and predictions of surface flux; c) assessing the applicability of the neural network models on estimate CO2 flux by using OCO-2 satellite data; d) studying the efficiency of using GPU-acceleration for neural network performance using IBM Power AI deep learning software and packages on IBM Minsky system.

Two simple leg net devices designed to protect lower-extremity skin grafts and donor sites and prevent decubitus ulcer.

PubMed

Hedman, Travis L; Chapman, Ted T; Dewey, William S; Quick, Charles D; Wolf, Steven E; Holcomb, John B

2007-01-01

Burn therapists routinely are tasked to position the lower extremities of burn patients for pressure ulcer prevention, skin graft protection, donor site ventilation, and edema reduction. We developed two durable and low-maintenance devices that allow effective positioning of the lower extremities. The high-profile and low-profile leg net devices were simple to fabricate and maintain. The frame was assembled using a three-quarter-inch diameter copper pipe and copper fittings (45 degrees, 90 degrees, and tees). A double layer of elasticized tubular netting was pulled over the frame and doubled back for leg support to complete the devices. The devices can be placed on any bed surface. The netting can be exchanged when soiled and the frame can be disinfected between patients using standard techniques. Both devices were used on approximately 250 patients for a total of 1200 treatment days. No incidence of pressure ulcer was observed, and graft take was not adversely affected. The devices have not required repairs or replacement. Medical providers reported they are easy to apply and effectively maintain proper positioning throughout application. Neither device interfered with the application of other positioning devices. Both devices were found to be an effective method of positioning lower extremities to prevent pressure ulcer, minimize graft loss and donor site morbidity, and reduce edema. The devices allowed for proper wound ventilation and protected grafted lower extremities on any bed surface. The devices are simple to fabricate and maintain. Both devices can be effectively used simultaneously with other positioning devices.

Color image definition evaluation method based on deep learning method

NASA Astrophysics Data System (ADS)

Liu, Di; Li, YingChun

2018-01-01

In order to evaluate different blurring levels of color image and improve the method of image definition evaluation, this paper proposed a method based on the depth learning framework and BP neural network classification model, and presents a non-reference color image clarity evaluation method. Firstly, using VGG16 net as the feature extractor to extract 4,096 dimensions features of the images, then the extracted features and labeled images are employed in BP neural network to train. And finally achieve the color image definition evaluation. The method in this paper are experimented by using images from the CSIQ database. The images are blurred at different levels. There are 4,000 images after the processing. Dividing the 4,000 images into three categories, each category represents a blur level. 300 out of 400 high-dimensional features are trained in VGG16 net and BP neural network, and the rest of 100 samples are tested. The experimental results show that the method can take full advantage of the learning and characterization capability of deep learning. Referring to the current shortcomings of the major existing image clarity evaluation methods, which manually design and extract features. The method in this paper can extract the images features automatically, and has got excellent image quality classification accuracy for the test data set. The accuracy rate is 96%. Moreover, the predicted quality levels of original color images are similar to the perception of the human visual system.

Surface daytime net radiation estimation using artificial neural networks

DOE PAGES

Jiang, Bo; Zhang, Yi; Liang, Shunlin; ...

2014-11-11

Net all-wave surface radiation (R n) is one of the most important fundamental parameters in various applications. However, conventional R n measurements are difficult to collect because of the high cost and ongoing maintenance of recording instruments. Therefore, various empirical R n estimation models have been developed. This study presents the results of two artificial neural network (ANN) models (general regression neural networks (GRNN) and Neuroet) to estimate R n globally from multi-source data, including remotely sensed products, surface measurements, and meteorological reanalysis products. R n estimates provided by the two ANNs were tested against in-situ radiation measurements obtained frommore » 251 global sites between 1991–2010 both in global mode (all data were used to fit the models) and in conditional mode (the data were divided into four subsets and the models were fitted separately). Based on the results obtained from extensive experiments, it has been proved that the two ANNs were superior to linear-based empirical models in both global and conditional modes and that the GRNN performed better and was more stable than Neuroet. The GRNN estimates had a determination coefficient (R 2) of 0.92, a root mean square error (RMSE) of 34.27 W·m –2 , and a bias of –0.61 W·m –2 in global mode based on the validation dataset. In conclusion, ANN methods are a potentially powerful tool for global R n estimation.« less

A simple stochastic weather generator for ecological modeling

Treesearch

A.G. Birt; M.R. Valdez-Vivas; R.M. Feldman; C.W. Lafon; D. Cairns; R.N. Coulson; M. Tchakerian; W. Xi; Jim Guldin

2010-01-01

Stochastic weather generators are useful tools for exploring the relationship between organisms and their environment. This paper describes a simple weather generator that can be used in ecological modeling projects. We provide a detailed description of methodology, and links to full C++ source code (http://weathergen.sourceforge.net) required to implement or modify...

Automated Detection of Diabetic Retinopathy using Deep Learning.

PubMed

Lam, Carson; Yi, Darvin; Guo, Margaret; Lindsey, Tony

2018-01-01

Diabetic retinopathy is a leading cause of blindness among working-age adults. Early detection of this condition is critical for good prognosis. In this paper, we demonstrate the use of convolutional neural networks (CNNs) on color fundus images for the recognition task of diabetic retinopathy staging. Our network models achieved test metric performance comparable to baseline literature results, with validation sensitivity of 95%. We additionally explored multinomial classification models, and demonstrate that errors primarily occur in the misclassification of mild disease as normal due to the CNNs inability to detect subtle disease features. We discovered that preprocessing with contrast limited adaptive histogram equalization and ensuring dataset fidelity by expert verification of class labels improves recognition of subtle features. Transfer learning on pretrained GoogLeNet and AlexNet models from ImageNet improved peak test set accuracies to 74.5%, 68.8%, and 57.2% on 2-ary, 3-ary, and 4-ary classification models, respectively.

Methods for quantifying simple gravity sensing in Drosophila melanogaster.

PubMed

Inagaki, Hidehiko K; Kamikouchi, Azusa; Ito, Kei

2010-01-01

Perception of gravity is essential for animals: most animals possess specific sense organs to detect the direction of the gravitational force. Little is known, however, about the molecular and neural mechanisms underlying their behavioral responses to gravity. Drosophila melanogaster, having a rather simple nervous system and a large variety of molecular genetic tools available, serves as an ideal model for analyzing the mechanisms underlying gravity sensing. Here we describe an assay to measure simple gravity responses of flies behaviorally. This method can be applied for screening genetic mutants of gravity perception. Furthermore, in combination with recent genetic techniques to silence or activate selective sets of neurons, it serves as a powerful tool to systematically identify neural substrates required for the proper behavioral responses to gravity. The assay requires 10 min to perform, and two experiments can be performed simultaneously, enabling 12 experiments per hour.

Evaluation of simple model for net radiation estimates above various vegetation covers

NASA Astrophysics Data System (ADS)

Hlavinka, P.; Trnka, M.; Fischer, M.; Kucera, J.; Mozny, M.; Zalud, Z.

2010-09-01

The main objective of submitted study was to calibrate and verify the simple model for net radiation (Rn) estimates during the growing periods of selected agricultural crops. In the same time the soil heat flux (G) measurements were analysed. The model needs incoming solar radiation, air temperature, vapor pressure measurements and information about albedo as input. The net radiation is determined as difference between the incoming net shortwave radiation (Rns) and the outgoing net longwave radiation (Rnl). The Rns is estimated from incoming solar radiation using albedo. The Rnl is estimated from daily maximum and minimum temperature, vapour pressure, incoming solar radiation and derived clear-sky radiation. The accuracy of the model was assessed on the basis of radiation balance measurements (by Net radiometer Schenk 8110) at two experimental stations in the Czech Republic (i.e. Polkovice 49°23´ (N), 17°17´ (E), 205 m a.s.l.; Domanínek 49°32´ (N), 16°15´ (E), 544 m a.s.l.) during the years 2009 and 2010. The parameter G was measured by Hukseflux Thermal Sensor HFP01. For the purpose of mentioned analyses the measurements were conducted during the growing season of spring barley, winter wheat, winter rape, grass, poplars and above field after harvest of cereals (after/without tillage). These covers are very common type of surface within agricultural landscape in Central Europe. The enhanced method of Rn and G estimation were then used for the SoilClim model runs. The present version of SoilClim uses very simple algorithm for radiation balance and should be modified to be closer to reality. Namely the estimates of reference evapotranspiration (ETo), actual evapotranspiration (ETa) and soil water content could be substantially improved by this way. Acknowledgement: We gratefully acknowledge the support of the Grant Agency of the Czech Republic (no. 521/09/P479) and Research plan No. MSM6215648905 "Biological and technological aspects of sustainability of controlled ecosystems and their adaptability to climate change" .

A feasibility study for long-path multiple detection using a neural network

NASA Technical Reports Server (NTRS)

Feuerbacher, G. A.; Moebes, T. A.

1994-01-01

Least-squares inverse filters have found widespread use in the deconvolution of seismograms and the removal of multiples. The use of least-squares prediction filters with prediction distances greater than unity leads to the method of predictive deconvolution which can be used for the removal of long path multiples. The predictive technique allows one to control the length of the desired output wavelet by control of the predictive distance, and hence to specify the desired degree of resolution. Events which are periodic within given repetition ranges can be attenuated selectively. The method is thus effective in the suppression of rather complex reverberation patterns. A back propagation(BP) neural network is constructed to perform the detection of first arrivals of the multiples and therefore aid in the more accurate determination of the predictive distance of the multiples. The neural detector is applied to synthetic reflection coefficients and synthetic seismic traces. The processing results show that the neural detector is accurate and should lead to an automated fast method for determining predictive distances across vast amounts of data such as seismic field records. The neural network system used in this study was the NASA Software Technology Branch's NETS system.

An Automatic Diagnosis Method of Facial Acne Vulgaris Based on Convolutional Neural Network.

PubMed

Shen, Xiaolei; Zhang, Jiachi; Yan, Chenjun; Zhou, Hong

2018-04-11

In this paper, we present a new automatic diagnosis method for facial acne vulgaris which is based on convolutional neural networks (CNNs). To overcome the shortcomings of previous methods which were the inability to classify enough types of acne vulgaris. The core of our method is to extract features of images based on CNNs and achieve classification by classifier. A binary-classifier of skin-and-non-skin is used to detect skin area and a seven-classifier is used to achieve the classification task of facial acne vulgaris and healthy skin. In the experiments, we compare the effectiveness of our CNN and the VGG16 neural network which is pre-trained on the ImageNet data set. We use a ROC curve to evaluate the performance of binary-classifier and use a normalized confusion matrix to evaluate the performance of seven-classifier. The results of our experiments show that the pre-trained VGG16 neural network is effective in extracting features from facial acne vulgaris images. And the features are very useful for the follow-up classifiers. Finally, we try applying the classifiers both based on the pre-trained VGG16 neural network to assist doctors in facial acne vulgaris diagnosis.

Self mobile space manipulator project

NASA Technical Reports Server (NTRS)

Brown, H. Ben; Friedman, Mark; Xu, Yangsheng; Kanade, Takeo

1992-01-01

A relatively simple, modular, low mass, low cost robot is being developed for space EVA that is large enough to be independently mobile on a space station or platform exterior, yet versatile enough to accomplish many vital tasks. The robot comprises two long flexible links connected by a rotary joint, with 2-DOF 'wrist' joints and grippers at each end. It walks by gripping pre-positioned attachment points, such as trusswork nodes, and alternately shifting its base of support from one foot (gripper) to the other. The robot can perform useful tasks such as visual inspection, material transport, and light assembly by manipulating objects with one gripper, while stabilizing itself with the other. At SOAR '90, we reported development of 1/3 scale robot hardware, modular trusswork to serve as a locomotion substrate, and a gravity compensation system to allow laboratory tests of locomotion strategies on the horizontal face of the trusswork. In this paper, we report on project progress including the development of: (1) adaptive control for automatic adjustment to loads; (2) enhanced manipulation capabilities; (3) machine vision, including the use of neural nets, to guide autonomous locomotion; (4) locomotion between orthogonal trusswork faces; and (5) improved facilities for gravity compensation and telerobotic control.

Deep feature extraction and combination for synthetic aperture radar target classification

NASA Astrophysics Data System (ADS)

Amrani, Moussa; Jiang, Feng

2017-10-01

Feature extraction has always been a difficult problem in the classification performance of synthetic aperture radar automatic target recognition (SAR-ATR). It is very important to select discriminative features to train a classifier, which is a prerequisite. Inspired by the great success of convolutional neural network (CNN), we address the problem of SAR target classification by proposing a feature extraction method, which takes advantage of exploiting the extracted deep features from CNNs on SAR images to introduce more powerful discriminative features and robust representation ability for them. First, the pretrained VGG-S net is fine-tuned on moving and stationary target acquisition and recognition (MSTAR) public release database. Second, after a simple preprocessing is performed, the fine-tuned network is used as a fixed feature extractor to extract deep features from the processed SAR images. Third, the extracted deep features are fused by using a traditional concatenation and a discriminant correlation analysis algorithm. Finally, for target classification, K-nearest neighbors algorithm based on LogDet divergence-based metric learning triplet constraints is adopted as a baseline classifier. Experiments on MSTAR are conducted, and the classification accuracy results demonstrate that the proposed method outperforms the state-of-the-art methods.

Neural Systems Involved in Fear and Anxiety Measured with Fear-Potentiated Startle

ERIC Educational Resources Information Center

Davis, Michael

2006-01-01

A good deal is now known about the neural circuitry involved in how conditioned fear can augment a simple reflex (fear-potentiated startle). This involves visual or auditory as well as shock pathways that project via the thalamus and perirhinal or insular cortex to the basolateral amygdala (BLA). The BLA projects to the central (CeA) and medial…

Developmental dissociation in the neural responses to simple multiplication and subtraction problems

PubMed Central

Prado, Jérôme; Mutreja, Rachna; Booth, James R.

2014-01-01

Mastering single-digit arithmetic during school years is commonly thought to depend upon an increasing reliance on verbally memorized facts. An alternative model, however, posits that fluency in single-digit arithmetic might also be achieved via the increasing use of efficient calculation procedures. To test between these hypotheses, we used a cross-sectional design to measure the neural activity associated with single-digit subtraction and multiplication in 34 children from 2nd to 7th grade. The neural correlates of language and numerical processing were also identified in each child via localizer scans. Although multiplication and subtraction were undistinguishable in terms of behavior, we found a striking developmental dissociation in their neural correlates. First, we observed grade-related increases of activity for multiplication, but not for subtraction, in a language-related region of the left temporal cortex. Second, we found grade-related increases of activity for subtraction, but not for multiplication, in a region of the right parietal cortex involved in the procedural manipulation of numerical quantities. The present results suggest that fluency in simple arithmetic in children may be achieved by both increasing reliance on verbal retrieval and by greater use of efficient quantity-based procedures, depending on the operation. PMID:25089323

Diversity within a Birdsong

NASA Astrophysics Data System (ADS)

Laje, Rodrigo; Mindlin, Gabriel B.

2002-12-01

We present a model for the activities of neural circuits in a nucleus found in the brains of songbirds: the robust nucleus of the archistriatum (RA). This is a fore brain song control nucleus responsible for the phasic and precise neural signals driving vocal and respiratory motor neurons during singing. Driving a physical model of the avian vocal organ with the signals generated by the neural model, we produce synthetic songs. This allows us to show that certain connectivity architectures in the RA give rise to a wide range of different vocalizations under simple excitatory instructions.

Auditory cortical plasticity induced by intracortical microstimulation under pharmacological blockage of inhibitory synapses.

PubMed

Yokota, R; Takahashi, H; Funamizu, A; Uchihara, M; Suzurikawa, J; Kanzaki, R

2006-01-01

Electrical stimulation that can reorganize our neural system has a potential for promising neurorehabilitation. We previously demonstrated that temporally controlled intracortical microstimulation (ICMS) could induce the spike time-dependant plasticity and modify tuning properties of cortical neurons as desired. A 'pairing' ICMS following tone-induced excitatory post-synaptic potentials (EPSPs) produced potentiation in response to the paired tones, while an 'anti-pairing' ICMS preceding the tone-induced EPSPs resulted in depression. However, the conventional ICMS affected both excitatory and inhibitory synapses, and thereby could not quantify net excitatory synaptic effects. In the present work, we evaluated the ICMS effects under a pharmacological blockage of inhibitory inputs. The pharmacological blockage enhanced the ICMS effects, suggesting that inhibitory inputs determine a plastic degree of the neural system. Alternatively, the conventional ICMS had an inadequate timing to control excitatory synaptic inputs, because inhibitory synapse determined the latency of total neural inputs.

Neural representation of orientation relative to gravity in the macaque cerebellum

PubMed Central

Laurens, Jean; Meng, Hui; Angelaki, Dora E.

2013-01-01

Summary A fundamental challenge for maintaining spatial orientation and interacting with the world is knowledge of our orientation relative to gravity, i.e. tilt. Sensing gravity is complicated because of Einstein’s equivalence principle, where gravitational and translational accelerations are physically indistinguishable. Theory has proposed that this ambiguity is solved by tracking head tilt through multisensory integration. Here we identify a group of Purkinje cells in the caudal cerebellar vermis with responses that reflect an estimate of head tilt. These tilt-selective cells are complementary to translation-selective Purkinje cells, such that their population activities sum to the net gravito-inertial acceleration encoded by the otolith organs, as predicted by theory. These findings reflect the remarkable ability of the cerebellum for neural computation and provide novel quantitative evidence for a neural representation of gravity, whose calculation relies on long-postulated theoretical concepts such as internal models and Bayesian priors. PMID:24360549

Sparse distributed memory and related models

NASA Technical Reports Server (NTRS)

Kanerva, Pentti

1992-01-01

Described here is sparse distributed memory (SDM) as a neural-net associative memory. It is characterized by two weight matrices and by a large internal dimension - the number of hidden units is much larger than the number of input or output units. The first matrix, A, is fixed and possibly random, and the second matrix, C, is modifiable. The SDM is compared and contrasted to (1) computer memory, (2) correlation-matrix memory, (3) feet-forward artificial neural network, (4) cortex of the cerebellum, (5) Marr and Albus models of the cerebellum, and (6) Albus' cerebellar model arithmetic computer (CMAC). Several variations of the basic SDM design are discussed: the selected-coordinate and hyperplane designs of Jaeckel, the pseudorandom associative neural memory of Hassoun, and SDM with real-valued input variables by Prager and Fallside. SDM research conducted mainly at the Research Institute for Advanced Computer Science (RIACS) in 1986-1991 is highlighted.

An avian model for the reversal of neurobehavioral teratogenicity with neural stem cells

PubMed Central

Dotan, Sharon; Pinkas, Adi; Slotkin, Theodore A.; Yanai, Joseph

2010-01-01

A fast and simple model which uses lower animals on the evolutionary scale is beneficial for developing procedures for the reversal of neurobehavioral teratogenicity with neural stem cells. Here, we established a procedure for the derivation of chick neural stem cells, establishing embryonic day (E) 10 as optimal for progression to neuronal phenotypes. Cells were obtained from the embryonic cerebral hemispheres and incubated for 5–7 days in enriched medium containing epidermal growth factor (EGF) and basic fibroblast growth factor (FGF2) according to a procedure originally developed for mice. A small percentage of the cells survived, proliferated and formed nestin-positive neurospheres. After removal of the growth factors to allow differentiation (5 days), 74% of the cells differentiated into all major lineages of the nervous system, including neurons (Beta III tubulin-positive, 54% of the total number of differentiated cells), astrocytes (GFAP-positive, 26%), and oligodendrocytes (O4-positive, 20%). These findings demonstrate that the cells were indeed neural stem cells. Next, the cells were transplanted in two allograft chick models; (1) direct cerebral transplantation to 24-hours-old chicks, followed by post-transplantation cell tracking at 24 hours, 6 days and 14 days, and (2) intravenous transplantation to chick embryos on E13, followed by cell tracking on E19. With both methods, transplanted cells were found in the brain. The chick embryo provides a convenient, precisely-timed and unlimited supply of neural progenitors for therapy by transplantation, as well as constituting a fast and simple model in which to evaluate the ability of neural stem cell transplantation to repair neural damage, steps that are critical for progress toward therapeutic applications. PMID:20211723

Fluctuation-Driven Neural Dynamics Reproduce Drosophila Locomotor Patterns

PubMed Central

Cruchet, Steeve; Gustafson, Kyle; Benton, Richard; Floreano, Dario

2015-01-01

The neural mechanisms determining the timing of even simple actions, such as when to walk or rest, are largely mysterious. One intriguing, but untested, hypothesis posits a role for ongoing activity fluctuations in neurons of central action selection circuits that drive animal behavior from moment to moment. To examine how fluctuating activity can contribute to action timing, we paired high-resolution measurements of freely walking Drosophila melanogaster with data-driven neural network modeling and dynamical systems analysis. We generated fluctuation-driven network models whose outputs—locomotor bouts—matched those measured from sensory-deprived Drosophila. From these models, we identified those that could also reproduce a second, unrelated dataset: the complex time-course of odor-evoked walking for genetically diverse Drosophila strains. Dynamical models that best reproduced both Drosophila basal and odor-evoked locomotor patterns exhibited specific characteristics. First, ongoing fluctuations were required. In a stochastic resonance-like manner, these fluctuations allowed neural activity to escape stable equilibria and to exceed a threshold for locomotion. Second, odor-induced shifts of equilibria in these models caused a depression in locomotor frequency following olfactory stimulation. Our models predict that activity fluctuations in action selection circuits cause behavioral output to more closely match sensory drive and may therefore enhance navigation in complex sensory environments. Together these data reveal how simple neural dynamics, when coupled with activity fluctuations, can give rise to complex patterns of animal behavior. PMID:26600381

A model of interval timing by neural integration

PubMed Central

Simen, Patrick; Balci, Fuat; deSouza, Laura; Cohen, Jonathan D.; Holmes, Philip

2011-01-01

We show that simple assumptions about neural processing lead to a model of interval timing as a temporal integration process, in which a noisy firing-rate representation of time rises linearly on average toward a response threshold over the course of an interval. Our assumptions include: that neural spike trains are approximately independent Poisson processes; that correlations among them can be largely cancelled by balancing excitation and inhibition; that neural populations can act as integrators; and that the objective of timed behavior is maximal accuracy and minimal variance. The model accounts for a variety of physiological and behavioral findings in rodents, monkeys and humans, including ramping firing rates between the onset of reward-predicting cues and the receipt of delayed rewards, and universally scale-invariant response time distributions in interval timing tasks. It furthermore makes specific, well-supported predictions about the skewness of these distributions, a feature of timing data that is usually ignored. The model also incorporates a rapid (potentially one-shot) duration-learning procedure. Human behavioral data support the learning rule’s predictions regarding learning speed in sequences of timed responses. These results suggest that simple, integration-based models should play as prominent a role in interval timing theory as they do in theories of perceptual decision making, and that a common neural mechanism may underlie both types of behavior. PMID:21697374

Cnidarian Nerve Nets and Neuromuscular Efficiency.

PubMed

Satterlie, Richard A

2015-12-01

Cnidarians are considered "nerve net animals" even though their nervous systems include various forms of condensation and centralization. Yet, their broad, two-dimensional muscle sheets are innervated by diffuse nerve nets. Do the motor nerve nets represent a primitive organization of multicellular nervous systems, do they represent a consequence of radial symmetry, or do they offer an efficient way to innervate a broad, two-dimensional muscle sheet, in which excitation of the muscle sheet can come from multiple sites of initiation? Regarding the primitive nature of cnidarian nervous systems, distinct neuronal systems exhibit some adaptations that are well known in higher animals, such as the use of oversized neurons with increased speed of conduction, and condensation of neurites into nerve-like tracts. A comparison of neural control of two-dimensional muscle sheets in a mollusc and jellyfish suggests that a possible primitive feature of cnidarian neurons may be a lack of regional specialization into conducting and transmitting regions. © The Author 2015. Published by Oxford University Press on behalf of the Society for Integrative and Comparative Biology. All rights reserved. For permissions please email: journals.permissions@oup.com.

Efficient convex-elastic net algorithm to solve the Euclidean traveling salesman problem.

PubMed

Al-Mulhem, M; Al-Maghrabi, T

1998-01-01

This paper describes a hybrid algorithm that combines an adaptive-type neural network algorithm and a nondeterministic iterative algorithm to solve the Euclidean traveling salesman problem (E-TSP). It begins with a brief introduction to the TSP and the E-TSP. Then, it presents the proposed algorithm with its two major components: the convex-elastic net (CEN) algorithm and the nondeterministic iterative improvement (NII) algorithm. These two algorithms are combined into the efficient convex-elastic net (ECEN) algorithm. The CEN algorithm integrates the convex-hull property and elastic net algorithm to generate an initial tour for the E-TSP. The NII algorithm uses two rearrangement operators to improve the initial tour given by the CEN algorithm. The paper presents simulation results for two instances of E-TSP: randomly generated tours and tours for well-known problems in the literature. Experimental results are given to show that the proposed algorithm ran find the nearly optimal solution for the E-TSP that outperform many similar algorithms reported in the literature. The paper concludes with the advantages of the new algorithm and possible extensions.

Alteration of neural action potential patterns by axonal stimulation: the importance of stimulus location.

PubMed

Crago, Patrick E; Makowski, Nathaniel S

2014-10-01

Stimulation of peripheral nerves is often superimposed on ongoing motor and sensory activity in the same axons, without a quantitative model of the net action potential train at the axon endpoint. We develop a model of action potential patterns elicited by superimposing constant frequency axonal stimulation on the action potentials arriving from a physiologically activated neural source. The model includes interactions due to collision block, resetting of the neural impulse generator, and the refractory period of the axon at the point of stimulation. Both the mean endpoint firing rate and the probability distribution of the action potential firing periods depend strongly on the relative firing rates of the two sources and the intersite conduction time between them. When the stimulus rate exceeds the neural rate, neural action potentials do not reach the endpoint and the rate of endpoint action potentials is the same as the stimulus rate, regardless of the intersite conduction time. However, when the stimulus rate is less than the neural rate, and the intersite conduction time is short, the two rates partially sum. Increases in stimulus rate produce non-monotonic increases in endpoint rate and continuously increasing block of neurally generated action potentials. Rate summation is reduced and more neural action potentials are blocked as the intersite conduction time increases. At long intersite conduction times, the endpoint rate simplifies to being the maximum of either the neural or the stimulus rate. This study highlights the potential of increasing the endpoint action potential rate and preserving neural information transmission by low rate stimulation with short intersite conduction times. Intersite conduction times can be decreased with proximal stimulation sites for muscles and distal stimulation sites for sensory endings. The model provides a basis for optimizing experiments and designing neuroprosthetic interventions involving motor or sensory stimulation.

Reconstitution of a Patterned Neural Tube from Single Mouse Embryonic Stem Cells.

PubMed

Ishihara, Keisuke; Ranga, Adrian; Lutolf, Matthias P; Tanaka, Elly M; Meinhardt, Andrea

2017-01-01

The recapitulation of tissue development and patterning in three-dimensional (3D) culture is an important dimension of stem cell research. Here, we describe a 3D culture protocol in which single mouse ES cells embedded in Matrigel under neural induction conditions clonally form a lumen containing, oval-shaped epithelial structure within 3 days. By Day 7 an apicobasally polarized neuroepithelium with uniformly dorsal cell identity forms. Treatment with retinoic acid at Day 2 results in posteriorization and self-organization of dorsal-ventral neural tube patterning. Neural tube organoid growth is also supported by pure laminin gels as well as poly(ethylene glycol) (PEG)-based artificial extracellular matrix hydrogels, which can be fine-tuned for key microenvironment characteristics. The rapid generation of a simple, patterned tissue in well-defined culture conditions makes the neural tube organoid a tractable model for studying neural stem cell self-organization.

Carbon nanotubes in neural interfacing applications

NASA Astrophysics Data System (ADS)

Voge, Christopher M.; Stegemann, Jan P.

2011-02-01

Carbon nanotubes (CNT) are remarkable materials with a simple and inert molecular structure that gives rise to a range of potentially valuable physical and electronic properties, including high aspect ratio, high mechanical strength and excellent electrical conductivity. This review summarizes recent research on the application of CNT-based materials to study and control cells of the nervous system. It includes the use of CNT as cell culture substrates, to create patterned surfaces and to study cell-matrix interactions. It also summarizes recent investigations of CNT toxicity, particularly as related to neural cells. The application of CNT-based materials to directing the differentiation of progenitor and stem cells toward neural lineages is also discussed. The emphasis is on how CNT surface chemistry and nanotopography can be altered, and how such changes can affect neural cell function. This knowledge can be applied to creating improved neural interfaces and devices, as well as providing new approaches to neural tissue engineering and regeneration.

Functional network in posttranslational modifications: Glyco-Net in Glycoconjugate Data Bank.

PubMed

Miura, Nobuaki; Okada, Takuya; Murayama, Daisuke; Hirose, Kazuko; Sato, Taku; Hashimoto, Ryo; Fukushima, Nobuhiro

2015-01-01

Elucidating pathways related to posttranslational modifications (PTMs) such as glycosylation is of growing importance in post-genome science and technology. Graphical networks describing the relationships among glycan-related molecules, including genes, proteins, lipids, and various biological events, are considered extremely valuable and convenient tools for the systematic investigation of PTMs. Glyco-Net (http://bibi.sci.hokudai.ac.jp/functions/) can dynamically make network figures among various biological molecules and biological events. A certain molecule or event is expressed with a node, and the relationship between the molecule and the event is indicated by arrows in the network figures. In this chapter, we mention the features and current status of the Glyco-Net and a simple example of the search with the Glyco-Net.

Automated selection of computed tomography display parameters using neural networks

NASA Astrophysics Data System (ADS)

Zhang, Di; Neu, Scott; Valentino, Daniel J.

2001-07-01

A collection of artificial neural networks (ANN's) was trained to identify simple anatomical structures in a set of x-ray computed tomography (CT) images. These neural networks learned to associate a point in an image with the anatomical structure containing the point by using the image pixels located on the horizontal and vertical lines that ran through the point. The neural networks were integrated into a computer software tool whose function is to select an index into a list of CT window/level values from the location of the user's mouse cursor. Based upon the anatomical structure selected by the user, the software tool automatically adjusts the image display to optimally view the structure.

Hidden Markov models and neural networks for fault detection in dynamic systems

NASA Technical Reports Server (NTRS)

Smyth, Padhraic

1994-01-01

Neural networks plus hidden Markov models (HMM) can provide excellent detection and false alarm rate performance in fault detection applications, as shown in this viewgraph presentation. Modified models allow for novelty detection. Key contributions of neural network models are: (1) excellent nonparametric discrimination capability; (2) a good estimator of posterior state probabilities, even in high dimensions, and thus can be embedded within overall probabilistic model (HMM); and (3) simple to implement compared to other nonparametric models. Neural network/HMM monitoring model is currently being integrated with the new Deep Space Network (DSN) antenna controller software and will be on-line monitoring a new DSN 34-m antenna (DSS-24) by July, 1994.

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.

Audio Classification in Speech and Music: A Comparison between a Statistical and a Neural Approach

NASA Astrophysics Data System (ADS)

Bugatti, Alessandro; Flammini, Alessandra; Migliorati, Pierangelo

2002-12-01

We focus the attention on the problem of audio classification in speech and music for multimedia applications. In particular, we present a comparison between two different techniques for speech/music discrimination. The first method is based on Zero crossing rate and Bayesian classification. It is very simple from a computational point of view, and gives good results in case of pure music or speech. The simulation results show that some performance degradation arises when the music segment contains also some speech superimposed on music, or strong rhythmic components. To overcome these problems, we propose a second method, that uses more features, and is based on neural networks (specifically a multi-layer Perceptron). In this case we obtain better performance, at the expense of a limited growth in the computational complexity. In practice, the proposed neural network is simple to be implemented if a suitable polynomial is used as the activation function, and a real-time implementation is possible even if low-cost embedded systems are used.

Fitting Neuron Models to Spike Trains

PubMed Central

Rossant, Cyrille; Goodman, Dan F. M.; Fontaine, Bertrand; Platkiewicz, Jonathan; Magnusson, Anna K.; Brette, Romain

2011-01-01

Computational modeling is increasingly used to understand the function of neural circuits in systems neuroscience. These studies require models of individual neurons with realistic input–output properties. Recently, it was found that spiking models can accurately predict the precisely timed spike trains produced by cortical neurons in response to somatically injected currents, if properly fitted. This requires fitting techniques that are efficient and flexible enough to easily test different candidate models. We present a generic solution, based on the Brian simulator (a neural network simulator in Python), which allows the user to define and fit arbitrary neuron models to electrophysiological recordings. It relies on vectorization and parallel computing techniques to achieve efficiency. We demonstrate its use on neural recordings in the barrel cortex and in the auditory brainstem, and confirm that simple adaptive spiking models can accurately predict the response of cortical neurons. Finally, we show how a complex multicompartmental model can be reduced to a simple effective spiking model. PMID:21415925

The brainstem reticular formation is a small-world, not scale-free, network

PubMed Central

Humphries, M.D; Gurney, K; Prescott, T.J

2005-01-01

Recently, it has been demonstrated that several complex systems may have simple graph-theoretic characterizations as so-called ‘small-world’ and ‘scale-free’ networks. These networks have also been applied to the gross neural connectivity between primate cortical areas and the nervous system of Caenorhabditis elegans. Here, we extend this work to a specific neural circuit of the vertebrate brain—the medial reticular formation (RF) of the brainstem—and, in doing so, we have made three key contributions. First, this work constitutes the first model (and quantitative review) of this important brain structure for over three decades. Second, we have developed the first graph-theoretic analysis of vertebrate brain connectivity at the neural network level. Third, we propose simple metrics to quantitatively assess the extent to which the networks studied are small-world or scale-free. We conclude that the medial RF is configured to create small-world (implying coherent rapid-processing capabilities), but not scale-free, type networks under assumptions which are amenable to quantitative measurement. PMID:16615219

Learning in a Simple Motor System

ERIC Educational Resources Information Center

Broussard, Dianne M.; Kassardjian, Charles D.

2004-01-01

Motor learning is a very basic, essential form of learning that appears to share common mechanisms across different motor systems. We evaluate and compare a few conceptual models for learning in a relatively simple neural system, the vestibulo-ocular reflex (VOR) of vertebrates. We also compare the different animal models that have been used to…

Automatic lesion detection and segmentation of 18F-FET PET in gliomas: A full 3D U-Net convolutional neural network study.

PubMed

Blanc-Durand, Paul; Van Der Gucht, Axel; Schaefer, Niklaus; Itti, Emmanuel; Prior, John O

2018-01-01

Amino-acids positron emission tomography (PET) is increasingly used in the diagnostic workup of patients with gliomas, including differential diagnosis, evaluation of tumor extension, treatment planning and follow-up. Recently, progresses of computer vision and machine learning have been translated for medical imaging. Aim was to demonstrate the feasibility of an automated 18F-fluoro-ethyl-tyrosine (18F-FET) PET lesion detection and segmentation relying on a full 3D U-Net Convolutional Neural Network (CNN). All dynamic 18F-FET PET brain image volumes were temporally realigned to the first dynamic acquisition, coregistered and spatially normalized onto the Montreal Neurological Institute template. Ground truth segmentations were obtained using manual delineation and thresholding (1.3 x background). The volumetric CNN was implemented based on a modified Keras implementation of a U-Net library with 3 layers for the encoding and decoding paths. Dice similarity coefficient (DSC) was used as an accuracy measure of segmentation. Thirty-seven patients were included (26 [70%] in the training set and 11 [30%] in the validation set). All 11 lesions were accurately detected with no false positive, resulting in a sensitivity and a specificity for the detection at the tumor level of 100%. After 150 epochs, DSC reached 0.7924 in the training set and 0.7911 in the validation set. After morphological dilatation and fixed thresholding of the predicted U-Net mask a substantial improvement of the DSC to 0.8231 (+ 4.1%) was noted. At the voxel level, this segmentation led to a 0.88 sensitivity [95% CI, 87.1 to, 88.2%] a 0.99 specificity [99.9 to 99.9%], a 0.78 positive predictive value: [76.9 to 78.3%], and a 0.99 negative predictive value [99.9 to 99.9%]. With relatively high performance, it was proposed the first full 3D automated procedure for segmentation of 18F-FET PET brain images of patients with different gliomas using a U-Net CNN architecture.

Illuminating Tradespace Decisions Using Efficient Experimental Space-Filling Designs for the Engineered Resilient System Architecture

DTIC Science & Technology

2015-06-30

7. Building Statistical Metamodels using Simulation Experimental Designs ............................................... 34 7.1. Statistical Design...system design drivers across several different domain models, our methodology uses statistical metamodeling to approximate the simulations’ behavior. A...output. We build metamodels using a number of statistical methods that include stepwise regression, boosted trees, neural nets, and bootstrap forest

Illuminating Tradespace Decisions Using Efficient Experimental Space-Filling Designs for the Engineered Resilient System Architecture

DTIC Science & Technology

2015-06-01

7. Building Statistical Metamodels using Simulation Experimental Designs ............................................... 34 7.1. Statistical Design...system design drivers across several different domain models, our methodology uses statistical metamodeling to approximate the simulations’ behavior. A...output. We build metamodels using a number of statistical methods that include stepwise regression, boosted trees, neural nets, and bootstrap forest

A Comparison of Rule-Based, K-Nearest Neighbor, and Neural Net Classifiers for Automated

Treesearch

Tai-Hoon Cho; Richard W. Conners; Philip A. Araman

1991-01-01

Over the last few years the authors have been involved in research aimed at developing a machine vision system for locating and identifying surface defects on materials. The particular problem being studied involves locating surface defects on hardwood lumber in a species independent manner. Obviously, the accurate location and identification of defects is of paramount...

Statistical Neurodynamics.

NASA Astrophysics Data System (ADS)

Paine, Gregory Harold

1982-03-01

The primary objective of the thesis is to explore the dynamical properties of small nerve networks by means of the methods of statistical mechanics. To this end, a general formalism is developed and applied to elementary groupings of model neurons which are driven by either constant (steady state) or nonconstant (nonsteady state) forces. Neuronal models described by a system of coupled, nonlinear, first-order, ordinary differential equations are considered. A linearized form of the neuronal equations is studied in detail. A Lagrange function corresponding to the linear neural network is constructed which, through a Legendre transformation, provides a constant of motion. By invoking the Maximum-Entropy Principle with the single integral of motion as a constraint, a probability distribution function for the network in a steady state can be obtained. The formalism is implemented for some simple networks driven by a constant force; accordingly, the analysis focuses on a study of fluctuations about the steady state. In particular, a network composed of N noninteracting neurons, termed Free Thinkers, is considered in detail, with a view to interpretation and numerical estimation of the Lagrange multiplier corresponding to the constant of motion. As an archetypical example of a net of interacting neurons, the classical neural oscillator, consisting of two mutually inhibitory neurons, is investigated. It is further shown that in the case of a network driven by a nonconstant force, the Maximum-Entropy Principle can be applied to determine a probability distribution functional describing the network in a nonsteady state. The above examples are reconsidered with nonconstant driving forces which produce small deviations from the steady state. Numerical studies are performed on simplified models of two physical systems: the starfish central nervous system and the mammalian olfactory bulb. Discussions are given as to how statistical neurodynamics can be used to gain a better understanding of the behavior of these systems.

Beyond the central pattern generator: amine modulation of decision-making neural pathways descending from the brain of the medicinal leech.

PubMed

Crisp, Kevin M; Mesce, Karen A

2006-05-01

The biological mechanisms of behavioral selection, as it relates to locomotion, are far from understood, even in relatively simple invertebrate animals. In the medicinal leech, Hirudo medicinalis, the decision to swim is distributed across populations of swim-activating and swim-inactivating neurons descending from the subesophageal ganglion of the compound cephalic ganglion, i.e. the brain. In the present study, we demonstrate that the serotonergic LL and Retzius cells in the brain are excited by swim-initiating stimuli and during spontaneous swim episodes. This activity likely influences or resets the neuromodulatory state of neural circuits involved in the activation or subsequent termination of locomotion. When serotonin (5-HT) was perfused over the brain, multi-unit recordings from descending brain neurons revealed rapid and substantial alterations. Subsequent intracellular recordings from identified command-like brain interneurons demonstrated that 5-HT, especially in combination with octopamine, inhibited swim-triggering neuron Tr1, as well as swim-inactivating neurons Tr2 and SIN1. Although 5-HT inhibited elements of the swim-inactivation pathway, rather than promoting them, the indirect and net effect of the amine was a reliable and sustained reduction in the firing of the segmental swim-gating neuron 204. This modulation caused cell 204 to relinquish its excitatory drive to the swim central pattern generator. The activation pattern of serotonergic brain neurons that we observed during swimming and the 5-HT-immunoreactive staining pattern obtained, suggest that within the head brain 5-HT secretion is massive. Over time, 5-HT secretion may provide a homeostatic feedback mechanism to limit swimming activity at the level of the head brain.

Biologically Plausible, Human-Scale Knowledge Representation.

PubMed

Crawford, Eric; Gingerich, Matthew; Eliasmith, Chris

2016-05-01

Several approaches to implementing symbol-like representations in neurally plausible models have been proposed. These approaches include binding through synchrony (Shastri & Ajjanagadde, ), "mesh" binding (van der Velde & de Kamps, ), and conjunctive binding (Smolensky, ). Recent theoretical work has suggested that most of these methods will not scale well, that is, that they cannot encode structured representations using any of the tens of thousands of terms in the adult lexicon without making implausible resource assumptions. Here, we empirically demonstrate that the biologically plausible structured representations employed in the Semantic Pointer Architecture (SPA) approach to modeling cognition (Eliasmith, ) do scale appropriately. Specifically, we construct a spiking neural network of about 2.5 million neurons that employs semantic pointers to successfully encode and decode the main lexical relations in WordNet, which has over 100,000 terms. In addition, we show that the same representations can be employed to construct recursively structured sentences consisting of arbitrary WordNet concepts, while preserving the original lexical structure. We argue that these results suggest that semantic pointers are uniquely well-suited to providing a biologically plausible account of the structured representations that underwrite human cognition. Copyright © 2015 Cognitive Science Society, Inc.