The EB factory project. I. A fast, neural-net-based, general purpose light curve classifier optimized for eclipsing binaries

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

Paegert, Martin; Stassun, Keivan G.; Burger, Dan M.

2014-08-01

We describe a new neural-net-based light curve classifier and provide it with documentation as a ready-to-use tool for the community. While optimized for identification and classification of eclipsing binary stars, the classifier is general purpose, and has been developed for speed in the context of upcoming massive surveys such as the Large Synoptic Survey Telescope. A challenge for classifiers in the context of neural-net training and massive data sets is to minimize the number of parameters required to describe each light curve. We show that a simple and fast geometric representation that encodes the overall light curve shape, together withmore » a chi-square parameter to capture higher-order morphology information results in efficient yet robust light curve classification, especially for eclipsing binaries. Testing the classifier on the ASAS light curve database, we achieve a retrieval rate of 98% and a false-positive rate of 2% for eclipsing binaries. We achieve similarly high retrieval rates for most other periodic variable-star classes, including RR Lyrae, Mira, and delta Scuti. However, the classifier currently has difficulty discriminating between different sub-classes of eclipsing binaries, and suffers a relatively low (∼60%) retrieval rate for multi-mode delta Cepheid stars. We find that it is imperative to train the classifier's neural network with exemplars that include the full range of light curve quality to which the classifier will be expected to perform; the classifier performs well on noisy light curves only when trained with noisy exemplars. The classifier source code, ancillary programs, a trained neural net, and a guide for use, are provided.« less

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.

High-Lift Optimization Design Using Neural Networks on a Multi-Element Airfoil

NASA Technical Reports Server (NTRS)

Greenman, Roxana M.; Roth, Karlin R.; Smith, Charles A. (Technical Monitor)

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. 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 networks 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 83% compared with traditional gradient-based optimization procedures for multiple optimization runs.

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.

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.

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.

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.

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 mixture neural net for multispectral imaging spectrometer processing

NASA Technical Reports Server (NTRS)

Casasent, David; Slagle, Timothy

1990-01-01

Each spatial region viewed by an imaging spectrometer contains various elements in a mixture. The elements present and the amount of each are to be determined. A neural net solution is considered. Initial optical neural net hardware is described. The first simulations on the component requirements of a neural net are considered. The pseudoinverse solution is shown to not suffice, i.e. a neural net solution is required.

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.

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.

Constructivism, Optimality Theory and Language Acquisition. The Shapes We Make in Each Other's Heads.

ERIC Educational Resources Information Center

Whincop, Chris

1996-01-01

This paper identifies a feature of human brain neural nets that may be described as the principle of ease of processing (PEP), and that, it is argued, is the primary force guiding a learner towards a target grammar. It is suggested that the same principle lies at the heart of Optimality Theory, which characterizes the course of language…

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

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

AIAA/USAF/NASA/OAI Symposium on Multidisciplinary Analysis and Optimization, 4th, Cleveland, OH, Sept. 21-23, 1992, Technical Papers. Pts. 1 & 2

NASA Technical Reports Server (NTRS)

1992-01-01

The papers presented at the symposium cover aerodynamics, design applications, propulsion systems, high-speed flight, structures, controls, sensitivity analysis, optimization algorithms, and space structures applications. Other topics include helicopter rotor design, artificial intelligence/neural nets, and computational aspects of optimization. Papers are included on flutter calculations for a system with interacting nonlinearities, optimization in solid rocket booster application, improving the efficiency of aerodynamic shape optimization procedures, nonlinear control theory, and probabilistic structural analysis of space truss structures for nonuniform thermal environmental effects.

HYBRID NEURAL NETWORK AND SUPPORT VECTOR MACHINE METHOD FOR OPTIMIZATION

NASA Technical Reports Server (NTRS)

Rai, Man Mohan (Inventor)

2005-01-01

System and method for optimization of a design associated with a response function, using a hybrid neural net and support vector machine (NN/SVM) analysis to minimize or maximize an objective function, optionally subject to one or more constraints. As a first example, the NN/SVM analysis is applied iteratively to design of an aerodynamic component, such as an airfoil shape, where the objective function measures deviation from a target pressure distribution on the perimeter of the aerodynamic component. As a second example, the NN/SVM analysis is applied to data classification of a sequence of data points in a multidimensional space. The NN/SVM analysis is also applied to data regression.

Hybrid Neural Network and Support Vector Machine Method for Optimization

NASA Technical Reports Server (NTRS)

Rai, Man Mohan (Inventor)

2007-01-01

System and method for optimization of a design associated with a response function, using a hybrid neural net and support vector machine (NN/SVM) analysis to minimize or maximize an objective function, optionally subject to one or more constraints. As a first example, the NN/SVM analysis is applied iteratively to design of an aerodynamic component, such as an airfoil shape, where the objective function measures deviation from a target pressure distribution on the perimeter of the aerodynamic component. As a second example, the NN/SVM analysis is applied to data classification of a sequence of data points in a multidimensional space. The NN/SVM analysis is also applied to data regression.

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.

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.

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.

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.

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.

Proto-experiences and subjective experiences: classical and quantum concepts.

PubMed

Vimal, Ram Lakhan Pandey

2008-03-01

Deterministic reductive monism and non-reductive substance dualism are two opposite views for consciousness, and both have serious problems. An alternative view is needed. For this, we hypothesize that strings or elementary particles (fermions and bosons) have two aspects: (i) elemental proto-experiences (PEs) as phenomenal aspect, and (ii) mass, charge, and spin as material aspect. Elemental PEs are hypothesized to be the properties of elementary particles and their interactions, which are composed of irreducible fundamental subjective experiences (SEs)/PEs that are in superimposed form in elementary particles and in their interactions. Since SEs/PEs are superimposed, elementary particles are not specific to any SE/PE; they (and all inert matter) are carriers of SEs/PEs, and hence, appear as non-experiential material entities. Furthermore, our hypothesis is that matter and associated elemental PEs co-evolved and co-developed into neural-nets and associated neural-net PEs (neural Darminism), respectively. The signals related to neural PEs interact in a neural-net and neural-net PEs emerges from random process of self-organization. The neural-net PEs are a set of SEs embedded in the neural-net by a non-computational or non-algorithmic process. The non-specificity of elementary particles is transformed into the specificity of neural-nets by neural Darwinism. The specificity of SEs emerges when feedforward and feedback signal interacts in the neuropil and are dependent on wakefulness (i.e., activation) attention, re-entry between neural populations, working memory, stimulus at above threshold, and neural net PE signals. This PE-SE framework integrates reductive and non-reductive views, complements the existing models, bridges the explanatory gaps, and minimizes the problem of causation.

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.

Neural nets on the MPP

NASA Technical Reports Server (NTRS)

Hastings, Harold M.; Waner, Stefan

1987-01-01

The Massively Parallel Processor (MPP) is an ideal machine for computer experiments with simulated neural nets as well as more general cellular automata. Experiments using the MPP with a formal model neural network are described. The results on problem mapping and computational efficiency apply equally well to the neural nets of Hopfield, Hinton et al., and Geman and Geman.

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.

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 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.

A neural network approach to job-shop scheduling.

PubMed

Zhou, D N; Cherkassky, V; Baldwin, T R; Olson, D E

1991-01-01

A novel analog computational network is presented for solving NP-complete constraint satisfaction problems, i.e. job-shop scheduling. In contrast to most neural approaches to combinatorial optimization based on quadratic energy cost function, the authors propose to use linear cost functions. As a result, the network complexity (number of neurons and the number of resistive interconnections) grows only linearly with problem size, and large-scale implementations become possible. The proposed approach is related to the linear programming network described by D.W. Tank and J.J. Hopfield (1985), which also uses a linear cost function for a simple optimization problem. It is shown how to map a difficult constraint-satisfaction problem onto a simple neural net in which the number of neural processors equals the number of subjobs (operations) and the number of interconnections grows linearly with the total number of operations. Simulations show that the authors' approach produces better solutions than existing neural approaches to job-shop scheduling, i.e. the traveling salesman problem-type Hopfield approach and integer linear programming approach of J.P.S. Foo and Y. Takefuji (1988), in terms of the quality of the solution and the network complexity.

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.

Stability Training for Convolutional Neural Nets in LArTPC

NASA Astrophysics Data System (ADS)

Lindsay, Matt; Wongjirad, Taritree

2017-01-01

Convolutional Neural Nets (CNNs) are the state of the art for many problems in computer vision and are a promising method for classifying interactions in Liquid Argon Time Projection Chambers (LArTPCs) used in neutrino oscillation experiments. Despite the good performance of CNN's, they are not without drawbacks, chief among them is vulnerability to noise and small perturbations to the input. One solution to this problem is a modification to the learning process called Stability Training developed by Zheng et al. We verify existing work and demonstrate volatility caused by simple Gaussian noise and also that the volatility can be nearly eliminated with Stability Training. We then go further and show that a traditional CNN is also vulnerable to realistic experimental noise and that a stability trained CNN remains accurate despite noise. This further adds to the optimism for CNNs for work in LArTPCs and other applications.

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.

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

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.

Image Halftoning Using Optimized Dot Diffusion

DTIC Science & Technology

1998-01-01

ppvnath@sys.caltech.edu ABSTRACT The dot diffusion method for digital halftoning has the advantage of parallelism unlike the error diffusion ...digital halftoning : ordered dither [1], error diffusion [2], neural-net based methods [8], and more recently direct binary search (DBS) [7]. Ordered...from periodic patterns. On the other hand error diffused halftones do not suffer from periodicity and offer blue noise characteristic [3] which is

Integrated Sensing Processor, Phase 2

DTIC Science & Technology

2005-12-01

performance analysis for several baseline classifiers including neural nets, linear classifiers, and kNN classifiers. Use of CCDR as a preprocessing step...below the level of the benchmark non-linear classifier for this problem ( kNN ). Furthermore, the CCDR preconditioned kNN achieved a 10% improvement over...the benchmark kNN without CCDR. Finally, we found an important connection between intrinsic dimension estimation via entropic graphs and the optimal

A novel constructive-optimizer neural network for the traveling salesman problem.

PubMed

Saadatmand-Tarzjan, Mahdi; Khademi, Morteza; Akbarzadeh-T, Mohammad-R; Moghaddam, Hamid Abrishami

2007-08-01

In this paper, a novel constructive-optimizer neural network (CONN) is proposed for the traveling salesman problem (TSP). CONN uses a feedback structure similar to Hopfield-type neural networks and a competitive training algorithm similar to the Kohonen-type self-organizing maps (K-SOMs). Consequently, CONN is composed of a constructive part, which grows the tour and an optimizer part to optimize it. In the training algorithm, an initial tour is created first and introduced to CONN. Then, it is trained in the constructive phase for adding a number of cities to the tour. Next, the training algorithm switches to the optimizer phase for optimizing the current tour by displacing the tour cities. After convergence in this phase, the training algorithm switches to the constructive phase anew and is continued until all cities are added to the tour. Furthermore, we investigate a relationship between the number of TSP cities and the number of cities to be added in each constructive phase. CONN was tested on nine sets of benchmark TSPs from TSPLIB to demonstrate its performance and efficiency. It performed better than several typical Neural networks (NNs), including KNIES_TSP_Local, KNIES_TSP_Global, Budinich's SOM, Co-Adaptive Net, and multivalued Hopfield network as wall as computationally comparable variants of the simulated annealing algorithm, in terms of both CPU time and accuracy. Furthermore, CONN converged considerably faster than expanding SOM and evolved integrated SOM and generated shorter tours compared to KNIES_DECOMPOSE. Although CONN is not yet comparable in terms of accuracy with some sophisticated computationally intensive algorithms, it converges significantly faster than they do. Generally speaking, CONN provides the best compromise between CPU time and accuracy among currently reported NNs for TSP.

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.

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.

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

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.

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.

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.

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.

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

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.

Character Recognition Using Genetically Trained Neural Networks

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

Diniz, C.; Stantz, K.M.; Trahan, M.W.

1998-10-01

Computationally intelligent recognition of characters and symbols addresses a wide range of applications including foreign language translation and chemical formula identification. The combination of intelligent learning and optimization algorithms with layered neural structures offers powerful techniques for character recognition. These techniques were originally developed by Sandia National Laboratories for pattern and spectral analysis; however, their ability to optimize vast amounts of data make them ideal for character recognition. An adaptation of the Neural Network Designer soflsvare allows the user to create a neural network (NN_) trained by a genetic algorithm (GA) that correctly identifies multiple distinct characters. The initial successfidmore » recognition of standard capital letters can be expanded to include chemical and mathematical symbols and alphabets of foreign languages, especially Arabic and Chinese. The FIN model constructed for this project uses a three layer feed-forward architecture. To facilitate the input of characters and symbols, a graphic user interface (GUI) has been developed to convert the traditional representation of each character or symbol to a bitmap. The 8 x 8 bitmap representations used for these tests are mapped onto the input nodes of the feed-forward neural network (FFNN) in a one-to-one correspondence. The input nodes feed forward into a hidden layer, and the hidden layer feeds into five output nodes correlated to possible character outcomes. During the training period the GA optimizes the weights of the NN until it can successfully recognize distinct characters. Systematic deviations from the base design test the network's range of applicability. Increasing capacity, the number of letters to be recognized, requires a nonlinear increase in the number of hidden layer neurodes. Optimal character recognition performance necessitates a minimum threshold for the number of cases when genetically training the net. And, the amount of noise significantly degrades character recognition efficiency, some of which can be overcome by adding noise during training and optimizing the form of the network's activation fimction.« less

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.

Image Halftoning and Inverse Halftoning for Optimized Dot Diffusion

DTIC Science & Technology

1998-01-01

systems.caltech.edu, ppvnath@sys.caltech.edu ABSTRACT The dot diffusion method for digital halftoning has the advantage of parallelism unlike the error ... halftoning : ordered dither [3], error diffusion [4], neural-net based methods [2], and more recently direct binary search (DBS) [10]. Ordered dithering is a...patterns. On the other hand error diffused halftones do not suffer from periodicity and offer blue noise characteristic [11] which is found to be

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.

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.

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.

A Globally Optimal Particle Tracking Technique for Stereo Imaging Velocimetry Experiments

NASA Technical Reports Server (NTRS)

McDowell, Mark

2008-01-01

An important phase of any Stereo Imaging Velocimetry experiment is particle tracking. Particle tracking seeks to identify and characterize the motion of individual particles entrained in a fluid or air experiment. We analyze a cylindrical chamber filled with water and seeded with density-matched particles. In every four-frame sequence, we identify a particle track by assigning a unique track label for each camera image. The conventional approach to particle tracking is to use an exhaustive tree-search method utilizing greedy algorithms to reduce search times. However, these types of algorithms are not optimal due to a cascade effect of incorrect decisions upon adjacent tracks. We examine the use of a guided evolutionary neural net with simulated annealing to arrive at a globally optimal assignment of tracks. The net is guided both by the minimization of the search space through the use of prior limiting assumptions about valid tracks and by a strategy which seeks to avoid high-energy intermediate states which can trap the net in a local minimum. A stochastic search algorithm is used in place of back-propagation of error to further reduce the chance of being trapped in an energy well. Global optimization is achieved by minimizing an objective function, which includes both track smoothness and particle-image utilization parameters. In this paper we describe our model and present our experimental results. We compare our results with a nonoptimizing, predictive tracker and obtain an average increase in valid track yield of 27 percent

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.

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.

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).

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 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.

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.

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.

A biologically inspired neural net for trajectory formation and obstacle avoidance.

PubMed

Glasius, R; Komoda, A; Gielen, S C

1996-06-01

In this paper we present a biologically inspired two-layered neural network for trajectory formation and obstacle avoidance. The two topographically ordered neural maps consist of analog neurons having continuous dynamics. The first layer, the sensory map, receives sensory information and builds up an activity pattern which contains the optimal solution (i.e. shortest path without collisions) for any given set of current position, target positions and obstacle positions. Targets and obstacles are allowed to move, in which case the activity pattern in the sensory map will change accordingly. The time evolution of the neural activity in the second layer, the motor map, results in a moving cluster of activity, which can be interpreted as a population vector. Through the feedforward connections between the two layers, input of the sensory map directs the movement of the cluster along the optimal path from the current position of the cluster to the target position. The smooth trajectory is the result of the intrinsic dynamics of the network only. No supervisor is required. The output of the motor map can be used for direct control of an autonomous system in a cluttered environment or for control of the actuators of a biological limb or robot manipulator. The system is able to reach a target even in the presence of an external perturbation. Computer simulations of a point robot and a multi-joint manipulator illustrate the theory.

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.

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.

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.

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.

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.

Nonlinear identification using a B-spline neural network and chaotic immune approaches

NASA Astrophysics Data System (ADS)

dos Santos Coelho, Leandro; Pessôa, Marcelo Wicthoff

2009-11-01

One of the important applications of B-spline neural network (BSNN) is to approximate nonlinear functions defined on a compact subset of a Euclidean space in a highly parallel manner. Recently, BSNN, a type of basis function neural network, has received increasing attention and has been applied in the field of nonlinear identification. BSNNs have the potential to "learn" the process model from input-output data or "learn" fault knowledge from past experience. BSNN can be used as function approximators to construct the analytical model for residual generation too. However, BSNN is trained by gradient-based methods that may fall into local minima during the learning procedure. When using feed-forward BSNNs, the quality of approximation depends on the control points (knots) placement of spline functions. This paper describes the application of a modified artificial immune network inspired optimization method - the opt-aiNet - combined with sequences generate by Hénon map to provide a stochastic search to adjust the control points of a BSNN. The numerical results presented here indicate that artificial immune network optimization methods are useful for building good BSNN model for the nonlinear identification of two case studies: (i) the benchmark of Box and Jenkins gas furnace, and (ii) an experimental ball-and-tube system.

Automated Detection of Clinically Significant Prostate Cancer in mp-MRI Images Based on an End-to-End Deep Neural Network.

PubMed

Wang, Zhiwei; Liu, Chaoyue; Cheng, Danpeng; Wang, Liang; Yang, Xin; Cheng, Kwang-Ting

2018-05-01

Automated methods for detecting clinically significant (CS) prostate cancer (PCa) in multi-parameter magnetic resonance images (mp-MRI) are of high demand. Existing methods typically employ several separate steps, each of which is optimized individually without considering the error tolerance of other steps. As a result, they could either involve unnecessary computational cost or suffer from errors accumulated over steps. In this paper, we present an automated CS PCa detection system, where all steps are optimized jointly in an end-to-end trainable deep neural network. The proposed neural network consists of concatenated subnets: 1) a novel tissue deformation network (TDN) for automated prostate detection and multimodal registration and 2) a dual-path convolutional neural network (CNN) for CS PCa detection. Three types of loss functions, i.e., classification loss, inconsistency loss, and overlap loss, are employed for optimizing all parameters of the proposed TDN and CNN. In the training phase, the two nets mutually affect each other and effectively guide registration and extraction of representative CS PCa-relevant features to achieve results with sufficient accuracy. The entire network is trained in a weakly supervised manner by providing only image-level annotations (i.e., presence/absence of PCa) without exact priors of lesions' locations. Compared with most existing systems which require supervised labels, e.g., manual delineation of PCa lesions, it is much more convenient for clinical usage. Comprehensive evaluation based on fivefold cross validation using 360 patient data demonstrates that our system achieves a high accuracy for CS PCa detection, i.e., a sensitivity of 0.6374 and 0.8978 at 0.1 and 1 false positives per normal/benign patient.

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.

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.

Optimal Spatial Design of Capacity and Quantity of Rainwater Catchment Systems for Urban Flood Mitigation

NASA Astrophysics Data System (ADS)

Huang, C.; Hsu, N.

2013-12-01

This study imports Low-Impact Development (LID) technology of rainwater catchment systems into a Storm-Water runoff Management Model (SWMM) to design the spatial capacity and quantity of rain barrel for urban flood mitigation. This study proposes a simulation-optimization model for effectively searching the optimal design. In simulation method, we design a series of regular spatial distributions of capacity and quantity of rainwater catchment facilities, and thus the reduced flooding circumstances using a variety of design forms could be simulated by SWMM. Moreover, we further calculate the net benefit that is equal to subtract facility cost from decreasing inundation loss and the best solution of simulation method would be the initial searching solution of the optimization model. In optimizing method, first we apply the outcome of simulation method and Back-Propagation Neural Network (BPNN) for developing a water level simulation model of urban drainage system in order to replace SWMM which the operating is based on a graphical user interface and is hard to combine with optimization model and method. After that we embed the BPNN-based simulation model into the developed optimization model which the objective function is minimizing the negative net benefit. Finally, we establish a tabu search-based algorithm to optimize the planning solution. This study applies the developed method in Zhonghe Dist., Taiwan. Results showed that application of tabu search and BPNN-based simulation model into the optimization model not only can find better solutions than simulation method in 12.75%, but also can resolve the limitations of previous studies. Furthermore, the optimized spatial rain barrel design can reduce 72% of inundation loss according to historical flood events.

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…

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.

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.

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.

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.

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.

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 Technical Reports Server (NTRS)

Thompson, David E.; Rajkumar, T.; Clancy, Daniel (Technical Monitor)

2002-01-01

The San Francisco Bay Delta is a large hydrodynamic complex that incorporates the Sacramento and San Joaquin Estuaries, the Burman 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 Burman 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 alone 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 this procedure is that the numerical simulation takes roughly 16 hours to complete a C: prediction. We have created a neural net, optimized with a genetic algorithm, that takes as input the archived data from multiple stations and predicts stage, salinity, and flow at the Carquinez Straits (at the downstream end of the Burman Marsh). This model seems to be robust in its predictions and operates much faster than the current numerical DSM2 model. Because the system is strongly tidal 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 this 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 sensation data. These further constrain the behavior of the model in predicting the longer-term health and future of this vital estuary.

A neural network architecture for implementation of expert systems for real time monitoring

NASA Technical Reports Server (NTRS)

Ramamoorthy, P. A.

1991-01-01

Since neural networks have the advantages of massive parallelism and simple architecture, they are good tools for implementing real time expert systems. In a rule based expert system, the antecedents of rules are in the conjunctive or disjunctive form. We constructed a multilayer feedforward type network in which neurons represent AND or OR operations of rules. Further, we developed a translator which can automatically map a given rule base into the network. Also, we proposed a new and powerful yet flexible architecture that combines the advantages of both fuzzy expert systems and neural networks. This architecture uses the fuzzy logic concepts to separate input data domains into several smaller and overlapped regions. Rule-based expert systems for time critical applications using neural networks, the automated implementation of rule-based expert systems with neural nets, and fuzzy expert systems vs. neural nets are covered.

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.

Optimization of DRASTIC method by artificial neural network, nitrate vulnerability index, and composite DRASTIC models to assess groundwater vulnerability for unconfined aquifer of Shiraz Plain, Iran.

PubMed

Baghapour, Mohammad Ali; Fadaei Nobandegani, Amir; Talebbeydokhti, Nasser; Bagherzadeh, Somayeh; Nadiri, Ata Allah; Gharekhani, Maryam; Chitsazan, Nima

2016-01-01

Extensive human activities and unplanned land uses have put groundwater resources of Shiraz plain at a high risk of nitrate pollution, causing several environmental and human health issues. To address these issues, water resources managers utilize groundwater vulnerability assessment and determination of protection. This study aimed to prepare the vulnerability maps of Shiraz aquifer by using Composite DRASTIC index, Nitrate Vulnerability index, and artificial neural network and also to compare their efficiency. The parameters of the indexes that were employed in this study are: depth to water table, net recharge, aquifer media, soil media, topography, impact of the vadose zone, hydraulic conductivity, and land use. These parameters were rated, weighted, and integrated using GIS, and then, used to develop the risk maps of Shiraz aquifer. The results indicated that the southeastern part of the aquifer was at the highest potential risk. Given the distribution of groundwater nitrate concentrations from the wells in the underlying aquifer, the artificial neural network model offered greater accuracy compared to the other two indexes. The study concluded that the artificial neural network model is an effective model to improve the DRASTIC index and provides a confident estimate of the pollution risk. As intensive agricultural activities are the dominant land use and water table is shallow in the vulnerable zones, optimized irrigation techniques and a lower rate of fertilizers are suggested. The findings of our study could be used as a scientific basis in future for sustainable groundwater management in Shiraz plain.

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.

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.

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.

Optimized star sensors laboratory calibration method using a regularization neural network.

PubMed

Zhang, Chengfen; Niu, Yanxiong; Zhang, Hao; Lu, Jiazhen

2018-02-10

High-precision ground calibration is essential to ensure the performance of star sensors. However, the complex distortion and multi-error coupling have brought great difficulties to traditional calibration methods, especially for large field of view (FOV) star sensors. Although increasing the complexity of models is an effective way to improve the calibration accuracy, it significantly increases the demand for calibration data. In order to achieve high-precision calibration of star sensors with large FOV, a novel laboratory calibration method based on a regularization neural network is proposed. A multi-layer structure neural network is designed to represent the mapping of the star vector and the corresponding star point coordinate directly. To ensure the generalization performance of the network, regularization strategies are incorporated into the net structure and the training algorithm. Simulation and experiment results demonstrate that the proposed method can achieve high precision with less calibration data and without any other priori information. Compared with traditional methods, the calibration error of the star sensor decreased by about 30%. The proposed method can satisfy the precision requirement for large FOV star sensors.

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).

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.

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.

A one-layer recurrent neural network for constrained pseudoconvex optimization and its application for dynamic portfolio optimization.

PubMed

Liu, Qingshan; Guo, Zhishan; Wang, Jun

2012-02-01

In this paper, a one-layer recurrent neural network is proposed for solving pseudoconvex optimization problems subject to linear equality and bound constraints. Compared with the existing neural networks for optimization (e.g., the projection neural networks), the proposed neural network is capable of solving more general pseudoconvex optimization problems with equality and bound constraints. Moreover, it is capable of solving constrained fractional programming problems as a special case. The convergence of the state variables of the proposed neural network to achieve solution optimality is guaranteed as long as the designed parameters in the model are larger than the derived lower bounds. Numerical examples with simulation results illustrate the effectiveness and characteristics of the proposed neural network. In addition, an application for dynamic portfolio optimization is discussed. Copyright © 2011 Elsevier Ltd. All rights reserved.

Caffe con Troll: Shallow Ideas to Speed Up Deep Learning

PubMed Central

Hadjis, Stefan; Abuzaid, Firas; Zhang, Ce; Ré, Christopher

2016-01-01

We present Caffe con Troll (CcT), a fully compatible end-to-end version of the popular framework Caffe with rebuilt internals. We built CcT to examine the performance characteristics of training and deploying general-purpose convolutional neural networks across different hardware architectures. We find that, by employing standard batching optimizations for CPU training, we achieve a 4.5× throughput improvement over Caffe on popular networks like CaffeNet. Moreover, with these improvements, the end-to-end training time for CNNs is directly proportional to the FLOPS delivered by the CPU, which enables us to efficiently train hybrid CPU-GPU systems for CNNs. PMID:27314106

Caffe con Troll: Shallow Ideas to Speed Up Deep Learning.

PubMed

Hadjis, Stefan; Abuzaid, Firas; Zhang, Ce; Ré, Christopher

2015-01-01

We present Caffe con Troll (CcT), a fully compatible end-to-end version of the popular framework Caffe with rebuilt internals. We built CcT to examine the performance characteristics of training and deploying general-purpose convolutional neural networks across different hardware architectures. We find that, by employing standard batching optimizations for CPU training, we achieve a 4.5× throughput improvement over Caffe on popular networks like CaffeNet. Moreover, with these improvements, the end-to-end training time for CNNs is directly proportional to the FLOPS delivered by the CPU, which enables us to efficiently train hybrid CPU-GPU systems for CNNs.

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).

FUEL-FLEXIBLE GASIFICATION-COMBUSTION TECHNOLOGY FOR PRODUCTION OF H2 AND SEQUESTRATION-READY CO2

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

George Rizeq; Janice West; Arnaldo Frydman

Further development of a combustion Large Eddy Simulation (LES) code for the design of advanced gaseous combustion systems is described in this sixth quarterly report. CFD Research Corporation (CFDRC) is developing the LES module within the parallel, unstructured solver included in the commercial CFD-ACE+ software. In this quarter, in-situ adaptive tabulation (ISAT) for efficient chemical rate storage and retrieval was implemented and tested within the Linear Eddy Model (LEM). ISAT type 3 is being tested so that extrapolation can be performed and further improve the retrieval rate. Further testing of the LEM for subgrid chemistry was performed for parallel applicationsmore » and for multi-step chemistry. Validation of the software on backstep and bluff-body reacting cases were performed. Initial calculations of the SimVal experiment at Georgia Tech using their LES code were performed. Georgia Tech continues the effort to parameterize the LEM over composition space so that a neural net can be used efficiently in the combustion LES code. A new and improved Artificial Neural Network (ANN), with log-transformed output, for the 1-step chemistry was implemented in CFDRC's LES code and gave reasonable results. This quarter, the 2nd consortium meeting was held at CFDRC. Next quarter, LES software development and testing will continue. Alpha testing of the code will continue to be performed on cases of interest to the industrial consortium. Optimization of subgrid models will be pursued, particularly with the ISAT approach. Also next quarter, the demonstration of the neural net approach, for multi-step chemical kinetics speed-up in CFD-ACE+, will be accomplished.« less

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

Schema generation in recurrent neural nets for intercepting a moving target.

PubMed

Fleischer, Andreas G

2010-06-01

The grasping of a moving object requires the development of a motor strategy to anticipate the trajectory of the target and to compute an optimal course of interception. During the performance of perception-action cycles, a preprogrammed prototypical movement trajectory, a motor schema, may highly reduce the control load. Subjects were asked to hit a target that was moving along a circular path by means of a cursor. Randomized initial target positions and velocities were detected in the periphery of the eyes, resulting in a saccade toward the target. Even when the target disappeared, the eyes followed the target's anticipated course. The Gestalt of the trajectories was dependent on target velocity. The prediction capability of the motor schema was investigated by varying the visibility range of cursor and target. Motor schemata were determined to be of limited precision, and therefore visual feedback was continuously required to intercept the moving target. To intercept a target, the motor schema caused the hand to aim ahead and to adapt to the target trajectory. The control of cursor velocity determined the point of interception. From a modeling point of view, a neural network was developed that allowed the implementation of a motor schema interacting with feedback control in an iterative manner. The neural net of the Wilson type consists of an excitation-diffusion layer allowing the generation of a moving bubble. This activation bubble runs down an eye-centered motor schema and causes a planar arm model to move toward the target. A bubble provides local integration and straightening of the trajectory during repetitive moves. The schema adapts to task demands by learning and serves as forward controller. On the basis of these model considerations the principal problem of embedding motor schemata in generalized control strategies is discussed.

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.

Visual gene developer: a fully programmable bioinformatics software for synthetic gene optimization.

PubMed

Jung, Sang-Kyu; McDonald, Karen

2011-08-16

Direct gene synthesis is becoming more popular owing to decreases in gene synthesis pricing. Compared with using natural genes, gene synthesis provides a good opportunity to optimize gene sequence for specific applications. In order to facilitate gene optimization, we have developed a stand-alone software called Visual Gene Developer. The software not only provides general functions for gene analysis and optimization along with an interactive user-friendly interface, but also includes unique features such as programming capability, dedicated mRNA secondary structure prediction, artificial neural network modeling, network & multi-threaded computing, and user-accessible programming modules. The software allows a user to analyze and optimize a sequence using main menu functions or specialized module windows. Alternatively, gene optimization can be initiated by designing a gene construct and configuring an optimization strategy. A user can choose several predefined or user-defined algorithms to design a complicated strategy. The software provides expandable functionality as platform software supporting module development using popular script languages such as VBScript and JScript in the software programming environment. Visual Gene Developer is useful for both researchers who want to quickly analyze and optimize genes, and those who are interested in developing and testing new algorithms in bioinformatics. The software is available for free download at http://www.visualgenedeveloper.net.

Visual gene developer: a fully programmable bioinformatics software for synthetic gene optimization

PubMed Central

2011-01-01

Background Direct gene synthesis is becoming more popular owing to decreases in gene synthesis pricing. Compared with using natural genes, gene synthesis provides a good opportunity to optimize gene sequence for specific applications. In order to facilitate gene optimization, we have developed a stand-alone software called Visual Gene Developer. Results The software not only provides general functions for gene analysis and optimization along with an interactive user-friendly interface, but also includes unique features such as programming capability, dedicated mRNA secondary structure prediction, artificial neural network modeling, network & multi-threaded computing, and user-accessible programming modules. The software allows a user to analyze and optimize a sequence using main menu functions or specialized module windows. Alternatively, gene optimization can be initiated by designing a gene construct and configuring an optimization strategy. A user can choose several predefined or user-defined algorithms to design a complicated strategy. The software provides expandable functionality as platform software supporting module development using popular script languages such as VBScript and JScript in the software programming environment. Conclusion Visual Gene Developer is useful for both researchers who want to quickly analyze and optimize genes, and those who are interested in developing and testing new algorithms in bioinformatics. The software is available for free download at http://www.visualgenedeveloper.net. PMID:21846353

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.

Efficient Coding and Energy Efficiency Are Promoted by Balanced Excitatory and Inhibitory Synaptic Currents in Neuronal Network

PubMed Central

Yu, Lianchun; Shen, Zhou; Wang, Chen; Yu, Yuguo

2018-01-01

Selective pressure may drive neural systems to process as much information as possible with the lowest energy cost. Recent experiment evidence revealed that the ratio between synaptic excitation and inhibition (E/I) in local cortex is generally maintained at a certain value which may influence the efficiency of energy consumption and information transmission of neural networks. To understand this issue deeply, we constructed a typical recurrent Hodgkin-Huxley network model and studied the general principles that governs the relationship among the E/I synaptic current ratio, the energy cost and total amount of information transmission. We observed in such a network that there exists an optimal E/I synaptic current ratio in the network by which the information transmission achieves the maximum with relatively low energy cost. The coding energy efficiency which is defined as the mutual information divided by the energy cost, achieved the maximum with the balanced synaptic current. Although background noise degrades information transmission and imposes an additional energy cost, we find an optimal noise intensity that yields the largest information transmission and energy efficiency at this optimal E/I synaptic transmission ratio. The maximization of energy efficiency also requires a certain part of energy cost associated with spontaneous spiking and synaptic activities. We further proved this finding with analytical solution based on the response function of bistable neurons, and demonstrated that optimal net synaptic currents are capable of maximizing both the mutual information and energy efficiency. These results revealed that the development of E/I synaptic current balance could lead a cortical network to operate at a highly efficient information transmission rate at a relatively low energy cost. The generality of neuronal models and the recurrent network configuration used here suggest that the existence of an optimal E/I cell ratio for highly efficient energy costs and information maximization is a potential principle for cortical circuit networks. Summary We conducted numerical simulations and mathematical analysis to examine the energy efficiency of neural information transmission in a recurrent network as a function of the ratio of excitatory and inhibitory synaptic connections. We obtained a general solution showing that there exists an optimal E/I synaptic ratio in a recurrent network at which the information transmission as well as the energy efficiency of this network achieves a global maximum. These results reflect general mechanisms for sensory coding processes, which may give insight into the energy efficiency of neural communication and coding. PMID:29773979

Efficient Coding and Energy Efficiency Are Promoted by Balanced Excitatory and Inhibitory Synaptic Currents in Neuronal Network.

PubMed

Yu, Lianchun; Shen, Zhou; Wang, Chen; Yu, Yuguo

2018-01-01

Selective pressure may drive neural systems to process as much information as possible with the lowest energy cost. Recent experiment evidence revealed that the ratio between synaptic excitation and inhibition (E/I) in local cortex is generally maintained at a certain value which may influence the efficiency of energy consumption and information transmission of neural networks. To understand this issue deeply, we constructed a typical recurrent Hodgkin-Huxley network model and studied the general principles that governs the relationship among the E/I synaptic current ratio, the energy cost and total amount of information transmission. We observed in such a network that there exists an optimal E/I synaptic current ratio in the network by which the information transmission achieves the maximum with relatively low energy cost. The coding energy efficiency which is defined as the mutual information divided by the energy cost, achieved the maximum with the balanced synaptic current. Although background noise degrades information transmission and imposes an additional energy cost, we find an optimal noise intensity that yields the largest information transmission and energy efficiency at this optimal E/I synaptic transmission ratio. The maximization of energy efficiency also requires a certain part of energy cost associated with spontaneous spiking and synaptic activities. We further proved this finding with analytical solution based on the response function of bistable neurons, and demonstrated that optimal net synaptic currents are capable of maximizing both the mutual information and energy efficiency. These results revealed that the development of E/I synaptic current balance could lead a cortical network to operate at a highly efficient information transmission rate at a relatively low energy cost. The generality of neuronal models and the recurrent network configuration used here suggest that the existence of an optimal E/I cell ratio for highly efficient energy costs and information maximization is a potential principle for cortical circuit networks. We conducted numerical simulations and mathematical analysis to examine the energy efficiency of neural information transmission in a recurrent network as a function of the ratio of excitatory and inhibitory synaptic connections. We obtained a general solution showing that there exists an optimal E/I synaptic ratio in a recurrent network at which the information transmission as well as the energy efficiency of this network achieves a global maximum. These results reflect general mechanisms for sensory coding processes, which may give insight into the energy efficiency of neural communication and coding.

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

PubMed

Liu, Qingshan; Dang, Chuangyin; Huang, Tingwen

2013-02-01

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

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.

Alteration of neural action potential patterns by axonal stimulation: the importance of stimulus location

PubMed Central

Crago, Patrick E; Makowski, Nathan S

2014-01-01

Objective 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. Approach 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. Main Results 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. Significance 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. PMID:25161163

Alteration of neural action potential patterns by axonal stimulation: the importance of stimulus location

NASA Astrophysics Data System (ADS)

Crago, Patrick E.; Makowski, Nathaniel S.

2014-10-01

Objective. 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. Approach. 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. Main results. 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. Significance. 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.

Feed Forward Neural Network and Optimal Control Problem with Control and State Constraints

NASA Astrophysics Data System (ADS)

Kmet', Tibor; Kmet'ová, Mária

2009-09-01

A feed forward neural network based optimal control synthesis is presented for solving optimal control problems with control and state constraints. The paper extends adaptive critic neural network architecture proposed by [5] to the optimal control problems with control and state constraints. The optimal control problem is transcribed into a nonlinear programming problem which is implemented with adaptive critic neural network. The proposed simulation method is illustrated by the optimal control problem of nitrogen transformation cycle model. Results show that adaptive critic based systematic approach holds promise for obtaining the optimal control with control and state constraints.

Improving Efficiency in Multi-Strange Baryon Reconstruction in d-Au at STAR

NASA Astrophysics Data System (ADS)

Leight, William

2003-10-01

We report preliminary multi-strange baryon measurements for d-Au collisions recorded at RHIC by the STAR experiment. After using classical topological analysis, in which cuts for each discriminating variable are adjusted by hand, we investigate improvements in signal-to-noise optimization using Linear Discriminant Analysis (LDA). LDA is an algorithm for finding, in the n-dimensional space of the n discriminating variables, the axis on which the signal and noise distributions are most separated. LDA is the first step in moving towards more sophisticated techniques for signal-to-noise optimization, such as Artificial Neural Nets. Due to the relatively low background and sufficiently high yields of d-Au collisions, they form an ideal system to study these possibilities for improving reconstruction methods. Such improvements will be extremely important for forthcoming Au-Au runs in which the size of the combinatoric background is a major problem in reconstruction efforts.

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.

Electronic neural networks for global optimization

NASA Technical Reports Server (NTRS)

Thakoor, A. P.; Moopenn, A. W.; Eberhardt, S.

1990-01-01

An electronic neural network with feedback architecture, implemented in analog custom VLSI is described. Its application to problems of global optimization for dynamic assignment is discussed. The convergence properties of the neural network hardware are compared with computer simulation results. The neural network's ability to provide optimal or near optimal solutions within only a few neuron time constants, a speed enhancement of several orders of magnitude over conventional search methods, is demonstrated. The effect of noise on the circuit dynamics and the convergence behavior of the neural network hardware is also examined.

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…

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

PubMed

Liu, Qingshan; Wang, Jun

2011-04-01

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

Feedback Synthesizes Neural Codes for Motion.

PubMed

Clarke, Stephen E; Maler, Leonard

2017-05-08

In senses as diverse as vision, hearing, touch, and the electrosense, sensory neurons receive bottom-up input from the environment, as well as top-down input from feedback loops involving higher brain regions [1-4]. Through connectivity with local inhibitory interneurons, these feedback loops can exert both positive and negative control over fundamental aspects of neural coding, including bursting [5, 6] and synchronous population activity [7, 8]. Here we show that a prominent midbrain feedback loop synthesizes a neural code for motion reversal in the hindbrain electrosensory ON- and OFF-type pyramidal cells. This top-down mechanism generates an accurate bidirectional encoding of object position, despite the inability of the electrosensory afferents to generate a consistent bottom-up representation [9, 10]. The net positive activity of this midbrain feedback is additionally regulated through a hindbrain feedback loop, which reduces stimulus-induced bursting and also dampens the ON and OFF cell responses to interfering sensory input [11]. We demonstrate that synthesis of motion representations and cancellation of distracting signals are mediated simultaneously by feedback, satisfying an accepted definition of spatial attention [12]. The balance of excitatory and inhibitory feedback establishes a "focal" distance for optimized neural coding, whose connection to a classic motion-tracking behavior provides new insight into the computational roles of feedback and active dendrites in spatial localization [13, 14]. Copyright © 2017 Elsevier Ltd. All rights reserved.

Optimization of neural network architecture using genetic programming improves detection and modeling of gene-gene interactions in studies of human diseases

PubMed Central

Ritchie, Marylyn D; White, Bill C; Parker, Joel S; Hahn, Lance W; Moore, Jason H

2003-01-01

Background Appropriate definition of neural network architecture prior to data analysis is crucial for successful data mining. This can be challenging when the underlying model of the data is unknown. The goal of this study was to determine whether optimizing neural network architecture using genetic programming as a machine learning strategy would improve the ability of neural networks to model and detect nonlinear interactions among genes in studies of common human diseases. Results Using simulated data, we show that a genetic programming optimized neural network approach is able to model gene-gene interactions as well as a traditional back propagation neural network. Furthermore, the genetic programming optimized neural network is better than the traditional back propagation neural network approach in terms of predictive ability and power to detect gene-gene interactions when non-functional polymorphisms are present. Conclusion This study suggests that a machine learning strategy for optimizing neural network architecture may be preferable to traditional trial-and-error approaches for the identification and characterization of gene-gene interactions in common, complex human diseases. PMID:12846935

Data fusion with artificial neural networks (ANN) for classification of earth surface from microwave satellite measurements

NASA Technical Reports Server (NTRS)

Lure, Y. M. Fleming; Grody, Norman C.; Chiou, Y. S. Peter; Yeh, H. Y. Michael

1993-01-01

A data fusion system with artificial neural networks (ANN) is used for fast and accurate classification of five earth surface conditions and surface changes, based on seven SSMI multichannel microwave satellite measurements. The measurements include brightness temperatures at 19, 22, 37, and 85 GHz at both H and V polarizations (only V at 22 GHz). The seven channel measurements are processed through a convolution computation such that all measurements are located at same grid. Five surface classes including non-scattering surface, precipitation over land, over ocean, snow, and desert are identified from ground-truth observations. The system processes sensory data in three consecutive phases: (1) pre-processing to extract feature vectors and enhance separability among detected classes; (2) preliminary classification of Earth surface patterns using two separate and parallely acting classifiers: back-propagation neural network and binary decision tree classifiers; and (3) data fusion of results from preliminary classifiers to obtain the optimal performance in overall classification. Both the binary decision tree classifier and the fusion processing centers are implemented by neural network architectures. The fusion system configuration is a hierarchical neural network architecture, in which each functional neural net will handle different processing phases in a pipelined fashion. There is a total of around 13,500 samples for this analysis, of which 4 percent are used as the training set and 96 percent as the testing set. After training, this classification system is able to bring up the detection accuracy to 94 percent compared with 88 percent for back-propagation artificial neural networks and 80 percent for binary decision tree classifiers. The neural network data fusion classification is currently under progress to be integrated in an image processing system at NOAA and to be implemented in a prototype of a massively parallel and dynamically reconfigurable Modular Neural Ring (MNR).

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

BP fusion model for the detection of oil spills on the sea by remote sensing

NASA Astrophysics Data System (ADS)

Chen, Weiwei; An, Jubai; Zhang, Hande; Lin, Bin

2003-06-01

Oil spills are very serious marine pollution in many countries. In order to detect and identify the oil-spilled on the sea by remote sensor, scientists have to conduct a research work on the remote sensing image. As to the detection of oil spills on the sea, edge detection is an important technology in image processing. There are many algorithms of edge detection developed for image processing. These edge detection algorithms always have their own advantages and disadvantages in the image processing. Based on the primary requirements of edge detection of the oil spills" image on the sea, computation time and detection accuracy, we developed a fusion model. The model employed a BP neural net to fuse the detection results of simple operators. The reason we selected BP neural net as the fusion technology is that the relation between simple operators" result of edge gray level and the image"s true edge gray level is nonlinear, while BP neural net is good at solving the nonlinear identification problem. Therefore in this paper we trained a BP neural net by some oil spill images, then applied the BP fusion model on the edge detection of other oil spill images and obtained a good result. In this paper the detection result of some gradient operators and Laplacian operator are also compared with the result of BP fusion model to analysis the fusion effect. At last the paper pointed out that the fusion model has higher accuracy and higher speed in the processing oil spill image"s edge detection.

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

Application of a neural network for reflectance spectrum classification

NASA Astrophysics Data System (ADS)

Yang, Gefei; Gartley, Michael

2017-05-01

Traditional reflectance spectrum classification algorithms are based on comparing spectrum across the electromagnetic spectrum anywhere from the ultra-violet to the thermal infrared regions. These methods analyze reflectance on a pixel by pixel basis. Inspired by high performance that Convolution Neural Networks (CNN) have demonstrated in image classification, we applied a neural network to analyze directional reflectance pattern images. By using the bidirectional reflectance distribution function (BRDF) data, we can reformulate the 4-dimensional into 2 dimensions, namely incident direction × reflected direction × channels. Meanwhile, RIT's micro-DIRSIG model is utilized to simulate additional training samples for improving the robustness of the neural networks training. Unlike traditional classification by using hand-designed feature extraction with a trainable classifier, neural networks create several layers to learn a feature hierarchy from pixels to classifier and all layers are trained jointly. Hence, the our approach of utilizing the angular features are different to traditional methods utilizing spatial features. Although training processing typically has a large computational cost, simple classifiers work well when subsequently using neural network generated features. Currently, most popular neural networks such as VGG, GoogLeNet and AlexNet are trained based on RGB spatial image data. Our approach aims to build a directional reflectance spectrum based neural network to help us to understand from another perspective. At the end of this paper, we compare the difference among several classifiers and analyze the trade-off among neural networks parameters.

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 dynamic programming and its application to control systems

NASA Astrophysics Data System (ADS)

Seong, Chang-Yun

There are few general practical feedback control methods for nonlinear MIMO (multi-input-multi-output) systems, although such methods exist for their linear counterparts. Neural Dynamic Programming (NDP) is proposed as a practical design method of optimal feedback controllers for nonlinear MIMO systems. NDP is an offspring of both neural networks and optimal control theory. In optimal control theory, the optimal solution to any nonlinear MIMO control problem may be obtained from the Hamilton-Jacobi-Bellman equation (HJB) or the Euler-Lagrange equations (EL). The two sets of equations provide the same solution in different forms: EL leads to a sequence of optimal control vectors, called Feedforward Optimal Control (FOC); HJB yields a nonlinear optimal feedback controller, called Dynamic Programming (DP). DP produces an optimal solution that can reject disturbances and uncertainties as a result of feedback. Unfortunately, computation and storage requirements associated with DP solutions can be problematic, especially for high-order nonlinear systems. This dissertation presents an approximate technique for solving the DP problem based on neural network techniques that provides many of the performance benefits (e.g., optimality and feedback) of DP and benefits from the numerical properties of neural networks. We formulate neural networks to approximate optimal feedback solutions whose existence DP justifies. We show the conditions under which NDP closely approximates the optimal solution. Finally, we introduce the learning operator characterizing the learning process of the neural network in searching the optimal solution. The analysis of the learning operator provides not only a fundamental understanding of the learning process in neural networks but also useful guidelines for selecting the number of weights of the neural network. As a result, NDP finds---with a reasonable amount of computation and storage---the optimal feedback solutions to nonlinear MIMO control problems that would be very difficult to solve with DP. NDP was demonstrated on several applications such as the lateral autopilot logic for a Boeing 747, the minimum fuel control of a double-integrator plant with bounded control, the backward steering of a two-trailer truck, and the set-point control of a two-link robot arm.

Near Optimal Event-Triggered Control of Nonlinear Discrete-Time Systems Using Neurodynamic Programming.

PubMed

Sahoo, Avimanyu; Xu, Hao; Jagannathan, Sarangapani

2016-09-01

This paper presents an event-triggered near optimal control of uncertain nonlinear discrete-time systems. Event-driven neurodynamic programming (NDP) is utilized to design the control policy. A neural network (NN)-based identifier, with event-based state and input vectors, is utilized to learn the system dynamics. An actor-critic framework is used to learn the cost function and the optimal control input. The NN weights of the identifier, the critic, and the actor NNs are tuned aperiodically once every triggered instant. An adaptive event-trigger condition to decide the trigger instants is derived. Thus, a suitable number of events are generated to ensure a desired accuracy of approximation. A near optimal performance is achieved without using value and/or policy iterations. A detailed analysis of nontrivial inter-event times with an explicit formula to show the reduction in computation is also derived. The Lyapunov technique is used in conjunction with the event-trigger condition to guarantee the ultimate boundedness of the closed-loop system. The simulation results are included to verify the performance of the controller. The net result is the development of event-driven NDP.

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.

Modeling Training Site Vegetation Coverage Probability with a Random Optimizing Procedure: An Artificial Neural Network Approach.

DTIC Science & Technology

1998-05-01

Coverage Probability with a Random Optimization Procedure: An Artificial Neural Network Approach by Biing T. Guan, George Z. Gertner, and Alan B...Modeling Training Site Vegetation Coverage Probability with a Random Optimizing Procedure: An Artificial Neural Network Approach 6. AUTHOR(S) Biing...coverage based on past coverage. Approach A literature survey was conducted to identify artificial neural network analysis techniques applicable for

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

Multidisciplinary Design Optimization for Aeropropulsion Engines and Solid Modeling/Animation via the Integrated Forced Methods

NASA Technical Reports Server (NTRS)

2004-01-01

The grant closure report is organized in the following four chapters: Chapter describes the two research areas Design optimization and Solid mechanics. Ten journal publications are listed in the second chapter. Five highlights is the subject matter of chapter three. CHAPTER 1. The Design Optimization Test Bed CometBoards. CHAPTER 2. Solid Mechanics: Integrated Force Method of Analysis. CHAPTER 3. Five Highlights: Neural Network and Regression Methods Demonstrated in the Design Optimization of a Subsonic Aircraft. Neural Network and Regression Soft Model Extended for PX-300 Aircraft Engine. Engine with Regression and Neural Network Approximators Designed. Cascade Optimization Strategy with Neural network and Regression Approximations Demonstrated on a Preliminary Aircraft Engine Design. Neural Network and Regression Approximations Used in Aircraft Design.

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.

Automatic classification of transiently evoked otoacoustic emissions using an artificial neural network.

PubMed

Buller, G; Lutman, M E

1998-08-01

The increasing use of transiently evoked otoacoustic emissions (TEOAE) in large neonatal hearing screening programmes makes a standardized method of response classification desirable. Until now methods have been either subjective or based on arbitrary response characteristics. This study takes an expert system approach to standardize the subjective judgements of an experienced scorer. The method that is developed comprises three stages. First, it transforms TEOAEs from waveforms in the time domain into a simplified parameter set. Second, the parameter set is classified by an artificial neural network that has been taught on a large database TEOAE waveforms and corresponding expert scores. Third, additional fuzzy logic rules automatically detect probable artefacts in the waveforms and synchronized spontaneous emission components. In this way, the knowledge of the experienced scorer is encapsulated in the expert system software and thereafter can be accessed by non-experts. Teaching and evaluation of the neural network was based on TEOAEs from a database totalling 2190 neonatal hearing screening tests. The database was divided into learning and test groups with 820 and 1370 waveforms respectively. From each recorded waveform a set of 12 parameters was calculated, representing signal static and dynamic properties. The artifical network was taught with parameter sets of only the learning groups. Reproduction of the human scorer classification by the neural net in the learning group showed a sensitivity for detecting screen fails of 99.3% (299 from 301 failed results on subjective scoring) and a specificity for detecting screen passes of 81.1% (421 of 519 pass results). To quantify the post hoc performance of the net (generalization), the test group was then presented to the network input. Sensitivity was 99.4% (474 from 477) and specificity was 87.3% (780 from 893). To check the efficiency of the classification method, a second learning group was selected out of the previous test group, and the previous learning group was used as the test group. Repeating learning and test procedures yielded 99.3% sensitivity and 80.7% specificity for reproduction, and 99.4% sensitivity and 86.7% specificity for generalization. In all respects, performance was better than for a previously optimized method based simply on cross-correlation between replicate non-linear waveforms. It is concluded that classification methods based on neural networks show promise for application to large neonatal screening programmes utilizing TEOAEs.

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.

Accounting for between-study variation in incremental net benefit in value of information methodology.

PubMed

Willan, Andrew R; Eckermann, Simon

2012-10-01

Previous applications of value of information methods for determining optimal sample size in randomized clinical trials have assumed no between-study variation in mean incremental net benefit. By adopting a hierarchical model, we provide a solution for determining optimal sample size with this assumption relaxed. The solution is illustrated with two examples from the literature. Expected net gain increases with increasing between-study variation, reflecting the increased uncertainty in incremental net benefit and reduced extent to which data are borrowed from previous evidence. Hence, a trial can become optimal where current evidence is sufficient assuming no between-study variation. However, despite the expected net gain increasing, the optimal sample size in the illustrated examples is relatively insensitive to the amount of between-study variation. Further percentage losses in expected net gain were small even when choosing sample sizes that reflected widely different between-study variation. Copyright © 2011 John Wiley & Sons, Ltd.

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.

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.

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.

Neural coordination can be enhanced by occasional interruption of normal firing patterns: a self-optimizing spiking neural network model.

PubMed

Woodward, Alexander; Froese, Tom; Ikegami, Takashi

2015-02-01

The state space of a conventional Hopfield network typically exhibits many different attractors of which only a small subset satisfies constraints between neurons in a globally optimal fashion. It has recently been demonstrated that combining Hebbian learning with occasional alterations of normal neural states avoids this problem by means of self-organized enlargement of the best basins of attraction. However, so far it is not clear to what extent this process of self-optimization is also operative in real brains. Here we demonstrate that it can be transferred to more biologically plausible neural networks by implementing a self-optimizing spiking neural network model. In addition, by using this spiking neural network to emulate a Hopfield network with Hebbian learning, we attempt to make a connection between rate-based and temporal coding based neural systems. Although further work is required to make this model more realistic, it already suggests that the efficacy of the self-optimizing process is independent from the simplifying assumptions of a conventional Hopfield network. We also discuss natural and cultural processes that could be responsible for occasional alteration of neural firing patterns in actual brains. Copyright © 2014 Elsevier Ltd. All rights reserved.

Neuro-genetic multioptimization of the determination of polychlorinated biphenyl congeners in human milk by headspace solid phase microextraction coupled to gas chromatography with electron capture detection.

PubMed

Kowalski, Cláudia Hoffmann; da Silva, Gilmare Antônia; Poppi, Ronei Jesus; Godoy, Helena Teixeira; Augusto, Fabio

2007-02-28

Polychlorinated biphenyls (PCB) can eventually contaminate breast milk, which is a serious issue to the newborn due to their high vulnerability. Solid phase microextraction (SPME) can be a very convenient technique for their isolation and pre-concentration prior chromatographic analysis. Here, a simultaneous multioptimization strategy based on a neuro-genetic approach was applied to a headspace SPME method for determination of 12 PCB in human milk. Gas chromatography with electron capture detection (ECD) was adopted for the separation and detection of the analytes. Experiments according to a Doehlert design were carried out with varied extraction time and temperature, media ionic strength and concentration of the methanol (co-solvent). To find the best model that simultaneously correlate all PCB peak areas and SPME extraction conditions, a multivariate calibration method based on a Bayesian Neural Network (BNN) was applied. The net output from the neural network was used as input in a genetic algorithm (GA) optimization operation (neuro-genetic approach). The GA pointed out that the best values of the overall SPME operational conditions were the saturation of the media with NaCl, extraction temperature of 95 degrees C, extraction time of 60 min and addition of 5% (v/v) methanol to the media. These optimized parameters resulted in the decrease of the detection limits and increase on the sensitivity for all tested analytes, showing that the use of neuro-genetic approach can be a promising way for optimization of SPME methods.

Sub-Audible Speech Recognition Based upon Electromyographic Signals

NASA Technical Reports Server (NTRS)

Jorgensen, Charles C. (Inventor); Agabon, Shane T. (Inventor); Lee, Diana D. (Inventor)

2012-01-01

Method and system for processing and identifying a sub-audible signal formed by a source of sub-audible sounds. Sequences of samples of sub-audible sound patterns ("SASPs") for known words/phrases in a selected database are received for overlapping time intervals, and Signal Processing Transforms ("SPTs") are formed for each sample, as part of a matrix of entry values. The matrix is decomposed into contiguous, non-overlapping two-dimensional cells of entries, and neural net analysis is applied to estimate reference sets of weight coefficients that provide sums with optimal matches to reference sets of values. The reference sets of weight coefficients are used to determine a correspondence between a new (unknown) word/phrase and a word/phrase in the database.

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

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 .

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.

Optimal exponential synchronization of general chaotic delayed neural networks: an LMI approach.

PubMed

Liu, Meiqin

2009-09-01

This paper investigates the optimal exponential synchronization problem of general chaotic neural networks with or without time delays by virtue of Lyapunov-Krasovskii stability theory and the linear matrix inequality (LMI) technique. This general model, which is the interconnection of a linear delayed dynamic system and a bounded static nonlinear operator, covers several well-known neural networks, such as Hopfield neural networks, cellular neural networks (CNNs), bidirectional associative memory (BAM) networks, and recurrent multilayer perceptrons (RMLPs) with or without delays. Using the drive-response concept, time-delay feedback controllers are designed to synchronize two identical chaotic neural networks as quickly as possible. The control design equations are shown to be a generalized eigenvalue problem (GEVP) which can be easily solved by various convex optimization algorithms to determine the optimal control law and the optimal exponential synchronization rate. Detailed comparisons with existing results are made and numerical simulations are carried out to demonstrate the effectiveness of the established synchronization laws.

Application of Neural Network Optimized by Mind Evolutionary Computation in Building Energy Prediction

NASA Astrophysics Data System (ADS)

Song, Chen; Zhong-Cheng, Wu; Hong, Lv

2018-03-01

Building Energy forecasting plays an important role in energy management and plan. Using mind evolutionary algorithm to find the optimal network weights and threshold, to optimize the BP neural network, can overcome the problem of the BP neural network into a local minimum point. The optimized network is used for time series prediction, and the same month forecast, to get two predictive values. Then two kinds of predictive values are put into neural network, to get the final forecast value. The effectiveness of the method was verified by experiment with the energy value of three buildings in Hefei.

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.

Salient regions detection using convolutional neural networks and color volume

NASA Astrophysics Data System (ADS)

Liu, Guang-Hai; Hou, Yingkun

2018-03-01

Convolutional neural network is an important technique in machine learning, pattern recognition and image processing. In order to reduce the computational burden and extend the classical LeNet-5 model to the field of saliency detection, we propose a simple and novel computing model based on LeNet-5 network. In the proposed model, hue, saturation and intensity are utilized to extract depth cues, and then we integrate depth cues and color volume to saliency detection following the basic structure of the feature integration theory. Experimental results show that the proposed computing model outperforms some existing state-of-the-art methods on MSRA1000 and ECSSD datasets.

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.

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.

Effect of design selection on response surface performance

NASA Technical Reports Server (NTRS)

Carpenter, William C.

1993-01-01

The mathematical formulation of the engineering optimization problem is given. Evaluation of the objective function and constraint equations can be very expensive in a computational sense. Thus, it is desirable to use as few evaluations as possible in obtaining its solution. In solving the equation, one approach is to develop approximations to the objective function and/or restraint equations and then to solve the equation using the approximations in place of the original functions. These approximations are referred to as response surfaces. The desirability of using response surfaces depends upon the number of functional evaluations required to build the response surfaces compared to the number required in the direct solution of the equation without approximations. The present study is concerned with evaluating the performance of response surfaces so that a decision can be made as to their effectiveness in optimization applications. In particular, this study focuses on how the quality of approximations is effected by design selection. Polynomial approximations and neural net approximations are considered.

Optimal input sizes for neural network de-interlacing

NASA Astrophysics Data System (ADS)

Choi, Hyunsoo; Seo, Guiwon; Lee, Chulhee

2009-02-01

Neural network de-interlacing has shown promising results among various de-interlacing methods. In this paper, we investigate the effects of input size for neural networks for various video formats when the neural networks are used for de-interlacing. In particular, we investigate optimal input sizes for CIF, VGA and HD video formats.

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.

Non-overlapping Neural Networks in Hydra vulgaris.

PubMed

Dupre, Christophe; Yuste, Rafael

2017-04-24

To understand the emergent properties of neural circuits, it would be ideal to record the activity of every neuron in a behaving animal and decode how it relates to behavior. We have achieved this with the cnidarian Hydra vulgaris, using calcium imaging of genetically engineered animals to measure the activity of essentially all of its neurons. Although the nervous system of Hydra is traditionally described as a simple nerve net, we surprisingly find instead a series of functional networks that are anatomically non-overlapping and are associated with specific behaviors. Three major functional networks extend through the entire animal and are activated selectively during longitudinal contractions, elongations in response to light, and radial contractions, whereas an additional network is located near the hypostome and is active during nodding. These results demonstrate the functional sophistication of apparently simple nerve nets, and the potential of Hydra and other basal metazoans as a model system for neural circuit studies. Published by Elsevier Ltd.

A novel recurrent neural network with finite-time convergence for linear programming.

PubMed

Liu, Qingshan; Cao, Jinde; Chen, Guanrong

2010-11-01

In this letter, a novel recurrent neural network based on the gradient method is proposed for solving linear programming problems. Finite-time convergence of the proposed neural network is proved by using the Lyapunov method. Compared with the existing neural networks for linear programming, the proposed neural network is globally convergent to exact optimal solutions in finite time, which is remarkable and rare in the literature of neural networks for optimization. Some numerical examples are given to show the effectiveness and excellent performance of the new recurrent neural network.

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.

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.

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.

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.

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.

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

PubMed

Liang, X B; Wang, J

2000-01-01

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

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.

Optimal insecticide-treated bed-net coverage and malaria treatment in a malaria-HIV co-infection model.

PubMed

Mohammed-Awel, Jemal; Numfor, Eric

2017-03-01

We propose and study a mathematical model for malaria-HIV co-infection transmission and control, in which malaria treatment and insecticide-treated nets are incorporated. The existence of a backward bifurcation is established analytically, and the occurrence of such backward bifurcation is influenced by disease-induced mortality, insecticide-treated bed-net coverage and malaria treatment parameters. To further assess the impact of malaria treatment and insecticide-treated bed-net coverage, we formulate an optimal control problem with malaria treatment and insecticide-treated nets as control functions. Using reasonable parameter values, numerical simulations of the optimal control suggest the possibility of eliminating malaria and reducing HIV prevalence significantly, within a short time horizon.

Optimization with artificial neural network systems - A mapping principle and a comparison to gradient based methods

NASA Technical Reports Server (NTRS)

Leong, Harrison Monfook

1988-01-01

General formulae for mapping optimization problems into systems of ordinary differential equations associated with artificial neural networks are presented. A comparison is made to optimization using gradient-search methods. The performance measure is the settling time from an initial state to a target state. A simple analytical example illustrates a situation where dynamical systems representing artificial neural network methods would settle faster than those representing gradient-search. Settling time was investigated for a more complicated optimization problem using computer simulations. The problem was a simplified version of a problem in medical imaging: determining loci of cerebral activity from electromagnetic measurements at the scalp. The simulations showed that gradient based systems typically settled 50 to 100 times faster than systems based on current neural network optimization methods.

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.

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 Meta-Memes Framework for Combinatorial Optimization

NASA Astrophysics Data System (ADS)

Song, Li Qin; Lim, Meng Hiot; Ong, Yew Soon

In this paper, we present a Neural Meta-Memes Framework (NMMF) for combinatorial optimization. NMMF is a framework which models basic optimization algorithms as memes and manages them dynamically when solving combinatorial problems. NMMF encompasses neural networks which serve as the overall planner/coordinator to balance the workload between memes. We show the efficacy of the proposed NMMF through empirical study on a class of combinatorial problem, the quadratic assignment problem (QAP).

The Optimal Forest Rotation: A Discussion and Annotated Bibliography

Treesearch

David H. Newman

1988-01-01

The literature contains six different criteria of the optimal forest rotation: (1) maximum single-rotation physical yield, (2) maximum single-rotation annual yield, (3) maximum single-rotation discounted net revenues, (4) maximum discounted net revenues from an infinite series of rotations, (5) maximum annual net revenues, and (6) maximum internal rate of return. First...

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.

Conversion of Continuous-Valued Deep Networks to Efficient Event-Driven Networks for Image Classification.

PubMed

Rueckauer, Bodo; Lungu, Iulia-Alexandra; Hu, Yuhuang; Pfeiffer, Michael; Liu, Shih-Chii

2017-01-01

Spiking neural networks (SNNs) can potentially offer an efficient way of doing inference because the neurons in the networks are sparsely activated and computations are event-driven. Previous work showed that simple continuous-valued deep Convolutional Neural Networks (CNNs) can be converted into accurate spiking equivalents. These networks did not include certain common operations such as max-pooling, softmax, batch-normalization and Inception-modules. This paper presents spiking equivalents of these operations therefore allowing conversion of nearly arbitrary CNN architectures. We show conversion of popular CNN architectures, including VGG-16 and Inception-v3, into SNNs that produce the best results reported to date on MNIST, CIFAR-10 and the challenging ImageNet dataset. SNNs can trade off classification error rate against the number of available operations whereas deep continuous-valued neural networks require a fixed number of operations to achieve their classification error rate. From the examples of LeNet for MNIST and BinaryNet for CIFAR-10, we show that with an increase in error rate of a few percentage points, the SNNs can achieve more than 2x reductions in operations compared to the original CNNs. This highlights the potential of SNNs in particular when deployed on power-efficient neuromorphic spiking neuron chips, for use in embedded applications.

Conversion of Continuous-Valued Deep Networks to Efficient Event-Driven Networks for Image Classification

PubMed Central

Rueckauer, Bodo; Lungu, Iulia-Alexandra; Hu, Yuhuang; Pfeiffer, Michael; Liu, Shih-Chii

2017-01-01

Spiking neural networks (SNNs) can potentially offer an efficient way of doing inference because the neurons in the networks are sparsely activated and computations are event-driven. Previous work showed that simple continuous-valued deep Convolutional Neural Networks (CNNs) can be converted into accurate spiking equivalents. These networks did not include certain common operations such as max-pooling, softmax, batch-normalization and Inception-modules. This paper presents spiking equivalents of these operations therefore allowing conversion of nearly arbitrary CNN architectures. We show conversion of popular CNN architectures, including VGG-16 and Inception-v3, into SNNs that produce the best results reported to date on MNIST, CIFAR-10 and the challenging ImageNet dataset. SNNs can trade off classification error rate against the number of available operations whereas deep continuous-valued neural networks require a fixed number of operations to achieve their classification error rate. From the examples of LeNet for MNIST and BinaryNet for CIFAR-10, we show that with an increase in error rate of a few percentage points, the SNNs can achieve more than 2x reductions in operations compared to the original CNNs. This highlights the potential of SNNs in particular when deployed on power-efficient neuromorphic spiking neuron chips, for use in embedded applications. PMID:29375284

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

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.

Influence of neural adaptation on dynamics and equilibrium state of neural activities in a ring neural network

NASA Astrophysics Data System (ADS)

Takiyama, Ken

2017-12-01

How neural adaptation affects neural information processing (i.e. the dynamics and equilibrium state of neural activities) is a central question in computational neuroscience. In my previous works, I analytically clarified the dynamics and equilibrium state of neural activities in a ring-type neural network model that is widely used to model the visual cortex, motor cortex, and several other brain regions. The neural dynamics and the equilibrium state in the neural network model corresponded to a Bayesian computation and statistically optimal multiple information integration, respectively, under a biologically inspired condition. These results were revealed in an analytically tractable manner; however, adaptation effects were not considered. Here, I analytically reveal how the dynamics and equilibrium state of neural activities in a ring neural network are influenced by spike-frequency adaptation (SFA). SFA is an adaptation that causes gradual inhibition of neural activity when a sustained stimulus is applied, and the strength of this inhibition depends on neural activities. I reveal that SFA plays three roles: (1) SFA amplifies the influence of external input in neural dynamics; (2) SFA allows the history of the external input to affect neural dynamics; and (3) the equilibrium state corresponds to the statistically optimal multiple information integration independent of the existence of SFA. In addition, the equilibrium state in a ring neural network model corresponds to the statistically optimal integration of multiple information sources under biologically inspired conditions, independent of the existence of SFA.

Genetic learning in rule-based and neural systems

NASA Technical Reports Server (NTRS)

Smith, Robert E.

1993-01-01

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

Construction of a Piezoresistive Neural Sensor Array

NASA Technical Reports Server (NTRS)

Carlson, W. B.; Schulze, W. A.; Pilgrim, P. M.

1996-01-01

The construction of a piezoresistive - piezoelectric sensor (or actuator) array is proposed using 'neural' connectivity for signal recognition and possible actuation functions. A closer integration of the sensor and decision functions is necessary in order to achieve intrinsic identification within the sensor. A neural sensor is the next logical step in development of truly 'intelligent' arrays. This proposal will integrate 1-3 polymer piezoresistors and MLC electroceramic devices for applications involving acoustic identification. The 'intelligent' piezoresistor -piezoelectric system incorporates printed resistors, composite resistors, and a feedback for the resetting of resistances. A model of a design is proposed in order to simulate electromechanical resistor interactions. The goal of optimizing a sensor geometry for improving device reliability, training, & signal identification capabilities is the goal of this work. At present, studies predict performance of a 'smart' device with a significant control of 'effective' compliance over a narrow pressure range due to a piezoresistor percolation threshold. An interesting possibility may be to use an array of control elements to shift the threshold function in order to change the level of resistance in a neural sensor array for identification, or, actuation applications. The proposed design employs elements of: (1) conductor loaded polymers for a 'fast' RC time constant response; and (2) multilayer ceramics for actuation or sensing and shifting of resistance in the polymer. Other material possibilities also exist using magnetoresistive layered systems for shifting the resistance. It is proposed to use a neural net configuration to test and to help study the possible changes required in the materials design of these devices. Numerical design models utilize electromechanical elements, in conjunction with structural elements in order to simulate piezoresistively controlled actuators and changes in resistance of sensors. The construction of these devices may show significant improvement in ability to interrogate signals and in the control of effective compliance. This work focuses on the development a variety of series/parallel interconnected piezoresistive control elements for the neural sensing function.

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.

Statistical-learning strategies generate only modestly performing predictive models for urinary symptoms following external beam radiotherapy of the prostate: A comparison of conventional and machine-learning methods

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

Yahya, Noorazrul, E-mail: noorazrul.yahya@research.uwa.edu.au; Ebert, Martin A.; Bulsara, Max

Purpose: Given the paucity of available data concerning radiotherapy-induced urinary toxicity, it is important to ensure derivation of the most robust models with superior predictive performance. This work explores multiple statistical-learning strategies for prediction of urinary symptoms following external beam radiotherapy of the prostate. Methods: The performance of logistic regression, elastic-net, support-vector machine, random forest, neural network, and multivariate adaptive regression splines (MARS) to predict urinary symptoms was analyzed using data from 754 participants accrued by TROG03.04-RADAR. Predictive features included dose-surface data, comorbidities, and medication-intake. Four symptoms were analyzed: dysuria, haematuria, incontinence, and frequency, each with three definitions (grade ≥more » 1, grade ≥ 2 and longitudinal) with event rate between 2.3% and 76.1%. Repeated cross-validations producing matched models were implemented. A synthetic minority oversampling technique was utilized in endpoints with rare events. Parameter optimization was performed on the training data. Area under the receiver operating characteristic curve (AUROC) was used to compare performance using sample size to detect differences of ≥0.05 at the 95% confidence level. Results: Logistic regression, elastic-net, random forest, MARS, and support-vector machine were the highest-performing statistical-learning strategies in 3, 3, 3, 2, and 1 endpoints, respectively. Logistic regression, MARS, elastic-net, random forest, neural network, and support-vector machine were the best, or were not significantly worse than the best, in 7, 7, 5, 5, 3, and 1 endpoints. The best-performing statistical model was for dysuria grade ≥ 1 with AUROC ± standard deviation of 0.649 ± 0.074 using MARS. For longitudinal frequency and dysuria grade ≥ 1, all strategies produced AUROC>0.6 while all haematuria endpoints and longitudinal incontinence models produced AUROC<0.6. Conclusions: Logistic regression and MARS were most likely to be the best-performing strategy for the prediction of urinary symptoms with elastic-net and random forest producing competitive results. The predictive power of the models was modest and endpoint-dependent. New features, including spatial dose maps, may be necessary to achieve better models.« less

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.

Green roof adoption in atlanta, georgia: the effects of building characteristics and subsidies on net private, public, and social benefits.

PubMed

Mullen, Jeffrey D; Lamsal, Madhur; Colson, Greg

2013-10-01

This research draws on and expands previous studies that have quantified the costs and benefits associated with conventional roofs versus green roofs. Using parameters from those studies to define alternative scenarios, we estimate from a private, public, and social perspective the costs and benefits of installing and maintaining an extensive green roof in Atlanta, GA. Results indicate net private benefits are a decreasing function of roof size and vary considerably across scenarios. In contrast, net public benefits are highly stable across scenarios, ranging from $32.49 to $32.90 m(-2). In addition, we evaluate two alternative subsidy regimes: (i) a general subsidy provided to every building that adopts a green roof and (ii) a targeted subsidy provided only to buildings for which net private benefits are negative but net public benefits are positive. In 6 of the 12 general subsidy scenarios the optimal public policy is not to offer a subsidy; in 5 scenarios the optimal subsidy rate is between $20 and $27 m(-2); and in 1 scenario the optimal rate is $5 m(-2). The optimal rate with a targeted subsidy is between $20 and $27 m(-2) in 11 scenarios and no subsidy is optimal in the twelfth. In most scenarios, a significant portion of net public benefits are generated by buildings for which net private benefits are positive. This suggests a policy focused on information dissemination and technical assistance may be more cost-effective than direct subsidy payments.

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.

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.

A Grey Wolf Optimizer for Modular Granular Neural Networks for Human Recognition

PubMed Central

Sánchez, Daniela; Melin, Patricia

2017-01-01

A grey wolf optimizer for modular neural network (MNN) with a granular approach is proposed. The proposed method performs optimal granulation of data and design of modular neural networks architectures to perform human recognition, and to prove its effectiveness benchmark databases of ear, iris, and face biometric measures are used to perform tests and comparisons against other works. The design of a modular granular neural network (MGNN) consists in finding optimal parameters of its architecture; these parameters are the number of subgranules, percentage of data for the training phase, learning algorithm, goal error, number of hidden layers, and their number of neurons. Nowadays, there is a great variety of approaches and new techniques within the evolutionary computing area, and these approaches and techniques have emerged to help find optimal solutions to problems or models and bioinspired algorithms are part of this area. In this work a grey wolf optimizer is proposed for the design of modular granular neural networks, and the results are compared against a genetic algorithm and a firefly algorithm in order to know which of these techniques provides better results when applied to human recognition. PMID:28894461

A Grey Wolf Optimizer for Modular Granular Neural Networks for Human Recognition.

PubMed

Sánchez, Daniela; Melin, Patricia; Castillo, Oscar

2017-01-01

A grey wolf optimizer for modular neural network (MNN) with a granular approach is proposed. The proposed method performs optimal granulation of data and design of modular neural networks architectures to perform human recognition, and to prove its effectiveness benchmark databases of ear, iris, and face biometric measures are used to perform tests and comparisons against other works. The design of a modular granular neural network (MGNN) consists in finding optimal parameters of its architecture; these parameters are the number of subgranules, percentage of data for the training phase, learning algorithm, goal error, number of hidden layers, and their number of neurons. Nowadays, there is a great variety of approaches and new techniques within the evolutionary computing area, and these approaches and techniques have emerged to help find optimal solutions to problems or models and bioinspired algorithms are part of this area. In this work a grey wolf optimizer is proposed for the design of modular granular neural networks, and the results are compared against a genetic algorithm and a firefly algorithm in order to know which of these techniques provides better results when applied to human recognition.

The role of under-determined approximations in engineering and science application

NASA Technical Reports Server (NTRS)

Carpenter, William C.

1992-01-01

There is currently a great deal of interest in using response surfaces in the optimization of aircraft performance. The objective function and/or constraint equations involved in these optimization problems may come from numerous disciplines such as structures, aerodynamics, environmental engineering, etc. In each of these disciplines, the mathematical complexity of the governing equations usually dictates that numerical results be obtained from large computer programs such as a finite element method program. Thus, when performing optimization studies, response surfaces are a convenient way of transferring information from the various disciplines to the optimization algorithm as opposed to bringing all the sundry computer programs together in a massive computer code. Response surfaces offer another advantage in the optimization of aircraft structures. A characteristic of these types of optimization problems is that evaluation of the objective function and response equations (referred to as a functional evaluation) can be very expensive in a computational sense. Because of the computational expense in obtaining functional evaluations, the present study was undertaken to investigate under-determinined approximations. An under-determined approximation is one in which there are fewer training pairs (pieces of information about a function) than there are undetermined parameters (coefficients or weights) associated with the approximation. Both polynomial approximations and neural net approximations were examined. Three main example problems were investigated: (1) a function of one design variable was considered; (2) a function of two design variables was considered; and (3) a 35 bar truss with 4 design variables was considered.

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.

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.

Deep Flare Net (DeFN) Model for Solar Flare Prediction

NASA Astrophysics Data System (ADS)

Nishizuka, N.; Sugiura, K.; Kubo, Y.; Den, M.; Ishii, M.

2018-05-01

We developed a solar flare prediction model using a deep neural network (DNN) named Deep Flare Net (DeFN). This model can calculate the probability of flares occurring in the following 24 hr in each active region, which is used to determine the most likely maximum classes of flares via a binary classification (e.g., ≥M class versus

Active Self-Paced Learning for Cost-Effective and Progressive Face Identification.

PubMed

Lin, Liang; Wang, Keze; Meng, Deyu; Zuo, Wangmeng; Zhang, Lei

2018-01-01

This paper aims to develop a novel cost-effective framework for face identification, which progressively maintains a batch of classifiers with the increasing face images of different individuals. By naturally combining two recently rising techniques: active learning (AL) and self-paced learning (SPL), our framework is capable of automatically annotating new instances and incorporating them into training under weak expert recertification. We first initialize the classifier using a few annotated samples for each individual, and extract image features using the convolutional neural nets. Then, a number of candidates are selected from the unannotated samples for classifier updating, in which we apply the current classifiers ranking the samples by the prediction confidence. In particular, our approach utilizes the high-confidence and low-confidence samples in the self-paced and the active user-query way, respectively. The neural nets are later fine-tuned based on the updated classifiers. Such heuristic implementation is formulated as solving a concise active SPL optimization problem, which also advances the SPL development by supplementing a rational dynamic curriculum constraint. The new model finely accords with the "instructor-student-collaborative" learning mode in human education. The advantages of this proposed framework are two-folds: i) The required number of annotated samples is significantly decreased while the comparable performance is guaranteed. A dramatic reduction of user effort is also achieved over other state-of-the-art active learning techniques. ii) The mixture of SPL and AL effectively improves not only the classifier accuracy compared to existing AL/SPL methods but also the robustness against noisy data. We evaluate our framework on two challenging datasets, which include hundreds of persons under diverse conditions, and demonstrate very promising results. Please find the code of this project at: http://hcp.sysu.edu.cn/projects/aspl/.

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.

Finding the Optimal Nets for Self-Folding Kirigami

NASA Astrophysics Data System (ADS)

Araújo, N. A. M.; da Costa, R. A.; Dorogovtsev, S. N.; Mendes, J. F. F.

2018-05-01

Three-dimensional shells can be synthesized from the spontaneous self-folding of two-dimensional templates of interconnected panels, called nets. However, some nets are more likely to self-fold into the desired shell under random movements. The optimal nets are the ones that maximize the number of vertex connections, i.e., vertices that have only two of its faces cut away from each other in the net. Previous methods for finding such nets are based on random search, and thus, they do not guarantee the optimal solution. Here, we propose a deterministic procedure. We map the connectivity of the shell into a shell graph, where the nodes and links of the graph represent the vertices and edges of the shell, respectively. Identifying the nets that maximize the number of vertex connections corresponds to finding the set of maximum leaf spanning trees of the shell graph. This method allows us not only to design the self-assembly of much larger shell structures but also to apply additional design criteria, as a complete catalog of the maximum leaf spanning trees is obtained.

Neural decoding with kernel-based metric learning.

PubMed

Brockmeier, Austin J; Choi, John S; Kriminger, Evan G; Francis, Joseph T; Principe, Jose C

2014-06-01

In studies of the nervous system, the choice of metric for the neural responses is a pivotal assumption. For instance, a well-suited distance metric enables us to gauge the similarity of neural responses to various stimuli and assess the variability of responses to a repeated stimulus-exploratory steps in understanding how the stimuli are encoded neurally. Here we introduce an approach where the metric is tuned for a particular neural decoding task. Neural spike train metrics have been used to quantify the information content carried by the timing of action potentials. While a number of metrics for individual neurons exist, a method to optimally combine single-neuron metrics into multineuron, or population-based, metrics is lacking. We pose the problem of optimizing multineuron metrics and other metrics using centered alignment, a kernel-based dependence measure. The approach is demonstrated on invasively recorded neural data consisting of both spike trains and local field potentials. The experimental paradigm consists of decoding the location of tactile stimulation on the forepaws of anesthetized rats. We show that the optimized metrics highlight the distinguishing dimensions of the neural response, significantly increase the decoding accuracy, and improve nonlinear dimensionality reduction methods for exploratory neural analysis.

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).

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.

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

Analog Processor To Solve Optimization Problems

NASA Technical Reports Server (NTRS)

Duong, Tuan A.; Eberhardt, Silvio P.; Thakoor, Anil P.

1993-01-01

Proposed analog processor solves "traveling-salesman" problem, considered paradigm of global-optimization problems involving routing or allocation of resources. Includes electronic neural network and auxiliary circuitry based partly on concepts described in "Neural-Network Processor Would Allocate Resources" (NPO-17781) and "Neural Network Solves 'Traveling-Salesman' Problem" (NPO-17807). Processor based on highly parallel computing solves problem in significantly less time.

Big Data: A Parallel Particle Swarm Optimization-Back-Propagation Neural Network Algorithm Based on MapReduce.

PubMed

Cao, Jianfang; Cui, Hongyan; Shi, Hao; Jiao, Lijuan

2016-01-01

A back-propagation (BP) neural network can solve complicated random nonlinear mapping problems; therefore, it can be applied to a wide range of problems. However, as the sample size increases, the time required to train BP neural networks becomes lengthy. Moreover, the classification accuracy decreases as well. To improve the classification accuracy and runtime efficiency of the BP neural network algorithm, we proposed a parallel design and realization method for a particle swarm optimization (PSO)-optimized BP neural network based on MapReduce on the Hadoop platform using both the PSO algorithm and a parallel design. The PSO algorithm was used to optimize the BP neural network's initial weights and thresholds and improve the accuracy of the classification algorithm. The MapReduce parallel programming model was utilized to achieve parallel processing of the BP algorithm, thereby solving the problems of hardware and communication overhead when the BP neural network addresses big data. Datasets on 5 different scales were constructed using the scene image library from the SUN Database. The classification accuracy of the parallel PSO-BP neural network algorithm is approximately 92%, and the system efficiency is approximately 0.85, which presents obvious advantages when processing big data. The algorithm proposed in this study demonstrated both higher classification accuracy and improved time efficiency, which represents a significant improvement obtained from applying parallel processing to an intelligent algorithm on big data.

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.

Saliency Detection and Deep Learning-Based Wildfire Identification in UAV Imagery.

PubMed

Zhao, Yi; Ma, Jiale; Li, Xiaohui; Zhang, Jie

2018-02-27

An unmanned aerial vehicle (UAV) equipped with global positioning systems (GPS) can provide direct georeferenced imagery, mapping an area with high resolution. So far, the major difficulty in wildfire image classification is the lack of unified identification marks, the fire features of color, shape, texture (smoke, flame, or both) and background can vary significantly from one scene to another. Deep learning (e.g., DCNN for Deep Convolutional Neural Network) is very effective in high-level feature learning, however, a substantial amount of training images dataset is obligatory in optimizing its weights value and coefficients. In this work, we proposed a new saliency detection algorithm for fast location and segmentation of core fire area in aerial images. As the proposed method can effectively avoid feature loss caused by direct resizing; it is used in data augmentation and formation of a standard fire image dataset 'UAV_Fire'. A 15-layered self-learning DCNN architecture named 'Fire_Net' is then presented as a self-learning fire feature exactor and classifier. We evaluated different architectures and several key parameters (drop out ratio, batch size, etc.) of the DCNN model regarding its validation accuracy. The proposed architecture outperformed previous methods by achieving an overall accuracy of 98%. Furthermore, 'Fire_Net' guarantied an average processing speed of 41.5 ms per image for real-time wildfire inspection. To demonstrate its practical utility, Fire_Net is tested on 40 sampled images in wildfire news reports and all of them have been accurately identified.

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.

A novel model of motor learning capable of developing an optimal movement control law online from scratch.

PubMed

Shimansky, Yury P; Kang, Tao; He, Jiping

2004-02-01

A computational model of a learning system (LS) is described that acquires knowledge and skill necessary for optimal control of a multisegmental limb dynamics (controlled object or CO), starting from "knowing" only the dimensionality of the object's state space. It is based on an optimal control problem setup different from that of reinforcement learning. The LS solves the optimal control problem online while practicing the manipulation of CO. The system's functional architecture comprises several adaptive components, each of which incorporates a number of mapping functions approximated based on artificial neural nets. Besides the internal model of the CO's dynamics and adaptive controller that computes the control law, the LS includes a new type of internal model, the minimal cost (IM(mc)) of moving the controlled object between a pair of states. That internal model appears critical for the LS's capacity to develop an optimal movement trajectory. The IM(mc) interacts with the adaptive controller in a cooperative manner. The controller provides an initial approximation of an optimal control action, which is further optimized in real time based on the IM(mc). The IM(mc) in turn provides information for updating the controller. The LS's performance was tested on the task of center-out reaching to eight randomly selected targets with a 2DOF limb model. The LS reached an optimal level of performance in a few tens of trials. It also quickly adapted to movement perturbations produced by two different types of external force field. The results suggest that the proposed design of a self-optimized control system can serve as a basis for the modeling of motor learning that includes the formation and adaptive modification of the plan of a goal-directed movement.

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 dynamic optimization for control systems. I. Background.

PubMed

Seong, C Y; Widrow, B

2001-01-01

The paper presents neural dynamic optimization (NDO) as a method of optimal feedback control for nonlinear multi-input-multi-output (MIMO) systems. The main feature of NDO is that it enables neural networks to approximate the optimal feedback solution whose existence dynamic programming (DP) justifies, thereby reducing the complexities of computation and storage problems of the classical methods such as DP. This paper mainly describes the background and motivations for the development of NDO, while the two other subsequent papers of this topic present the theory of NDO and demonstrate the method with several applications including control of autonomous vehicles and of a robot arm, respectively.

Neural dynamic optimization for control systems.III. Applications.

PubMed

Seong, C Y; Widrow, B

2001-01-01

For pt.II. see ibid., p. 490-501. The paper presents neural dynamic optimization (NDO) as a method of optimal feedback control for nonlinear multi-input-multi-output (MIMO) systems. The main feature of NDO is that it enables neural networks to approximate the optimal feedback solution whose existence dynamic programming (DP) justifies, thereby reducing the complexities of computation and storage problems of the classical methods such as DP. This paper demonstrates NDO with several applications including control of autonomous vehicles and of a robot-arm, while the two other companion papers of this topic describes the background for the development of NDO and present the theory of the method, respectively.

Neural dynamic optimization for control systems.II. Theory.

PubMed

Seong, C Y; Widrow, B

2001-01-01

The paper presents neural dynamic optimization (NDO) as a method of optimal feedback control for nonlinear multi-input-multi-output (MIMO) systems. The main feature of NDO is that it enables neural networks to approximate the optimal feedback solution whose existence dynamic programming (DP) justifies, thereby reducing the complexities of computation and storage problems of the classical methods such as DP. This paper mainly describes the theory of NDO, while the two other companion papers of this topic explain the background for the development of NDO and demonstrate the method with several applications including control of autonomous vehicles and of a robot arm, respectively.

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 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.

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.

Optimal control, optimization and asymptotic analysis of Purcell's microswimmer model

NASA Astrophysics Data System (ADS)

Wiezel, Oren; Or, Yizhar

2016-11-01

Purcell's swimmer (1977) is a classic model of a three-link microswimmer that moves by performing periodic shape changes. Becker et al. (2003) showed that the swimmer's direction of net motion is reversed upon increasing the stroke amplitude of joint angles. Tam and Hosoi (2007) used numerical optimization in order to find optimal gaits for maximizing either net displacement or Lighthill's energetic efficiency. In our work, we analytically derive leading-order expressions as well as next-order corrections for both net displacement and energetic efficiency of Purcell's microswimmer. Using these expressions enables us to explicitly show the reversal in direction of motion, as well as obtaining an estimate for the optimal stroke amplitude. We also find the optimal swimmer's geometry for maximizing either displacement or energetic efficiency. Additionally, the gait optimization problem is revisited and analytically formulated as an optimal control system with only two state variables, which can be solved using Pontryagin's maximum principle. It can be shown that the optimal solution must follow a "singular arc". Numerical solution of the boundary value problem is obtained, which exactly reproduces Tam and Hosoi's optimal gait.

Two-step optimization of pressure and recovery of reverse osmosis desalination process.

PubMed

Liang, Shuang; Liu, Cui; Song, Lianfa

2009-05-01

Driving pressure and recovery are two primary design variables of a reverse osmosis process that largely determine the total cost of seawater and brackish water desalination. A two-step optimization procedure was developed in this paper to determine the values of driving pressure and recovery that minimize the total cost of RO desalination. It was demonstrated that the optimal net driving pressure is solely determined by the electricity price and the membrane price index, which is a lumped parameter to collectively reflect membrane price, resistance, and service time. On the other hand, the optimal recovery is determined by the electricity price, initial osmotic pressure, and costs for pretreatment of raw water and handling of retentate. Concise equations were derived for the optimal net driving pressure and recovery. The dependences of the optimal net driving pressure and recovery on the electricity price, membrane price, and costs for raw water pretreatment and retentate handling were discussed.

Molnets: An Artificial Chemistry Based on Neural Networks

NASA Technical Reports Server (NTRS)

Colombano, Silvano; Luk, Johnny; Segovia-Juarez, Jose L.; Lohn, Jason; Clancy, Daniel (Technical Monitor)

2002-01-01

The fundamental problem in the evolution of matter is to understand how structure-function relationships are formed and increase in complexity from the molecular level all the way to a genetic system. We have created a system where structure-function relationships arise naturally and without the need of ad hoc function assignments to given structures. The idea was inspired by neural networks, where the structure of the net embodies specific computational properties. In this system networks interact with other networks to create connections between the inputs of one net and the outputs of another. The newly created net then recomputes its own synaptic weights, based on anti-hebbian rules. As a result some connections may be cut, and multiple nets can emerge as products of a 'reaction'. The idea is to study emergent reaction behaviors, based on simple rules that constitute a pseudophysics of the system. These simple rules are parameterized to produce behaviors that emulate chemical reactions. We find that these simple rules show a gradual increase in the size and complexity of molecules. We have been building a virtual artificial chemistry laboratory for discovering interesting reactions and for testing further ideas on the evolution of primitive molecules. Some of these ideas include the potential effect of membranes and selective diffusion according to molecular size.

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.

Comparison of artificial intelligence classifiers for SIP attack data

NASA Astrophysics Data System (ADS)

Safarik, Jakub; Slachta, Jiri

2016-05-01

Honeypot application is a source of valuable data about attacks on the network. We run several SIP honeypots in various computer networks, which are separated geographically and logically. Each honeypot runs on public IP address and uses standard SIP PBX ports. All information gathered via honeypot is periodically sent to the centralized server. This server classifies all attack data by neural network algorithm. The paper describes optimizations of a neural network classifier, which lower the classification error. The article contains the comparison of two neural network algorithm used for the classification of validation data. The first is the original implementation of the neural network described in recent work; the second neural network uses further optimizations like input normalization or cross-entropy cost function. We also use other implementations of neural networks and machine learning classification algorithms. The comparison test their capabilities on validation data to find the optimal classifier. The article result shows promise for further development of an accurate SIP attack classification engine.

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.

Big Data: A Parallel Particle Swarm Optimization-Back-Propagation Neural Network Algorithm Based on MapReduce

PubMed Central

Cao, Jianfang; Cui, Hongyan; Shi, Hao; Jiao, Lijuan

2016-01-01

A back-propagation (BP) neural network can solve complicated random nonlinear mapping problems; therefore, it can be applied to a wide range of problems. However, as the sample size increases, the time required to train BP neural networks becomes lengthy. Moreover, the classification accuracy decreases as well. To improve the classification accuracy and runtime efficiency of the BP neural network algorithm, we proposed a parallel design and realization method for a particle swarm optimization (PSO)-optimized BP neural network based on MapReduce on the Hadoop platform using both the PSO algorithm and a parallel design. The PSO algorithm was used to optimize the BP neural network’s initial weights and thresholds and improve the accuracy of the classification algorithm. The MapReduce parallel programming model was utilized to achieve parallel processing of the BP algorithm, thereby solving the problems of hardware and communication overhead when the BP neural network addresses big data. Datasets on 5 different scales were constructed using the scene image library from the SUN Database. The classification accuracy of the parallel PSO-BP neural network algorithm is approximately 92%, and the system efficiency is approximately 0.85, which presents obvious advantages when processing big data. The algorithm proposed in this study demonstrated both higher classification accuracy and improved time efficiency, which represents a significant improvement obtained from applying parallel processing to an intelligent algorithm on big data. PMID:27304987

RBF neural network based PI pitch controller for a class of 5-MW wind turbines using particle swarm optimization algorithm.

PubMed

Poultangari, Iman; Shahnazi, Reza; Sheikhan, Mansour

2012-09-01

In order to control the pitch angle of blades in wind turbines, commonly the proportional and integral (PI) controller due to its simplicity and industrial usability is employed. The neural networks and evolutionary algorithms are tools that provide a suitable ground to determine the optimal PI gains. In this paper, a radial basis function (RBF) neural network based PI controller is proposed for collective pitch control (CPC) of a 5-MW wind turbine. In order to provide an optimal dataset to train the RBF neural network, particle swarm optimization (PSO) evolutionary algorithm is used. The proposed method does not need the complexities, nonlinearities and uncertainties of the system under control. The simulation results show that the proposed controller has satisfactory performance. Copyright © 2012 ISA. Published by Elsevier Ltd. All rights reserved.

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.

Achieving Consistent Near-Optimal Pattern Recognition Accuracy Using Particle Swarm Optimization to Pre-Train Artificial Neural Networks

ERIC Educational Resources Information Center

Nikelshpur, Dmitry O.

2014-01-01

Similar to mammalian brains, Artificial Neural Networks (ANN) are universal approximators, capable of yielding near-optimal solutions to a wide assortment of problems. ANNs are used in many fields including medicine, internet security, engineering, retail, robotics, warfare, intelligence control, and finance. "ANNs have a tendency to get…

Finite Set Control Transcription for Optimal Control Applications

DTIC Science & Technology

2009-05-01

Figures 1.1 The Parameters of x . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 10 2.1 Categories of Optimization Algorithms ...Programming (NLP) algorithm , such as SNOPT2 (hereafter, called the optimizer). The Finite Set Control Transcription (FSCT) method is essentially a...artificial neural networks, ge- netic algorithms , or combinations thereof for analysis.4,5 Indeed, an actual biological neural network is an example of

Neural Network Prediction of New Aircraft Design Coefficients

NASA Technical Reports Server (NTRS)

Norgaard, Magnus; Jorgensen, Charles C.; Ross, James C.

1997-01-01

This paper discusses a neural network tool for more effective aircraft design evaluations during wind tunnel tests. Using a hybrid neural network optimization method, we have produced fast and reliable predictions of aerodynamical coefficients, found optimal flap settings, and flap schedules. For validation, the tool was tested on a 55% scale model of the USAF/NASA Subsonic High Alpha Research Concept aircraft (SHARC). Four different networks were trained to predict coefficients of lift, drag, moment of inertia, and lift drag ratio (C(sub L), C(sub D), C(sub M), and L/D) from angle of attack and flap settings. The latter network was then used to determine an overall optimal flap setting and for finding optimal flap schedules.

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.

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.

Study on loading path optimization of internal high pressure forming process

NASA Astrophysics Data System (ADS)

Jiang, Shufeng; Zhu, Hengda; Gao, Fusheng

2017-09-01

In the process of internal high pressure forming, there is no formula to describe the process parameters and forming results. The article use numerical simulation to obtain several input parameters and corresponding output result, use the BP neural network to found their mapping relationship, and with weighted summing method make each evaluating parameters to set up a formula which can evaluate quality. Then put the training BP neural network into the particle swarm optimization, and take the evaluating formula of the quality as adapting formula of particle swarm optimization, finally do the optimization and research at the range of each parameters. The results show that the parameters obtained by the BP neural network algorithm and the particle swarm optimization algorithm can meet the practical requirements. The method can solve the optimization of the process parameters in the internal high pressure forming process.

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.

Feature Extraction and Selection Strategies for Automated Target Recognition

NASA Technical Reports Server (NTRS)

Greene, W. Nicholas; Zhang, Yuhan; Lu, Thomas T.; Chao, Tien-Hsin

2010-01-01

Several feature extraction and selection methods for an existing automatic target recognition (ATR) system using JPLs Grayscale Optical Correlator (GOC) and Optimal Trade-Off Maximum Average Correlation Height (OT-MACH) filter were tested using MATLAB. The ATR system is composed of three stages: a cursory region of-interest (ROI) search using the GOC and OT-MACH filter, a feature extraction and selection stage, and a final classification stage. Feature extraction and selection concerns transforming potential target data into more useful forms as well as selecting important subsets of that data which may aide in detection and classification. The strategies tested were built around two popular extraction methods: Principal Component Analysis (PCA) and Independent Component Analysis (ICA). Performance was measured based on the classification accuracy and free-response receiver operating characteristic (FROC) output of a support vector machine(SVM) and a neural net (NN) classifier.

Feature extraction and selection strategies for automated target recognition

NASA Astrophysics Data System (ADS)

Greene, W. Nicholas; Zhang, Yuhan; Lu, Thomas T.; Chao, Tien-Hsin

2010-04-01

Several feature extraction and selection methods for an existing automatic target recognition (ATR) system using JPLs Grayscale Optical Correlator (GOC) and Optimal Trade-Off Maximum Average Correlation Height (OT-MACH) filter were tested using MATLAB. The ATR system is composed of three stages: a cursory regionof- interest (ROI) search using the GOC and OT-MACH filter, a feature extraction and selection stage, and a final classification stage. Feature extraction and selection concerns transforming potential target data into more useful forms as well as selecting important subsets of that data which may aide in detection and classification. The strategies tested were built around two popular extraction methods: Principal Component Analysis (PCA) and Independent Component Analysis (ICA). Performance was measured based on the classification accuracy and free-response receiver operating characteristic (FROC) output of a support vector machine(SVM) and a neural net (NN) classifier.

PrAS: Prediction of amidation sites using multiple feature extraction.

PubMed

Wang, Tong; Zheng, Wei; Wuyun, Qiqige; Wu, Zhenfeng; Ruan, Jishou; Hu, Gang; Gao, Jianzhao

2017-02-01

Amidation plays an important role in a variety of pathological processes and serious diseases like neural dysfunction and hypertension. However, identification of protein amidation sites through traditional experimental methods is time consuming and expensive. In this paper, we proposed a novel predictor for Prediction of Amidation Sites (PrAS), which is the first software package for academic users. The method incorporated four representative feature types, which are position-based features, physicochemical and biochemical properties features, predicted structure-based features and evolutionary information features. A novel feature selection method, positive contribution feature selection was proposed to optimize features. PrAS achieved AUC of 0.96, accuracy of 92.1%, sensitivity of 81.2%, specificity of 94.9% and MCC of 0.76 on the independent test set. PrAS is freely available at https://sourceforge.net/p/praspkg. Copyright © 2016 Elsevier Ltd. All rights reserved.

Adaptive Optimization of Aircraft Engine Performance Using Neural Networks

NASA Technical Reports Server (NTRS)

Simon, Donald L.; Long, Theresa W.

1995-01-01

Preliminary results are presented on the development of an adaptive neural network based control algorithm to enhance aircraft engine performance. This work builds upon a previous National Aeronautics and Space Administration (NASA) effort known as Performance Seeking Control (PSC). PSC is an adaptive control algorithm which contains a model of the aircraft's propulsion system which is updated on-line to match the operation of the aircraft's actual propulsion system. Information from the on-line model is used to adapt the control system during flight to allow optimal operation of the aircraft's propulsion system (inlet, engine, and nozzle) to improve aircraft engine performance without compromising reliability or operability. Performance Seeking Control has been shown to yield reductions in fuel flow, increases in thrust, and reductions in engine fan turbine inlet temperature. The neural network based adaptive control, like PSC, will contain a model of the propulsion system which will be used to calculate optimal control commands on-line. Hopes are that it will be able to provide some additional benefits above and beyond those of PSC. The PSC algorithm is computationally intensive, it is valid only at near steady-state flight conditions, and it has no way to adapt or learn on-line. These issues are being addressed in the development of the optimal neural controller. Specialized neural network processing hardware is being developed to run the software, the algorithm will be valid at steady-state and transient conditions, and will take advantage of the on-line learning capability of neural networks. Future plans include testing the neural network software and hardware prototype against an aircraft engine simulation. In this paper, the proposed neural network software and hardware is described and preliminary neural network training results are presented.

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.

Forecasting outpatient visits using empirical mode decomposition coupled with back-propagation artificial neural networks optimized by particle swarm optimization

PubMed Central

Huang, Daizheng; Wu, Zhihui

2017-01-01

Accurately predicting the trend of outpatient visits by mathematical modeling can help policy makers manage hospitals effectively, reasonably organize schedules for human resources and finances, and appropriately distribute hospital material resources. In this study, a hybrid method based on empirical mode decomposition and back-propagation artificial neural networks optimized by particle swarm optimization is developed to forecast outpatient visits on the basis of monthly numbers. The data outpatient visits are retrieved from January 2005 to December 2013 and first obtained as the original time series. Second, the original time series is decomposed into a finite and often small number of intrinsic mode functions by the empirical mode decomposition technique. Third, a three-layer back-propagation artificial neural network is constructed to forecast each intrinsic mode functions. To improve network performance and avoid falling into a local minimum, particle swarm optimization is employed to optimize the weights and thresholds of back-propagation artificial neural networks. Finally, the superposition of forecasting results of the intrinsic mode functions is regarded as the ultimate forecasting value. Simulation indicates that the proposed method attains a better performance index than the other four methods. PMID:28222194

Forecasting outpatient visits using empirical mode decomposition coupled with back-propagation artificial neural networks optimized by particle swarm optimization.

PubMed

Huang, Daizheng; Wu, Zhihui

2017-01-01

Accurately predicting the trend of outpatient visits by mathematical modeling can help policy makers manage hospitals effectively, reasonably organize schedules for human resources and finances, and appropriately distribute hospital material resources. In this study, a hybrid method based on empirical mode decomposition and back-propagation artificial neural networks optimized by particle swarm optimization is developed to forecast outpatient visits on the basis of monthly numbers. The data outpatient visits are retrieved from January 2005 to December 2013 and first obtained as the original time series. Second, the original time series is decomposed into a finite and often small number of intrinsic mode functions by the empirical mode decomposition technique. Third, a three-layer back-propagation artificial neural network is constructed to forecast each intrinsic mode functions. To improve network performance and avoid falling into a local minimum, particle swarm optimization is employed to optimize the weights and thresholds of back-propagation artificial neural networks. Finally, the superposition of forecasting results of the intrinsic mode functions is regarded as the ultimate forecasting value. Simulation indicates that the proposed method attains a better performance index than the other four methods.

A new optimized GA-RBF neural network algorithm.

PubMed

Jia, Weikuan; Zhao, Dean; Shen, Tian; Su, Chunyang; Hu, Chanli; Zhao, Yuyan

2014-01-01

When confronting the complex problems, radial basis function (RBF) neural network has the advantages of adaptive and self-learning ability, but it is difficult to determine the number of hidden layer neurons, and the weights learning ability from hidden layer to the output layer is low; these deficiencies easily lead to decreasing learning ability and recognition precision. Aiming at this problem, we propose a new optimized RBF neural network algorithm based on genetic algorithm (GA-RBF algorithm), which uses genetic algorithm to optimize the weights and structure of RBF neural network; it chooses new ways of hybrid encoding and optimizing simultaneously. Using the binary encoding encodes the number of the hidden layer's neurons and using real encoding encodes the connection weights. Hidden layer neurons number and connection weights are optimized simultaneously in the new algorithm. However, the connection weights optimization is not complete; we need to use least mean square (LMS) algorithm for further leaning, and finally get a new algorithm model. Using two UCI standard data sets to test the new algorithm, the results show that the new algorithm improves the operating efficiency in dealing with complex problems and also improves the recognition precision, which proves that the new algorithm is valid.

Optimizing Photosynthetic and Respiratory Parameters Based on the Seasonal Variation Pattern in Regional Net Ecosystem Productivity Obtained from Atmospheric Inversion

NASA Astrophysics Data System (ADS)

Chen, Z.; Chen, J.; Zheng, X.; Jiang, F.; Zhang, S.; Ju, W.; Yuan, W.; Mo, G.

2014-12-01

In this study, we explore the feasibility of optimizing ecosystem photosynthetic and respiratory parameters from the seasonal variation pattern of the net carbon flux. An optimization scheme is proposed to estimate two key parameters (Vcmax and Q10) by exploiting the seasonal variation in the net ecosystem carbon flux retrieved by an atmospheric inversion system. This scheme is implemented to estimate Vcmax and Q10 of the Boreal Ecosystem Productivity Simulator (BEPS) to improve its NEP simulation in the Boreal North America (BNA) region. Simultaneously, in-situ NEE observations at six eddy covariance sites are used to evaluate the NEE simulations. The results show that the performance of the optimized BEPS is superior to that of the BEPS with the default parameter values. These results have the implication on using atmospheric CO2 data for optimizing ecosystem parameters through atmospheric inversion or data assimilation techniques.

Optimal feedback control successfully explains changes in neural modulations during experiments with brain-machine interfaces.

PubMed

Benyamini, Miri; Zacksenhouse, Miriam

2015-01-01

Recent experiments with brain-machine-interfaces (BMIs) indicate that the extent of neural modulations increased abruptly upon starting to operate the interface, and especially after the monkey stopped moving its hand. In contrast, neural modulations that are correlated with the kinematics of the movement remained relatively unchanged. Here we demonstrate that similar changes are produced by simulated neurons that encode the relevant signals generated by an optimal feedback controller during simulated BMI experiments. The optimal feedback controller relies on state estimation that integrates both visual and proprioceptive feedback with prior estimations from an internal model. The processing required for optimal state estimation and control were conducted in the state-space, and neural recording was simulated by modeling two populations of neurons that encode either only the estimated state or also the control signal. Spike counts were generated as realizations of doubly stochastic Poisson processes with linear tuning curves. The model successfully reconstructs the main features of the kinematics and neural activity during regular reaching movements. Most importantly, the activity of the simulated neurons successfully reproduces the observed changes in neural modulations upon switching to brain control. Further theoretical analysis and simulations indicate that increasing the process noise during normal reaching movement results in similar changes in neural modulations. Thus, we conclude that the observed changes in neural modulations during BMI experiments can be attributed to increasing process noise associated with the imperfect BMI filter, and, more directly, to the resulting increase in the variance of the encoded signals associated with state estimation and the required control signal.

Optimal feedback control successfully explains changes in neural modulations during experiments with brain-machine interfaces

PubMed Central

Benyamini, Miri; Zacksenhouse, Miriam

2015-01-01

Recent experiments with brain-machine-interfaces (BMIs) indicate that the extent of neural modulations increased abruptly upon starting to operate the interface, and especially after the monkey stopped moving its hand. In contrast, neural modulations that are correlated with the kinematics of the movement remained relatively unchanged. Here we demonstrate that similar changes are produced by simulated neurons that encode the relevant signals generated by an optimal feedback controller during simulated BMI experiments. The optimal feedback controller relies on state estimation that integrates both visual and proprioceptive feedback with prior estimations from an internal model. The processing required for optimal state estimation and control were conducted in the state-space, and neural recording was simulated by modeling two populations of neurons that encode either only the estimated state or also the control signal. Spike counts were generated as realizations of doubly stochastic Poisson processes with linear tuning curves. The model successfully reconstructs the main features of the kinematics and neural activity during regular reaching movements. Most importantly, the activity of the simulated neurons successfully reproduces the observed changes in neural modulations upon switching to brain control. Further theoretical analysis and simulations indicate that increasing the process noise during normal reaching movement results in similar changes in neural modulations. Thus, we conclude that the observed changes in neural modulations during BMI experiments can be attributed to increasing process noise associated with the imperfect BMI filter, and, more directly, to the resulting increase in the variance of the encoded signals associated with state estimation and the required control signal. PMID:26042002

A Subsonic Aircraft Design Optimization With Neural Network and Regression Approximators

NASA Technical Reports Server (NTRS)

Patnaik, Surya N.; Coroneos, Rula M.; Guptill, James D.; Hopkins, Dale A.; Haller, William J.

2004-01-01

The Flight-Optimization-System (FLOPS) code encountered difficulty in analyzing a subsonic aircraft. The limitation made the design optimization problematic. The deficiencies have been alleviated through use of neural network and regression approximations. The insight gained from using the approximators is discussed in this paper. The FLOPS code is reviewed. Analysis models are developed and validated for each approximator. The regression method appears to hug the data points, while the neural network approximation follows a mean path. For an analysis cycle, the approximate model required milliseconds of central processing unit (CPU) time versus seconds by the FLOPS code. Performance of the approximators was satisfactory for aircraft analysis. A design optimization capability has been created by coupling the derived analyzers to the optimization test bed CometBoards. The approximators were efficient reanalysis tools in the aircraft design optimization. Instability encountered in the FLOPS analyzer was eliminated. The convergence characteristics were improved for the design optimization. The CPU time required to calculate the optimum solution, measured in hours with the FLOPS code was reduced to minutes with the neural network approximation and to seconds with the regression method. Generation of the approximators required the manipulation of a very large quantity of data. Design sensitivity with respect to the bounds of aircraft constraints is easily generated.

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 .

An efficient self-organizing map designed by genetic algorithms for the traveling salesman problem.

PubMed

Jin, Hui-Dong; Leung, Kwong-Sak; Wong, Man-Leung; Xu, Z B

2003-01-01

As a typical combinatorial optimization problem, the traveling salesman problem (TSP) has attracted extensive research interest. In this paper, we develop a self-organizing map (SOM) with a novel learning rule. It is called the integrated SOM (ISOM) since its learning rule integrates the three learning mechanisms in the SOM literature. Within a single learning step, the excited neuron is first dragged toward the input city, then pushed to the convex hull of the TSP, and finally drawn toward the middle point of its two neighboring neurons. A genetic algorithm is successfully specified to determine the elaborate coordination among the three learning mechanisms as well as the suitable parameter setting. The evolved ISOM (eISOM) is examined on three sets of TSP to demonstrate its power and efficiency. The computation complexity of the eISOM is quadratic, which is comparable to other SOM-like neural networks. Moreover, the eISOM can generate more accurate solutions than several typical approaches for TSP including the SOM developed by Budinich, the expanding SOM, the convex elastic net, and the FLEXMAP algorithm. Though its solution accuracy is not yet comparable to some sophisticated heuristics, the eISOM is one of the most accurate neural networks for the TSP.

Detection of Oil Chestnuts Infected by Blue Mold Using Near-Infrared Hyperspectral Imaging Combined with Artificial Neural Networks.

PubMed

Feng, Lei; Zhu, Susu; Lin, Fucheng; Su, Zhenzhu; Yuan, Kangpei; Zhao, Yiying; He, Yong; Zhang, Chu

2018-06-15

Mildew damage is a major reason for chestnut poor quality and yield loss. In this study, a near-infrared hyperspectral imaging system in the 874⁻1734 nm spectral range was applied to detect the mildew damage to chestnuts caused by blue mold. Principal component analysis (PCA) scored images were firstly employed to qualitatively and intuitively distinguish moldy chestnuts from healthy chestnuts. Spectral data were extracted from the hyperspectral images. A successive projections algorithm (SPA) was used to select 12 optimal wavelengths. Artificial neural networks, including back propagation neural network (BPNN), evolutionary neural network (ENN), extreme learning machine (ELM), general regression neural network (GRNN) and radial basis neural network (RBNN) were used to build models using the full spectra and optimal wavelengths to distinguish moldy chestnuts. BPNN and ENN models using full spectra and optimal wavelengths obtained satisfactory performances, with classification accuracies all surpassing 99%. The results indicate the potential for the rapid and non-destructive detection of moldy chestnuts by hyperspectral imaging, which would help to develop online detection system for healthy and blue mold infected chestnuts.

Design Sensitivity for a Subsonic Aircraft Predicted by Neural Network and Regression Models

NASA Technical Reports Server (NTRS)

Hopkins, Dale A.; Patnaik, Surya N.

2005-01-01

A preliminary methodology was obtained for the design optimization of a subsonic aircraft by coupling NASA Langley Research Center s Flight Optimization System (FLOPS) with NASA Glenn Research Center s design optimization testbed (COMETBOARDS with regression and neural network analysis approximators). The aircraft modeled can carry 200 passengers at a cruise speed of Mach 0.85 over a range of 2500 n mi and can operate on standard 6000-ft takeoff and landing runways. The design simulation was extended to evaluate the optimal airframe and engine parameters for the subsonic aircraft to operate on nonstandard runways. Regression and neural network approximators were used to examine aircraft operation on runways ranging in length from 4500 to 7500 ft.

A biologically inspired neural network for dynamic programming.

PubMed

Francelin Romero, R A; Kacpryzk, J; Gomide, F

2001-12-01

An artificial neural network with a two-layer feedback topology and generalized recurrent neurons, for solving nonlinear discrete dynamic optimization problems, is developed. A direct method to assign the weights of neural networks is presented. The method is based on Bellmann's Optimality Principle and on the interchange of information which occurs during the synaptic chemical processing among neurons. The neural network based algorithm is an advantageous approach for dynamic programming due to the inherent parallelism of the neural networks; further it reduces the severity of computational problems that can occur in methods like conventional methods. Some illustrative application examples are presented to show how this approach works out including the shortest path and fuzzy decision making problems.

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.

Toward Optimal Target Placement for Neural Prosthetic Devices

PubMed Central

Cunningham, John P.; Yu, Byron M.; Gilja, Vikash; Ryu, Stephen I.; Shenoy, Krishna V.

2008-01-01

Neural prosthetic systems have been designed to estimate continuous reach trajectories (motor prostheses) and to predict discrete reach targets (communication prostheses). In the latter case, reach targets are typically decoded from neural spiking activity during an instructed delay period before the reach begins. Such systems use targets placed in radially symmetric geometries independent of the tuning properties of the neurons available. Here we seek to automate the target placement process and increase decode accuracy in communication prostheses by selecting target locations based on the neural population at hand. Motor prostheses that incorporate intended target information could also benefit from this consideration. We present an optimal target placement algorithm that approximately maximizes decode accuracy with respect to target locations. In simulated neural spiking data fit from two monkeys, the optimal target placement algorithm yielded statistically significant improvements up to 8 and 9% for two and sixteen targets, respectively. For four and eight targets, gains were more modest, as the target layouts found by the algorithm closely resembled the canonical layouts. We trained a monkey in this paradigm and tested the algorithm with experimental neural data to confirm some of the results found in simulation. In all, the algorithm can serve not only to create new target layouts that outperform canonical layouts, but it can also confirm or help select among multiple canonical layouts. The optimal target placement algorithm developed here is the first algorithm of its kind, and it should both improve decode accuracy and help automate target placement for neural prostheses. PMID:18829845

IrisDenseNet: Robust Iris Segmentation Using Densely Connected Fully Convolutional Networks in the Images by Visible Light and Near-Infrared Light Camera Sensors

PubMed Central

Arsalan, Muhammad; Naqvi, Rizwan Ali; Kim, Dong Seop; Nguyen, Phong Ha; Owais, Muhammad; Park, Kang Ryoung

2018-01-01

The recent advancements in computer vision have opened new horizons for deploying biometric recognition algorithms in mobile and handheld devices. Similarly, iris recognition is now much needed in unconstraint scenarios with accuracy. These environments make the acquired iris image exhibit occlusion, low resolution, blur, unusual glint, ghost effect, and off-angles. The prevailing segmentation algorithms cannot cope with these constraints. In addition, owing to the unavailability of near-infrared (NIR) light, iris recognition in visible light environment makes the iris segmentation challenging with the noise of visible light. Deep learning with convolutional neural networks (CNN) has brought a considerable breakthrough in various applications. To address the iris segmentation issues in challenging situations by visible light and near-infrared light camera sensors, this paper proposes a densely connected fully convolutional network (IrisDenseNet), which can determine the true iris boundary even with inferior-quality images by using better information gradient flow between the dense blocks. In the experiments conducted, five datasets of visible light and NIR environments were used. For visible light environment, noisy iris challenge evaluation part-II (NICE-II selected from UBIRIS.v2 database) and mobile iris challenge evaluation (MICHE-I) datasets were used. For NIR environment, the institute of automation, Chinese academy of sciences (CASIA) v4.0 interval, CASIA v4.0 distance, and IIT Delhi v1.0 iris datasets were used. Experimental results showed the optimal segmentation of the proposed IrisDenseNet and its excellent performance over existing algorithms for all five datasets. PMID:29748495

IrisDenseNet: Robust Iris Segmentation Using Densely Connected Fully Convolutional Networks in the Images by Visible Light and Near-Infrared Light Camera Sensors.

PubMed

Arsalan, Muhammad; Naqvi, Rizwan Ali; Kim, Dong Seop; Nguyen, Phong Ha; Owais, Muhammad; Park, Kang Ryoung

2018-05-10

The recent advancements in computer vision have opened new horizons for deploying biometric recognition algorithms in mobile and handheld devices. Similarly, iris recognition is now much needed in unconstraint scenarios with accuracy. These environments make the acquired iris image exhibit occlusion, low resolution, blur, unusual glint, ghost effect, and off-angles. The prevailing segmentation algorithms cannot cope with these constraints. In addition, owing to the unavailability of near-infrared (NIR) light, iris recognition in visible light environment makes the iris segmentation challenging with the noise of visible light. Deep learning with convolutional neural networks (CNN) has brought a considerable breakthrough in various applications. To address the iris segmentation issues in challenging situations by visible light and near-infrared light camera sensors, this paper proposes a densely connected fully convolutional network (IrisDenseNet), which can determine the true iris boundary even with inferior-quality images by using better information gradient flow between the dense blocks. In the experiments conducted, five datasets of visible light and NIR environments were used. For visible light environment, noisy iris challenge evaluation part-II (NICE-II selected from UBIRIS.v2 database) and mobile iris challenge evaluation (MICHE-I) datasets were used. For NIR environment, the institute of automation, Chinese academy of sciences (CASIA) v4.0 interval, CASIA v4.0 distance, and IIT Delhi v1.0 iris datasets were used. Experimental results showed the optimal segmentation of the proposed IrisDenseNet and its excellent performance over existing algorithms for all five datasets.

An Evolutionary Optimization Framework for Neural Networks and Neuromorphic Architectures

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

Schuman, Catherine D; Plank, James; Disney, Adam

2016-01-01

As new neural network and neuromorphic architectures are being developed, new training methods that operate within the constraints of the new architectures are required. Evolutionary optimization (EO) is a convenient training method for new architectures. In this work, we review a spiking neural network architecture and a neuromorphic architecture, and we describe an EO training framework for these architectures. We present the results of this training framework on four classification data sets and compare those results to other neural network and neuromorphic implementations. We also discuss how this EO framework may be extended to other architectures.

Application of Artificial Neural Networks to the Design of Turbomachinery Airfoils

NASA Technical Reports Server (NTRS)

Rai, Man Mohan; Madavan, Nateri

1997-01-01

Artificial neural networks are widely used in engineering applications, such as control, pattern recognition, plant modeling and condition monitoring to name just a few. In this seminar we will explore the possibility of applying neural networks to aerodynamic design, in particular, the design of turbomachinery airfoils. The principle idea behind this effort is to represent the design space using a neural network (within some parameter limits), and then to employ an optimization procedure to search this space for a solution that exhibits optimal performance characteristics. Results obtained for design problems in two spatial dimensions will be presented.

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.

Reducing neural network training time with parallel processing

NASA Technical Reports Server (NTRS)

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

1995-01-01

Obtaining optimal solutions for engineering design problems is often expensive because the process typically requires numerous iterations involving analysis and optimization programs. Previous research has shown that a near optimum solution can be obtained in less time by simulating a slow, expensive analysis with a fast, inexpensive neural network. A new approach has been developed to further reduce this time. This approach decomposes a large neural network into many smaller neural networks that can be trained in parallel. Guidelines are developed to avoid some of the pitfalls when training smaller neural networks in parallel. These guidelines allow the engineer: to determine the number of nodes on the hidden layer of the smaller neural networks; to choose the initial training weights; and to select a network configuration that will capture the interactions among the smaller neural networks. This paper presents results describing how these guidelines are developed.

Artificial Neural Networks Applications: from Aircraft Design Optimization to Orbiting Spacecraft On-board Environment Monitoring

NASA Technical Reports Server (NTRS)

Jules, Kenol; Lin, Paul P.

2002-01-01

This paper reviews some of the recent applications of artificial neural networks taken from various works performed by the authors over the last four years at the NASA Glenn Research Center. This paper focuses mainly on two areas. First, artificial neural networks application in design and optimization of aircraft/engine propulsion systems to shorten the overall design cycle. Out of that specific application, a generic design tool was developed, which can be used for most design optimization process. Second, artificial neural networks application in monitoring the microgravity quality onboard the International Space Station, using on-board accelerometers for data acquisition. These two different applications are reviewed in this paper to show the broad applicability of artificial intelligence in various disciplines. The intent of this paper is not to give in-depth details of these two applications, but to show the need to combine different artificial intelligence techniques or algorithms in order to design an optimized or versatile system.

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.

Power prediction in mobile communication systems using an optimal neural-network structure.

PubMed

Gao, X M; Gao, X Z; Tanskanen, J A; Ovaska, S J

1997-01-01

Presents a novel neural-network-based predictor for received power level prediction in direct sequence code division multiple access (DS/CDMA) systems. The predictor consists of an adaptive linear element (Adaline) followed by a multilayer perceptron (MLP). An important but difficult problem in designing such a cascade predictor is to determine the complexity of the networks. We solve this problem by using the predictive minimum description length (PMDL) principle to select the optimal numbers of input and hidden nodes. This approach results in a predictor with both good noise attenuation and excellent generalization capability. The optimized neural networks are used for predictive filtering of very noisy Rayleigh fading signals with 1.8 GHz carrier frequency. Our results show that the optimal neural predictor can provide smoothed in-phase and quadrature signals with signal-to-noise ratio (SNR) gains of about 12 and 7 dB at the urban mobile speeds of 5 and 50 km/h, respectively. The corresponding power signal SNR gains are about 11 and 5 dB. Therefore, the neural predictor is well suitable for power control applications where ldquodelaylessrdquo noise attenuation and efficient reduction of fast fading are required.

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.

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.

Livermore Big Artificial Neural Network Toolkit

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

Essen, Brian Van; Jacobs, Sam; Kim, Hyojin

2016-07-01

LBANN is a toolkit that is designed to train artificial neural networks efficiently on high performance computing architectures. It is optimized to take advantages of key High Performance Computing features to accelerate neural network training. Specifically it is optimized for low-latency, high bandwidth interconnects, node-local NVRAM, node-local GPU accelerators, and high bandwidth parallel file systems. It is built on top of the open source Elemental distributed-memory dense and spars-direct linear algebra and optimization library that is released under the BSD license. The algorithms contained within LBANN are drawn from the academic literature and implemented to work within a distributed-memory framework.

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.

A Wavelet Neural Network Optimal Control Model for Traffic-Flow Prediction in Intelligent Transport Systems

NASA Astrophysics Data System (ADS)

Huang, Darong; Bai, Xing-Rong

Based on wavelet transform and neural network theory, a traffic-flow prediction model, which was used in optimal control of Intelligent Traffic system, is constructed. First of all, we have extracted the scale coefficient and wavelet coefficient from the online measured raw data of traffic flow via wavelet transform; Secondly, an Artificial Neural Network model of Traffic-flow Prediction was constructed and trained using the coefficient sequences as inputs and raw data as outputs; Simultaneous, we have designed the running principium of the optimal control system of traffic-flow Forecasting model, the network topological structure and the data transmitted model; Finally, a simulated example has shown that the technique is effectively and exactly. The theoretical results indicated that the wavelet neural network prediction model and algorithms have a broad prospect for practical application.

Ads' click-through rates predicting based on gated recurrent unit neural networks

NASA Astrophysics Data System (ADS)

Chen, Qiaohong; Guo, Zixuan; Dong, Wen; Jin, Lingzi

2018-05-01

In order to improve the effect of online advertising and to increase the revenue of advertising, the gated recurrent unit neural networks(GRU) model is used as the ads' click through rates(CTR) predicting. Combined with the characteristics of gated unit structure and the unique of time sequence in data, using BPTT algorithm to train the model. Furthermore, by optimizing the step length algorithm of the gated unit recurrent neural networks, making the model reach optimal point better and faster in less iterative rounds. The experiment results show that the model based on the gated recurrent unit neural networks and its optimization of step length algorithm has the better effect on the ads' CTR predicting, which helps advertisers, media and audience achieve a win-win and mutually beneficial situation in Three-Side Game.

Online POMDP Algorithms for Very Large Observation Spaces

DTIC Science & Technology

2017-06-06

stochastic optimization: From sets to paths." In Advances in Neural Information Processing Systems, pp. 1585- 1593 . 2015. • Luo, Yuanfu, Haoyu Bai...and Wee Sun Lee. "Adaptive stochastic optimization: From sets to paths." In Advances in Neural Information Processing Systems, pp. 1585- 1593 . 2015

An optimally evolved connective ratio of neural networks that maximizes the occurrence of synchronized bursting behavior

PubMed Central

2012-01-01

Background Synchronized bursting activity (SBA) is a remarkable dynamical behavior in both ex vivo and in vivo neural networks. Investigations of the underlying structural characteristics associated with SBA are crucial to understanding the system-level regulatory mechanism of neural network behaviors. Results In this study, artificial pulsed neural networks were established using spike response models to capture fundamental dynamics of large scale ex vivo cortical networks. Network simulations with synaptic parameter perturbations showed the following two findings. (i) In a network with an excitatory ratio (ER) of 80-90%, its connective ratio (CR) was within a range of 10-30% when the occurrence of SBA reached the highest expectation. This result was consistent with the experimental observation in ex vivo neuronal networks, which were reported to possess a matured inhibitory synaptic ratio of 10-20% and a CR of 10-30%. (ii) No SBA occurred when a network does not contain any all-positive-interaction feedback loop (APFL) motif. In a neural network containing APFLs, the number of APFLs presented an optimal range corresponding to the maximal occurrence of SBA, which was very similar to the optimal CR. Conclusions In a neural network, the evolutionarily selected CR (10-30%) optimizes the occurrence of SBA, and APFL serves a pivotal network motif required to maximize the occurrence of SBA. PMID:22462685

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.

Artificial neural network modeling and optimization of ultrahigh pressure extraction of green tea polyphenols.

PubMed

Xi, Jun; Xue, Yujing; Xu, Yinxiang; Shen, Yuhong

2013-11-01

In this study, the ultrahigh pressure extraction of green tea polyphenols was modeled and optimized by a three-layer artificial neural network. A feed-forward neural network trained with an error back-propagation algorithm was used to evaluate the effects of pressure, liquid/solid ratio and ethanol concentration on the total phenolic content of green tea extracts. The neural network coupled with genetic algorithms was also used to optimize the conditions needed to obtain the highest yield of tea polyphenols. The obtained optimal architecture of artificial neural network model involved a feed-forward neural network with three input neurons, one hidden layer with eight neurons and one output layer including single neuron. The trained network gave the minimum value in the MSE of 0.03 and the maximum value in the R(2) of 0.9571, which implied a good agreement between the predicted value and the actual value, and confirmed a good generalization of the network. Based on the combination of neural network and genetic algorithms, the optimum extraction conditions for the highest yield of green tea polyphenols were determined as follows: 498.8 MPa for pressure, 20.8 mL/g for liquid/solid ratio and 53.6% for ethanol concentration. The total phenolic content of the actual measurement under the optimum predicated extraction conditions was 582.4 ± 0.63 mg/g DW, which was well matched with the predicted value (597.2mg/g DW). This suggests that the artificial neural network model described in this work is an efficient quantitative tool to predict the extraction efficiency of green tea polyphenols. Crown Copyright © 2013. Published by Elsevier Ltd. All rights reserved.

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.

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.

Frequency modulation entrains slow neural oscillations and optimizes human listening behavior

PubMed Central

Henry, Molly J.; Obleser, Jonas

2012-01-01

The human ability to continuously track dynamic environmental stimuli, in particular speech, is proposed to profit from “entrainment” of endogenous neural oscillations, which involves phase reorganization such that “optimal” phase comes into line with temporally expected critical events, resulting in improved processing. The current experiment goes beyond previous work in this domain by addressing two thus far unanswered questions. First, how general is neural entrainment to environmental rhythms: Can neural oscillations be entrained by temporal dynamics of ongoing rhythmic stimuli without abrupt onsets? Second, does neural entrainment optimize performance of the perceptual system: Does human auditory perception benefit from neural phase reorganization? In a human electroencephalography study, listeners detected short gaps distributed uniformly with respect to the phase angle of a 3-Hz frequency-modulated stimulus. Listeners’ ability to detect gaps in the frequency-modulated sound was not uniformly distributed in time, but clustered in certain preferred phases of the modulation. Moreover, the optimal stimulus phase was individually determined by the neural delta oscillation entrained by the stimulus. Finally, delta phase predicted behavior better than stimulus phase or the event-related potential after the gap. This study demonstrates behavioral benefits of phase realignment in response to frequency-modulated auditory stimuli, overall suggesting that frequency fluctuations in natural environmental input provide a pacing signal for endogenous neural oscillations, thereby influencing perceptual processing. PMID:23151506

Derivation of Optimal Cropping Pattern in Part of Hirakud Command using Cuckoo Search

NASA Astrophysics Data System (ADS)

Rath, Ashutosh; Biswal, Sudarsan; Samantaray, Sandeep; Swain, Prakash Chandra, PROF.

2017-08-01

The economicgrowth of a Nation depends on agriculture which relies on the obtainable water resources, available land and crops. The contribution of water in an appropriate quantity at appropriate time plays avitalrole to increase the agricultural production. Optimal utilization of available resources can be achieved by proper planning and management of water resources projects and adoption of appropriate technology. In the present work, the command area of Sambalpur distribrutary System is taken up for investigation. Further, adoption of a fixed cropping pattern causes the reduction of yield. The present study aims at developing different crop planning strategies to increase the net benefit from the command area with minimum investment. Optimization models are developed for Kharif season using LINDO and Cuckoo Search (CS) algorithm for maximization of the net benefits. In process of development of Optimization model the factors such as cultivable land, seeds, fertilizers, man power, water cost, etc. are taken as constraints. The irrigation water needs of major crops and the total available water through canals in the command of Sambalpur Distributary are estimated. LINDO and Cuckoo Search models are formulated and used to derive the optimal cropping pattern yielding maximum net benefits. The net benefits of Rs.585.0 lakhs in Kharif Season are obtained by adopting LINGO and 596.07 lakhs from Cuckoo Search, respectively, whereas the net benefits of 447.0 lakhs is received by the farmers of the locality with the adopting present cropping pattern.

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.

The relative phases of basal ganglia activities dynamically shape effective connectivity in Parkinson's disease.

PubMed

Cagnan, Hayriye; Duff, Eugene Paul; Brown, Peter

2015-06-01

Optimal phase alignment between oscillatory neural circuits is hypothesized to optimize information flow and enhance system performance. This theory is known as communication-through-coherence. The basal ganglia motor circuit exhibits exaggerated oscillatory and coherent activity patterns in Parkinson's disease. Such activity patterns are linked to compromised motor system performance as evinced by bradykinesia, rigidity and tremor, suggesting that network function might actually deteriorate once a certain level of net synchrony is exceeded in the motor circuit. Here, we characterize the processes underscoring excessive synchronization and its termination. To this end, we analysed local field potential recordings from the subthalamic nucleus and globus pallidus of five patients with Parkinson's disease (four male and one female, aged 37-64 years). We observed that certain phase alignments between subthalamic nucleus and globus pallidus amplified local neural synchrony in the beta frequency band while others either suppressed it or did not induce any significant change with respect to surrogates. The increase in local beta synchrony directly correlated with how long the two nuclei locked to beta-amplifying phase alignments. Crucially, administration of the dopamine prodrug, levodopa, reduced the frequency and duration of periods during which subthalamic and pallidal populations were phase-locked to beta-amplifying alignments. Conversely ON dopamine, the total duration over which subthalamic and pallidal populations were aligned to phases that left beta-amplitude unchanged with respect to surrogates increased. Thus dopaminergic input shifted circuit dynamics from persistent periods of locking to amplifying phase alignments, associated with compromised motoric function, to more dynamic phase alignment and improved motoric function. This effect of dopamine on local circuit resonance suggests means by which novel electrical interventions might prevent resonance-related pathological circuit interactions. © The Author (2015). Published by Oxford University Press on behalf of the Guarantors of Brain.

Neural network for nonsmooth pseudoconvex optimization with general convex constraints.

PubMed

Bian, Wei; Ma, Litao; Qin, Sitian; Xue, Xiaoping

2018-05-01

In this paper, a one-layer recurrent neural network is proposed for solving a class of nonsmooth, pseudoconvex optimization problems with general convex constraints. Based on the smoothing method, we construct a new regularization function, which does not depend on any information of the feasible region. Thanks to the special structure of the regularization function, we prove the global existence, uniqueness and "slow solution" character of the state of the proposed neural network. Moreover, the state solution of the proposed network is proved to be convergent to the feasible region in finite time and to the optimal solution set of the related optimization problem subsequently. In particular, the convergence of the state to an exact optimal solution is also considered in this paper. Numerical examples with simulation results are given to show the efficiency and good characteristics of the proposed network. In addition, some preliminary theoretical analysis and application of the proposed network for a wider class of dynamic portfolio optimization are included. Copyright © 2018 Elsevier Ltd. All rights reserved.

Optimal Decision Making in Neural Inhibition Models

ERIC Educational Resources Information Center

van Ravenzwaaij, Don; van der Maas, Han L. J.; Wagenmakers, Eric-Jan

2012-01-01

In their influential "Psychological Review" article, Bogacz, Brown, Moehlis, Holmes, and Cohen (2006) discussed optimal decision making as accomplished by the drift diffusion model (DDM). The authors showed that neural inhibition models, such as the leaky competing accumulator model (LCA) and the feedforward inhibition model (FFI), can mimic the…

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.

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

NASA Technical Reports Server (NTRS)

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

1992-01-01

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

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).

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)

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.

Features Extraction of Flotation Froth Images and BP Neural Network Soft-Sensor Model of Concentrate Grade Optimized by Shuffled Cuckoo Searching Algorithm

PubMed Central

Wang, Jie-sheng; Han, Shuang; Shen, Na-na; Li, Shu-xia

2014-01-01

For meeting the forecasting target of key technology indicators in the flotation process, a BP neural network soft-sensor model based on features extraction of flotation froth images and optimized by shuffled cuckoo search algorithm is proposed. Based on the digital image processing technique, the color features in HSI color space, the visual features based on the gray level cooccurrence matrix, and the shape characteristics based on the geometric theory of flotation froth images are extracted, respectively, as the input variables of the proposed soft-sensor model. Then the isometric mapping method is used to reduce the input dimension, the network size, and learning time of BP neural network. Finally, a shuffled cuckoo search algorithm is adopted to optimize the BP neural network soft-sensor model. Simulation results show that the model has better generalization results and prediction accuracy. PMID:25133210

Artificial neural networks in evaluation and optimization of modified release solid dosage forms.

PubMed

Ibrić, Svetlana; Djuriš, Jelena; Parojčić, Jelena; Djurić, Zorica

2012-10-18

Implementation of the Quality by Design (QbD) approach in pharmaceutical development has compelled researchers in the pharmaceutical industry to employ Design of Experiments (DoE) as a statistical tool, in product development. Among all DoE techniques, response surface methodology (RSM) is the one most frequently used. Progress of computer science has had an impact on pharmaceutical development as well. Simultaneous with the implementation of statistical methods, machine learning tools took an important place in drug formulation. Twenty years ago, the first papers describing application of artificial neural networks in optimization of modified release products appeared. Since then, a lot of work has been done towards implementation of new techniques, especially Artificial Neural Networks (ANN) in modeling of production, drug release and drug stability of modified release solid dosage forms. The aim of this paper is to review artificial neural networks in evaluation and optimization of modified release solid dosage forms.

Artificial Neural Networks in Evaluation and Optimization of Modified Release Solid Dosage Forms

PubMed Central

Ibrić, Svetlana; Djuriš, Jelena; Parojčić, Jelena; Djurić, Zorica

2012-01-01

Implementation of the Quality by Design (QbD) approach in pharmaceutical development has compelled researchers in the pharmaceutical industry to employ Design of Experiments (DoE) as a statistical tool, in product development. Among all DoE techniques, response surface methodology (RSM) is the one most frequently used. Progress of computer science has had an impact on pharmaceutical development as well. Simultaneous with the implementation of statistical methods, machine learning tools took an important place in drug formulation. Twenty years ago, the first papers describing application of artificial neural networks in optimization of modified release products appeared. Since then, a lot of work has been done towards implementation of new techniques, especially Artificial Neural Networks (ANN) in modeling of production, drug release and drug stability of modified release solid dosage forms. The aim of this paper is to review artificial neural networks in evaluation and optimization of modified release solid dosage forms. PMID:24300369

A neural network strategy for end-point optimization of batch processes.

PubMed

Krothapally, M; Palanki, S

1999-01-01

The traditional way of operating batch processes has been to utilize an open-loop "golden recipe". However, there can be substantial batch to batch variation in process conditions and this open-loop strategy can lead to non-optimal operation. In this paper, a new approach is presented for end-point optimization of batch processes by utilizing neural networks. This strategy involves the training of two neural networks; one to predict switching times and the other to predict the input profile in the singular region. This approach alleviates the computational problems associated with the classical Pontryagin's approach and the nonlinear programming approach. The efficacy of this scheme is illustrated via simulation of a fed-batch fermentation.

A Danger-Theory-Based Immune Network Optimization Algorithm

PubMed Central

Li, Tao; Xiao, Xin; Shi, Yuanquan

2013-01-01

Existing artificial immune optimization algorithms reflect a number of shortcomings, such as premature convergence and poor local search ability. This paper proposes a danger-theory-based immune network optimization algorithm, named dt-aiNet. The danger theory emphasizes that danger signals generated from changes of environments will guide different levels of immune responses, and the areas around danger signals are called danger zones. By defining the danger zone to calculate danger signals for each antibody, the algorithm adjusts antibodies' concentrations through its own danger signals and then triggers immune responses of self-regulation. So the population diversity can be maintained. Experimental results show that the algorithm has more advantages in the solution quality and diversity of the population. Compared with influential optimization algorithms, CLONALG, opt-aiNet, and dopt-aiNet, the algorithm has smaller error values and higher success rates and can find solutions to meet the accuracies within the specified function evaluation times. PMID:23483853

An improved wavelet neural network medical image segmentation algorithm with combined maximum entropy

NASA Astrophysics Data System (ADS)

Hu, Xiaoqian; Tao, Jinxu; Ye, Zhongfu; Qiu, Bensheng; Xu, Jinzhang

2018-05-01

In order to solve the problem of medical image segmentation, a wavelet neural network medical image segmentation algorithm based on combined maximum entropy criterion is proposed. Firstly, we use bee colony algorithm to optimize the network parameters of wavelet neural network, get the parameters of network structure, initial weights and threshold values, and so on, we can quickly converge to higher precision when training, and avoid to falling into relative extremum; then the optimal number of iterations is obtained by calculating the maximum entropy of the segmented image, so as to achieve the automatic and accurate segmentation effect. Medical image segmentation experiments show that the proposed algorithm can reduce sample training time effectively and improve convergence precision, and segmentation effect is more accurate and effective than traditional BP neural network (back propagation neural network : a multilayer feed forward neural network which trained according to the error backward propagation algorithm.

Optimization behavior of brainstem respiratory neurons. A cerebral neural network model.

PubMed

Poon, C S

1991-01-01

A recent model of respiratory control suggested that the steady-state respiratory responses to CO2 and exercise may be governed by an optimal control law in the brainstem respiratory neurons. It was not certain, however, whether such complex optimization behavior could be accomplished by a realistic biological neural network. To test this hypothesis, we developed a hybrid computer-neural model in which the dynamics of the lung, brain and other tissue compartments were simulated on a digital computer. Mimicking the "controller" was a human subject who pedalled on a bicycle with varying speed (analog of ventilatory output) with a view to minimize an analog signal of the total cost of breathing (chemical and mechanical) which was computed interactively and displayed on an oscilloscope. In this manner, the visuomotor cortex served as a proxy (homolog) of the brainstem respiratory neurons in the model. Results in 4 subjects showed a linear steady-state ventilatory CO2 response to arterial PCO2 during simulated CO2 inhalation and a nearly isocapnic steady-state response during simulated exercise. Thus, neural optimization is a plausible mechanism for respiratory control during exercise and can be achieved by a neural network with cognitive computational ability without the need for an exercise stimulus.

Research on particle swarm optimization algorithm based on optimal movement probability

NASA Astrophysics Data System (ADS)

Ma, Jianhong; Zhang, Han; He, Baofeng

2017-01-01

The particle swarm optimization algorithm to improve the control precision, and has great application value training neural network and fuzzy system control fields etc.The traditional particle swarm algorithm is used for the training of feed forward neural networks,the search efficiency is low, and easy to fall into local convergence.An improved particle swarm optimization algorithm is proposed based on error back propagation gradient descent. Particle swarm optimization for Solving Least Squares Problems to meme group, the particles in the fitness ranking, optimization problem of the overall consideration, the error back propagation gradient descent training BP neural network, particle to update the velocity and position according to their individual optimal and global optimization, make the particles more to the social optimal learning and less to its optimal learning, it can avoid the particles fall into local optimum, by using gradient information can accelerate the PSO local search ability, improve the multi beam particle swarm depth zero less trajectory information search efficiency, the realization of improved particle swarm optimization algorithm. Simulation results show that the algorithm in the initial stage of rapid convergence to the global optimal solution can be near to the global optimal solution and keep close to the trend, the algorithm has faster convergence speed and search performance in the same running time, it can improve the convergence speed of the algorithm, especially the later search efficiency.

Advanced obstacle avoidance for a laser based wheelchair using optimised Bayesian neural networks.

PubMed

Trieu, Hoang T; Nguyen, Hung T; Willey, Keith

2008-01-01

In this paper we present an advanced method of obstacle avoidance for a laser based intelligent wheelchair using optimized Bayesian neural networks. Three neural networks are designed for three separate sub-tasks: passing through a door way, corridor and wall following and general obstacle avoidance. The accurate usable accessible space is determined by including the actual wheelchair dimensions in a real-time map used as inputs to each networks. Data acquisitions are performed separately to collect the patterns required for specified sub-tasks. Bayesian frame work is used to determine the optimal neural network structure in each case. Then these networks are trained under the supervision of Bayesian rule. Experiment results showed that compare to the VFH algorithm our neural networks navigated a smoother path following a near optimum trajectory.

[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.

BioNetFit: a fitting tool compatible with BioNetGen, NFsim and distributed computing environments

DOE PAGES

Thomas, Brandon R.; Chylek, Lily A.; Colvin, Joshua; ...

2015-11-09

Rule-based models are analyzed with specialized simulators, such as those provided by the BioNetGen and NFsim open-source software packages. Here in this paper, we present BioNetFit, a general-purpose fitting tool that is compatible with BioNetGen and NFsim. BioNetFit is designed to take advantage of distributed computing resources. This feature facilitates fitting (i.e. optimization of parameter values for consistency with data) when simulations are computationally expensive.

Generation of optimal artificial neural networks using a pattern search algorithm: application to approximation of chemical systems.

PubMed

Ihme, Matthias; Marsden, Alison L; Pitsch, Heinz

2008-02-01

A pattern search optimization method is applied to the generation of optimal artificial neural networks (ANNs). Optimization is performed using a mixed variable extension to the generalized pattern search method. This method offers the advantage that categorical variables, such as neural transfer functions and nodal connectivities, can be used as parameters in optimization. When used together with a surrogate, the resulting algorithm is highly efficient for expensive objective functions. Results demonstrate the effectiveness of this method in optimizing an ANN for the number of neurons, the type of transfer function, and the connectivity among neurons. The optimization method is applied to a chemistry approximation of practical relevance. In this application, temperature and a chemical source term are approximated as functions of two independent parameters using optimal ANNs. Comparison of the performance of optimal ANNs with conventional tabulation methods demonstrates equivalent accuracy by considerable savings in memory storage. The architecture of the optimal ANN for the approximation of the chemical source term consists of a fully connected feedforward network having four nonlinear hidden layers and 117 synaptic weights. An equivalent representation of the chemical source term using tabulation techniques would require a 500 x 500 grid point discretization of the parameter space.

Bidirectional optimization of the melting spinning process.

PubMed

Liang, Xiao; Ding, Yongsheng; Wang, Zidong; Hao, Kuangrong; Hone, Kate; Wang, Huaping

2014-02-01

A bidirectional optimizing approach for the melting spinning process based on an immune-enhanced neural network is proposed. The proposed bidirectional model can not only reveal the internal nonlinear relationship between the process configuration and the quality indices of the fibers as final product, but also provide a tool for engineers to develop new fiber products with expected quality specifications. A neural network is taken as the basis for the bidirectional model, and an immune component is introduced to enlarge the searching scope of the solution field so that the neural network has a larger possibility to find the appropriate and reasonable solution, and the error of prediction can therefore be eliminated. The proposed intelligent model can also help to determine what kind of process configuration should be made in order to produce satisfactory fiber products. To make the proposed model practical to the manufacturing, a software platform is developed. Simulation results show that the proposed model can eliminate the approximation error raised by the neural network-based optimizing model, which is due to the extension of focusing scope by the artificial immune mechanism. Meanwhile, the proposed model with the corresponding software can conduct optimization in two directions, namely, the process optimization and category development, and the corresponding results outperform those with an ordinary neural network-based intelligent model. It is also proved that the proposed model has the potential to act as a valuable tool from which the engineers and decision makers of the spinning process could benefit.

Experiments in Neural-Network Control of a Free-Flying Space Robot

NASA Technical Reports Server (NTRS)

Wilson, Edward

1995-01-01

Four important generic issues are identified and addressed in some depth in this thesis as part of the development of an adaptive neural network based control system for an experimental free flying space robot prototype. The first issue concerns the importance of true system level design of the control system. A new hybrid strategy is developed here, in depth, for the beneficial integration of neural networks into the total control system. A second important issue in neural network control concerns incorporating a priori knowledge into the neural network. In many applications, it is possible to get a reasonably accurate controller using conventional means. If this prior information is used purposefully to provide a starting point for the optimizing capabilities of the neural network, it can provide much faster initial learning. In a step towards addressing this issue, a new generic Fully Connected Architecture (FCA) is developed for use with backpropagation. A third issue is that neural networks are commonly trained using a gradient based optimization method such as backpropagation; but many real world systems have Discrete Valued Functions (DVFs) that do not permit gradient based optimization. One example is the on-off thrusters that are common on spacecraft. A new technique is developed here that now extends backpropagation learning for use with DVFs. The fourth issue is that the speed of adaptation is often a limiting factor in the implementation of a neural network control system. This issue has been strongly resolved in the research by drawing on the above new contributions.

Electronic Neural Networks

NASA Technical Reports Server (NTRS)

Thakoor, Anil

1990-01-01

Viewgraphs on electronic neural networks for space station are presented. Topics covered include: electronic neural networks; electronic implementations; VLSI/thin film hybrid hardware for neurocomputing; computations with analog parallel processing; features of neuroprocessors; applications of neuroprocessors; neural network hardware for terrain trafficability determination; a dedicated processor for path planning; neural network system interface; neural network for robotic control; error backpropagation algorithm for learning; resource allocation matrix; global optimization neuroprocessor; and electrically programmable read only thin-film synaptic array.

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.

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

NASA Technical Reports Server (NTRS)

Rai, Man Mohan

2006-01-01

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

Model-based occluded object recognition using Petri nets

NASA Astrophysics Data System (ADS)

Zhou, Chuan; Hura, Gurdeep S.

1998-09-01

This paper discusses the use of Petri nets to model the process of the object matching between an image and a model under different 2D geometric transformations. This transformation finds its applications in sensor-based robot control, flexible manufacturing system and industrial inspection, etc. A description approach for object structure is presented by its topological structure relation called Point-Line Relation Structure (PLRS). It has been shown how Petri nets can be used to model the matching process, and an optimal or near optimal matching can be obtained by tracking the reachability graph of the net. The experiment result shows that object can be successfully identified and located under 2D transformation such as translations, rotations, scale changes and distortions due to object occluded partially.

Money Changes Everything: Funding Shocks and Optimal Admissions and Financial Aid Policies in Higher Education

ERIC Educational Resources Information Center

Nagler, Matthew G.

2006-01-01

The paper examines the effect of a shock to university funding on tuition net of financial aid, admissions selectivity, and enrollment levels chosen by an optimizing university. Whereas a positive shock, such as a major donation, results in lower net tuition and greater selectivity with respect to all students, its effect on enrollment may not be…

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.

Aerodynamic Design Using Neural Networks

NASA Technical Reports Server (NTRS)

Rai, Man Mohan; Madavan, Nateri K.

2003-01-01

The design of aerodynamic components of aircraft, such as wings or engines, involves a process of obtaining the most optimal component shape that can deliver the desired level of component performance, subject to various constraints, e.g., total weight or cost, that the component must satisfy. Aerodynamic design can thus be formulated as an optimization problem that involves the minimization of an objective function subject to constraints. A new aerodynamic design optimization procedure based on neural networks and response surface methodology (RSM) incorporates the advantages of both traditional RSM and neural networks. The procedure uses a strategy, denoted parameter-based partitioning of the design space, to construct a sequence of response surfaces based on both neural networks and polynomial fits to traverse the design space in search of the optimal solution. Some desirable characteristics of the new design optimization procedure include the ability to handle a variety of design objectives, easily impose constraints, and incorporate design guidelines and rules of thumb. It provides an infrastructure for variable fidelity analysis and reduces the cost of computation by using less-expensive, lower fidelity simulations in the early stages of the design evolution. The initial or starting design can be far from optimal. The procedure is easy and economical to use in large-dimensional design space and can be used to perform design tradeoff studies rapidly. Designs involving multiple disciplines can also be optimized. Some practical applications of the design procedure that have demonstrated some of its capabilities include the inverse design of an optimal turbine airfoil starting from a generic shape and the redesign of transonic turbines to improve their unsteady aerodynamic characteristics.

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.

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.

Influence of the optimization methods on neural state estimation quality of the drive system with elasticity.

PubMed

Orlowska-Kowalska, Teresa; Kaminski, Marcin

2014-01-01

The paper deals with the implementation of optimized neural networks (NNs) for state variable estimation of the drive system with an elastic joint. The signals estimated by NNs are used in the control structure with a state-space controller and additional feedbacks from the shaft torque and the load speed. High estimation quality is very important for the correct operation of a closed-loop system. The precision of state variables estimation depends on the generalization properties of NNs. A short review of optimization methods of the NN is presented. Two techniques typical for regularization and pruning methods are described and tested in detail: the Bayesian regularization and the Optimal Brain Damage methods. Simulation results show good precision of both optimized neural estimators for a wide range of changes of the load speed and the load torque, not only for nominal but also changed parameters of the drive system. The simulation results are verified in a laboratory setup.

Cascade Optimization Strategy with Neural Network and Regression Approximations Demonstrated on a Preliminary Aircraft Engine Design

NASA Technical Reports Server (NTRS)

Hopkins, Dale A.; Patnaik, Surya N.

2000-01-01

A preliminary aircraft engine design methodology is being developed that utilizes a cascade optimization strategy together with neural network and regression approximation methods. The cascade strategy employs different optimization algorithms in a specified sequence. The neural network and regression methods are used to approximate solutions obtained from the NASA Engine Performance Program (NEPP), which implements engine thermodynamic cycle and performance analysis models. The new methodology is proving to be more robust and computationally efficient than the conventional optimization approach of using a single optimization algorithm with direct reanalysis. The methodology has been demonstrated on a preliminary design problem for a novel subsonic turbofan engine concept that incorporates a wave rotor as a cycle-topping device. Computations of maximum thrust were obtained for a specific design point in the engine mission profile. The results (depicted in the figure) show a significant improvement in the maximum thrust obtained using the new methodology in comparison to benchmark solutions obtained using NEPP in a manual design mode.

Adaptive Critic Neural Network-Based Terminal Area Energy Management and Approach and Landing Guidance

NASA Technical Reports Server (NTRS)

Grantham, Katie

2003-01-01

Reusable Launch Vehicles (RLVs) have different mission requirements than the Space Shuttle, which is used for benchmark guidance design. Therefore, alternative Terminal Area Energy Management (TAEM) and Approach and Landing (A/L) Guidance schemes can be examined in the interest of cost reduction. A neural network based solution for a finite horizon trajectory optimization problem is presented in this paper. In this approach the optimal trajectory of the vehicle is produced by adaptive critic based neural networks, which were trained off-line to maintain a gradual glideslope.

Neural-network-based online HJB solution for optimal robust guaranteed cost control of continuous-time uncertain nonlinear systems.

PubMed

Liu, Derong; Wang, Ding; Wang, Fei-Yue; Li, Hongliang; Yang, Xiong

2014-12-01

In this paper, the infinite horizon optimal robust guaranteed cost control of continuous-time uncertain nonlinear systems is investigated using neural-network-based online solution of Hamilton-Jacobi-Bellman (HJB) equation. By establishing an appropriate bounded function and defining a modified cost function, the optimal robust guaranteed cost control problem is transformed into an optimal control problem. It can be observed that the optimal cost function of the nominal system is nothing but the optimal guaranteed cost of the original uncertain system. A critic neural network is constructed to facilitate the solution of the modified HJB equation corresponding to the nominal system. More importantly, an additional stabilizing term is introduced for helping to verify the stability, which reinforces the updating process of the weight vector and reduces the requirement of an initial stabilizing control. The uniform ultimate boundedness of the closed-loop system is analyzed by using the Lyapunov approach as well. Two simulation examples are provided to verify the effectiveness of the present control approach.

Error-based analysis of optimal tuning functions explains phenomena observed in sensory neurons.

PubMed

Yaeli, Steve; Meir, Ron

2010-01-01

Biological systems display impressive capabilities in effectively responding to environmental signals in real time. There is increasing evidence that organisms may indeed be employing near optimal Bayesian calculations in their decision-making. An intriguing question relates to the properties of optimal encoding methods, namely determining the properties of neural populations in sensory layers that optimize performance, subject to physiological constraints. Within an ecological theory of neural encoding/decoding, we show that optimal Bayesian performance requires neural adaptation which reflects environmental changes. Specifically, we predict that neuronal tuning functions possess an optimal width, which increases with prior uncertainty and environmental noise, and decreases with the decoding time window. Furthermore, even for static stimuli, we demonstrate that dynamic sensory tuning functions, acting at relatively short time scales, lead to improved performance. Interestingly, the narrowing of tuning functions as a function of time was recently observed in several biological systems. Such results set the stage for a functional theory which may explain the high reliability of sensory systems, and the utility of neuronal adaptation occurring at multiple time scales.

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.

Statistically optimal perception and learning: from behavior to neural representations

PubMed Central

Fiser, József; Berkes, Pietro; Orbán, Gergő; Lengyel, Máté

2010-01-01

Human perception has recently been characterized as statistical inference based on noisy and ambiguous sensory inputs. Moreover, suitable neural representations of uncertainty have been identified that could underlie such probabilistic computations. In this review, we argue that learning an internal model of the sensory environment is another key aspect of the same statistical inference procedure and thus perception and learning need to be treated jointly. We review evidence for statistically optimal learning in humans and animals, and reevaluate possible neural representations of uncertainty based on their potential to support statistically optimal learning. We propose that spontaneous activity can have a functional role in such representations leading to a new, sampling-based, framework of how the cortex represents information and uncertainty. PMID:20153683

Optimal and robust control of a class of nonlinear systems using dynamically re-optimised single network adaptive critic design

NASA Astrophysics Data System (ADS)

Tiwari, Shivendra N.; Padhi, Radhakant

2018-01-01

Following the philosophy of adaptive optimal control, a neural network-based state feedback optimal control synthesis approach is presented in this paper. First, accounting for a nominal system model, a single network adaptive critic (SNAC) based multi-layered neural network (called as NN1) is synthesised offline. However, another linear-in-weight neural network (called as NN2) is trained online and augmented to NN1 in such a manner that their combined output represent the desired optimal costate for the actual plant. To do this, the nominal model needs to be updated online to adapt to the actual plant, which is done by synthesising yet another linear-in-weight neural network (called as NN3) online. Training of NN3 is done by utilising the error information between the nominal and actual states and carrying out the necessary Lyapunov stability analysis using a Sobolev norm based Lyapunov function. This helps in training NN2 successfully to capture the required optimal relationship. The overall architecture is named as 'Dynamically Re-optimised single network adaptive critic (DR-SNAC)'. Numerical results for two motivating illustrative problems are presented, including comparison studies with closed form solution for one problem, which clearly demonstrate the effectiveness and benefit of the proposed approach.

Disease Prediction based on Functional Connectomes using a Scalable and Spatially-Informed Support Vector Machine

PubMed Central

Watanabe, Takanori; Kessler, Daniel; Scott, Clayton; Angstadt, Michael; Sripada, Chandra

2014-01-01

Substantial evidence indicates that major psychiatric disorders are associated with distributed neural dysconnectivity, leading to strong interest in using neuroimaging methods to accurately predict disorder status. In this work, we are specifically interested in a multivariate approach that uses features derived from whole-brain resting state functional connectomes. However, functional connectomes reside in a high dimensional space, which complicates model interpretation and introduces numerous statistical and computational challenges. Traditional feature selection techniques are used to reduce data dimensionality, but are blind to the spatial structure of the connectomes. We propose a regularization framework where the 6-D structure of the functional connectome (defined by pairs of points in 3-D space) is explicitly taken into account via the fused Lasso or the GraphNet regularizer. Our method only restricts the loss function to be convex and margin-based, allowing non-differentiable loss functions such as the hinge-loss to be used. Using the fused Lasso or GraphNet regularizer with the hinge-loss leads to a structured sparse support vector machine (SVM) with embedded feature selection. We introduce a novel efficient optimization algorithm based on the augmented Lagrangian and the classical alternating direction method, which can solve both fused Lasso and GraphNet regularized SVM with very little modification. We also demonstrate that the inner subproblems of the algorithm can be solved efficiently in analytic form by coupling the variable splitting strategy with a data augmentation scheme. Experiments on simulated data and resting state scans from a large schizophrenia dataset show that our proposed approach can identify predictive regions that are spatially contiguous in the 6-D “connectome space,” offering an additional layer of interpretability that could provide new insights about various disease processes. PMID:24704268

SOM neural network fault diagnosis method of polymerization kettle equipment optimized by improved PSO algorithm.

PubMed

Wang, Jie-sheng; Li, Shu-xia; Gao, Jie

2014-01-01

For meeting the real-time fault diagnosis and the optimization monitoring requirements of the polymerization kettle in the polyvinyl chloride resin (PVC) production process, a fault diagnosis strategy based on the self-organizing map (SOM) neural network is proposed. Firstly, a mapping between the polymerization process data and the fault pattern is established by analyzing the production technology of polymerization kettle equipment. The particle swarm optimization (PSO) algorithm with a new dynamical adjustment method of inertial weights is adopted to optimize the structural parameters of SOM neural network. The fault pattern classification of the polymerization kettle equipment is to realize the nonlinear mapping from symptom set to fault set according to the given symptom set. Finally, the simulation experiments of fault diagnosis are conducted by combining with the industrial on-site historical data of the polymerization kettle and the simulation results show that the proposed PSO-SOM fault diagnosis strategy is effective.

Evaluation of thermal conductivity of MgO-MWCNTs/EG hybrid nanofluids based on experimental data by selecting optimal artificial neural networks

NASA Astrophysics Data System (ADS)

Vafaei, Masoud; Afrand, Masoud; Sina, Nima; Kalbasi, Rasool; Sourani, Forough; Teimouri, Hamid

2017-01-01

In this paper, the thermal conductivity ratio of MgO-MWCNTs/EG hybrid nanofluids has been predicted by an optimal artificial neural network at solid volume fractions of 0.05%, 0.1%, 0.15%, 0.2%, 0.4% and 0.6% in the temperature range of 25-50 °C. In this way, at the first, thirty six experimental data was presented to determine the thermal conductivity ratio of the hybrid nanofluid. Then, four optimal artificial neural networks with 6, 8, 10 and 12 neurons in hidden layer were designed to predict the thermal conductivity ratio of the nanofluid. The comparison between four optimal ANN results and experimental showed that the ANN with 12 neurons in hidden layer was the best model. Moreover, the results obtained from the best ANN indicated the maximum deviation margin of 0.8%.

Two neural network algorithms for designing optimal terminal controllers with open final time

NASA Technical Reports Server (NTRS)

Plumer, Edward S.

1992-01-01

Multilayer neural networks, trained by the backpropagation through time algorithm (BPTT), have been used successfully as state-feedback controllers for nonlinear terminal control problems. Current BPTT techniques, however, are not able to deal systematically with open final-time situations such as minimum-time problems. Two approaches which extend BPTT to open final-time problems are presented. In the first, a neural network learns a mapping from initial-state to time-to-go. In the second, the optimal number of steps for each trial run is found using a line-search. Both methods are derived using Lagrange multiplier techniques. This theoretical framework is used to demonstrate that the derived algorithms are direct extensions of forward/backward sweep methods used in N-stage optimal control. The two algorithms are tested on a Zermelo problem and the resulting trajectories compare favorably to optimal control results.

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

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.

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.

Efficiency Improvement in a Busy Radiology Practice: Determination of Musculoskeletal Magnetic Resonance Imaging Protocol Using Deep-Learning Convolutional Neural Networks.

PubMed

Lee, Young Han

2018-04-04

The purposes of this study are to evaluate the feasibility of protocol determination with a convolutional neural networks (CNN) classifier based on short-text classification and to evaluate the agreements by comparing protocols determined by CNN with those determined by musculoskeletal radiologists. Following institutional review board approval, the database of a hospital information system (HIS) was queried for lists of MRI examinations, referring department, patient age, and patient gender. These were exported to a local workstation for analyses: 5258 and 1018 consecutive musculoskeletal MRI examinations were used for the training and test datasets, respectively. The subjects for pre-processing were routine or tumor protocols and the contents were word combinations of the referring department, region, contrast media (or not), gender, and age. The CNN Embedded vector classifier was used with Word2Vec Google news vectors. The test set was tested with each classification model and results were output as routine or tumor protocols. The CNN determinations were evaluated using the receiver operating characteristic (ROC) curves. The accuracies were evaluated by a radiologist-confirmed protocol as the reference protocols. The optimal cut-off values for protocol determination between routine protocols and tumor protocols was 0.5067 with a sensitivity of 92.10%, a specificity of 95.76%, and an area under curve (AUC) of 0.977. The overall accuracy was 94.2% for the ConvNet model. All MRI protocols were correct in the pelvic bone, upper arm, wrist, and lower leg MRIs. Deep-learning-based convolutional neural networks were clinically utilized to determine musculoskeletal MRI protocols. CNN-based text learning and applications could be extended to other radiologic tasks besides image interpretations, improving the work performance of the radiologist.

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.

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.

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.

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

PubMed

Shimansky, Yury P

2009-12-01

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

Estimation of tissue stiffness, reflex activity, optimal muscle length and slack length in stroke patients using an electromyography driven antagonistic wrist model.

PubMed

de Gooijer-van de Groep, Karin L; de Vlugt, Erwin; van der Krogt, Hanneke J; Helgadóttir, Áróra; Arendzen, J Hans; Meskers, Carel G M; de Groot, Jurriaan H

2016-06-01

About half of all chronic stroke patients experience loss of arm function coinciding with increased stiffness, reduced range of motion and a flexed wrist due to a change in neural and/or structural tissue properties. Quantitative assessment of these changes is of clinical importance, yet not trivial. The goal of this study was to quantify the neural and structural properties contributing to wrist joint stiffness and to compare these properties between healthy subjects and stroke patients. Stroke patients (n=32) and healthy volunteers (n=14) were measured using ramp-and-hold rotations applied to the wrist joint by a haptic manipulator. Neural (reflexive torque) and structural (connective tissue stiffness and slack lengths and (contractile) optimal muscle lengths) parameters were estimated using an electromyography driven antagonistic wrist model. Kruskal-Wallis analysis with multiple comparisons was used to compare results between healthy subjects, stroke patients with modified Ashworth score of zero and stroke patients with modified Ashworth score of one or more. Stroke patients with modified Ashworth score of one or more differed from healthy controls (P<0.05) by increased tissue stiffness, increased reflexive torque, decreased optimal muscle length and decreased slack length of connective tissue of the flexor muscles. Non-invasive quantitative analysis, including estimation of optimal muscle lengths, enables to identify neural and non-neural changes in chronic stroke patients. Monitoring these changes in time is important to understand the recovery process and to optimize treatment. Copyright © 2016 Elsevier Ltd. All rights reserved.

Extracellular voltage threshold settings can be tuned for optimal encoding of movement and stimulus parameters

NASA Astrophysics Data System (ADS)

Oby, Emily R.; Perel, Sagi; Sadtler, Patrick T.; Ruff, Douglas A.; Mischel, Jessica L.; Montez, David F.; Cohen, Marlene R.; Batista, Aaron P.; Chase, Steven M.

2016-06-01

Objective. A traditional goal of neural recording with extracellular electrodes is to isolate action potential waveforms of an individual neuron. Recently, in brain-computer interfaces (BCIs), it has been recognized that threshold crossing events of the voltage waveform also convey rich information. To date, the threshold for detecting threshold crossings has been selected to preserve single-neuron isolation. However, the optimal threshold for single-neuron identification is not necessarily the optimal threshold for information extraction. Here we introduce a procedure to determine the best threshold for extracting information from extracellular recordings. We apply this procedure in two distinct contexts: the encoding of kinematic parameters from neural activity in primary motor cortex (M1), and visual stimulus parameters from neural activity in primary visual cortex (V1). Approach. We record extracellularly from multi-electrode arrays implanted in M1 or V1 in monkeys. Then, we systematically sweep the voltage detection threshold and quantify the information conveyed by the corresponding threshold crossings. Main Results. The optimal threshold depends on the desired information. In M1, velocity is optimally encoded at higher thresholds than speed; in both cases the optimal thresholds are lower than are typically used in BCI applications. In V1, information about the orientation of a visual stimulus is optimally encoded at higher thresholds than is visual contrast. A conceptual model explains these results as a consequence of cortical topography. Significance. How neural signals are processed impacts the information that can be extracted from them. Both the type and quality of information contained in threshold crossings depend on the threshold setting. There is more information available in these signals than is typically extracted. Adjusting the detection threshold to the parameter of interest in a BCI context should improve our ability to decode motor intent, and thus enhance BCI control. Further, by sweeping the detection threshold, one can gain insights into the topographic organization of the nearby neural tissue.

Extracellular voltage threshold settings can be tuned for optimal encoding of movement and stimulus parameters

PubMed Central

Oby, Emily R; Perel, Sagi; Sadtler, Patrick T; Ruff, Douglas A; Mischel, Jessica L; Montez, David F; Cohen, Marlene R; Batista, Aaron P; Chase, Steven M

2018-01-01

Objective A traditional goal of neural recording with extracellular electrodes is to isolate action potential waveforms of an individual neuron. Recently, in brain–computer interfaces (BCIs), it has been recognized that threshold crossing events of the voltage waveform also convey rich information. To date, the threshold for detecting threshold crossings has been selected to preserve single-neuron isolation. However, the optimal threshold for single-neuron identification is not necessarily the optimal threshold for information extraction. Here we introduce a procedure to determine the best threshold for extracting information from extracellular recordings. We apply this procedure in two distinct contexts: the encoding of kinematic parameters from neural activity in primary motor cortex (M1), and visual stimulus parameters from neural activity in primary visual cortex (V1). Approach We record extracellularly from multi-electrode arrays implanted in M1 or V1 in monkeys. Then, we systematically sweep the voltage detection threshold and quantify the information conveyed by the corresponding threshold crossings. Main Results The optimal threshold depends on the desired information. In M1, velocity is optimally encoded at higher thresholds than speed; in both cases the optimal thresholds are lower than are typically used in BCI applications. In V1, information about the orientation of a visual stimulus is optimally encoded at higher thresholds than is visual contrast. A conceptual model explains these results as a consequence of cortical topography. Significance How neural signals are processed impacts the information that can be extracted from them. Both the type and quality of information contained in threshold crossings depend on the threshold setting. There is more information available in these signals than is typically extracted. Adjusting the detection threshold to the parameter of interest in a BCI context should improve our ability to decode motor intent, and thus enhance BCI control. Further, by sweeping the detection threshold, one can gain insights into the topographic organization of the nearby neural tissue. PMID:27097901

A stimulus-dependent spike threshold is an optimal neural coder

PubMed Central

Jones, Douglas L.; Johnson, Erik C.; Ratnam, Rama

2015-01-01

A neural code based on sequences of spikes can consume a significant portion of the brain's energy budget. Thus, energy considerations would dictate that spiking activity be kept as low as possible. However, a high spike-rate improves the coding and representation of signals in spike trains, particularly in sensory systems. These are competing demands, and selective pressure has presumably worked to optimize coding by apportioning a minimum number of spikes so as to maximize coding fidelity. The mechanisms by which a neuron generates spikes while maintaining a fidelity criterion are not known. Here, we show that a signal-dependent neural threshold, similar to a dynamic or adapting threshold, optimizes the trade-off between spike generation (encoding) and fidelity (decoding). The threshold mimics a post-synaptic membrane (a low-pass filter) and serves as an internal decoder. Further, it sets the average firing rate (the energy constraint). The decoding process provides an internal copy of the coding error to the spike-generator which emits a spike when the error equals or exceeds a spike threshold. When optimized, the trade-off leads to a deterministic spike firing-rule that generates optimally timed spikes so as to maximize fidelity. The optimal coder is derived in closed-form in the limit of high spike-rates, when the signal can be approximated as a piece-wise constant signal. The predicted spike-times are close to those obtained experimentally in the primary electrosensory afferent neurons of weakly electric fish (Apteronotus leptorhynchus) and pyramidal neurons from the somatosensory cortex of the rat. We suggest that KCNQ/Kv7 channels (underlying the M-current) are good candidates for the decoder. They are widely coupled to metabolic processes and do not inactivate. We conclude that the neural threshold is optimized to generate an energy-efficient and high-fidelity neural code. PMID:26082710

Extracellular voltage threshold settings can be tuned for optimal encoding of movement and stimulus parameters.

PubMed

Oby, Emily R; Perel, Sagi; Sadtler, Patrick T; Ruff, Douglas A; Mischel, Jessica L; Montez, David F; Cohen, Marlene R; Batista, Aaron P; Chase, Steven M

2016-06-01

A traditional goal of neural recording with extracellular electrodes is to isolate action potential waveforms of an individual neuron. Recently, in brain-computer interfaces (BCIs), it has been recognized that threshold crossing events of the voltage waveform also convey rich information. To date, the threshold for detecting threshold crossings has been selected to preserve single-neuron isolation. However, the optimal threshold for single-neuron identification is not necessarily the optimal threshold for information extraction. Here we introduce a procedure to determine the best threshold for extracting information from extracellular recordings. We apply this procedure in two distinct contexts: the encoding of kinematic parameters from neural activity in primary motor cortex (M1), and visual stimulus parameters from neural activity in primary visual cortex (V1). We record extracellularly from multi-electrode arrays implanted in M1 or V1 in monkeys. Then, we systematically sweep the voltage detection threshold and quantify the information conveyed by the corresponding threshold crossings. The optimal threshold depends on the desired information. In M1, velocity is optimally encoded at higher thresholds than speed; in both cases the optimal thresholds are lower than are typically used in BCI applications. In V1, information about the orientation of a visual stimulus is optimally encoded at higher thresholds than is visual contrast. A conceptual model explains these results as a consequence of cortical topography. How neural signals are processed impacts the information that can be extracted from them. Both the type and quality of information contained in threshold crossings depend on the threshold setting. There is more information available in these signals than is typically extracted. Adjusting the detection threshold to the parameter of interest in a BCI context should improve our ability to decode motor intent, and thus enhance BCI control. Further, by sweeping the detection threshold, one can gain insights into the topographic organization of the nearby neural tissue.

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.

A neural-network-based model for the dynamic simulation of the tire/suspension system while traversing road irregularities.

PubMed

Guarneri, Paolo; Rocca, Gianpiero; Gobbi, Massimiliano

2008-09-01

This paper deals with the simulation of the tire/suspension dynamics by using recurrent neural networks (RNNs). RNNs are derived from the multilayer feedforward neural networks, by adding feedback connections between output and input layers. The optimal network architecture derives from a parametric analysis based on the optimal tradeoff between network accuracy and size. The neural network can be trained with experimental data obtained in the laboratory from simulated road profiles (cleats). The results obtained from the neural network demonstrate good agreement with the experimental results over a wide range of operation conditions. The NN model can be effectively applied as a part of vehicle system model to accurately predict elastic bushings and tire dynamics behavior. Although the neural network model, as a black-box model, does not provide a good insight of the physical behavior of the tire/suspension system, it is a useful tool for assessing vehicle ride and noise, vibration, harshness (NVH) performance due to its good computational efficiency and accuracy.

Neural-network-assisted genetic algorithm applied to silicon clusters

NASA Astrophysics Data System (ADS)

Marim, L. R.; Lemes, M. R.; dal Pino, A.

2003-03-01

Recently, a new optimization procedure that combines the power of artificial neural-networks with the versatility of the genetic algorithm (GA) was introduced. This method, called neural-network-assisted genetic algorithm (NAGA), uses a neural network to restrict the search space and it is expected to speed up the solution of global optimization problems if some previous information is available. In this paper, we have tested NAGA to determine the ground-state geometry of Sin (10⩽n⩽15) according to a tight-binding total-energy method. Our results indicate that NAGA was able to find the desired global minimum of the potential energy for all the test cases and it was at least ten times faster than pure genetic algorithm.

Advanced integrated enhanced vision systems

NASA Astrophysics Data System (ADS)

Kerr, J. R.; Luk, Chiu H.; Hammerstrom, Dan; Pavel, Misha

2003-09-01

In anticipation of its ultimate role in transport, business and rotary wing aircraft, we clarify the role of Enhanced Vision Systems (EVS): how the output data will be utilized, appropriate architecture for total avionics integration, pilot and control interfaces, and operational utilization. Ground-map (database) correlation is critical, and we suggest that "synthetic vision" is simply a subset of the monitor/guidance interface issue. The core of integrated EVS is its sensor processor. In order to approximate optimal, Bayesian multi-sensor fusion and ground correlation functionality in real time, we are developing a neural net approach utilizing human visual pathway and self-organizing, associative-engine processing. In addition to EVS/SVS imagery, outputs will include sensor-based navigation and attitude signals as well as hazard detection. A system architecture is described, encompassing an all-weather sensor suite; advanced processing technology; intertial, GPS and other avionics inputs; and pilot and machine interfaces. Issues of total-system accuracy and integrity are addressed, as well as flight operational aspects relating to both civil certification and military applications in IMC.

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

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.

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.

Evolvable rough-block-based neural network and its biomedical application to hypoglycemia detection system.

PubMed

San, Phyo Phyo; Ling, Sai Ho; Nuryani; Nguyen, Hung

2014-08-01

This paper focuses on the hybridization technology using rough sets concepts and neural computing for decision and classification purposes. Based on the rough set properties, the lower region and boundary region are defined to partition the input signal to a consistent (predictable) part and an inconsistent (random) part. In this way, the neural network is designed to deal only with the boundary region, which mainly consists of an inconsistent part of applied input signal causing inaccurate modeling of the data set. Owing to different characteristics of neural network (NN) applications, the same structure of conventional NN might not give the optimal solution. Based on the knowledge of application in this paper, a block-based neural network (BBNN) is selected as a suitable classifier due to its ability to evolve internal structures and adaptability in dynamic environments. This architecture will systematically incorporate the characteristics of application to the structure of hybrid rough-block-based neural network (R-BBNN). A global training algorithm, hybrid particle swarm optimization with wavelet mutation is introduced for parameter optimization of proposed R-BBNN. The performance of the proposed R-BBNN algorithm was evaluated by an application to the field of medical diagnosis using real hypoglycemia episodes in patients with Type 1 diabetes mellitus. The performance of the proposed hybrid system has been compared with some of the existing neural networks. The comparison results indicated that the proposed method has improved classification performance and results in early convergence of the network.

Neural Network and Regression Approximations in High Speed Civil Transport Aircraft Design Optimization

NASA Technical Reports Server (NTRS)

Patniak, Surya N.; Guptill, James D.; Hopkins, Dale A.; Lavelle, Thomas M.

1998-01-01

Nonlinear mathematical-programming-based design optimization can be an elegant method. However, the calculations required to generate the merit function, constraints, and their gradients, which are frequently required, can make the process computational intensive. The computational burden can be greatly reduced by using approximating analyzers derived from an original analyzer utilizing neural networks and linear regression methods. The experience gained from using both of these approximation methods in the design optimization of a high speed civil transport aircraft is the subject of this paper. The Langley Research Center's Flight Optimization System was selected for the aircraft analysis. This software was exercised to generate a set of training data with which a neural network and a regression method were trained, thereby producing the two approximating analyzers. The derived analyzers were coupled to the Lewis Research Center's CometBoards test bed to provide the optimization capability. With the combined software, both approximation methods were examined for use in aircraft design optimization, and both performed satisfactorily. The CPU time for solution of the problem, which had been measured in hours, was reduced to minutes with the neural network approximation and to seconds with the regression method. Instability encountered in the aircraft analysis software at certain design points was also eliminated. On the other hand, there were costs and difficulties associated with training the approximating analyzers. The CPU time required to generate the input-output pairs and to train the approximating analyzers was seven times that required for solution of the problem.

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.

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

Development of a Prediction Model Based on RBF Neural Network for Sheet Metal Fixture Locating Layout Design and Optimization.

PubMed

Wang, Zhongqi; Yang, Bo; Kang, Yonggang; Yang, Yuan

2016-01-01

Fixture plays an important part in constraining excessive sheet metal part deformation at machining, assembly, and measuring stages during the whole manufacturing process. However, it is still a difficult and nontrivial task to design and optimize sheet metal fixture locating layout at present because there is always no direct and explicit expression describing sheet metal fixture locating layout and responding deformation. To that end, an RBF neural network prediction model is proposed in this paper to assist design and optimization of sheet metal fixture locating layout. The RBF neural network model is constructed by training data set selected by uniform sampling and finite element simulation analysis. Finally, a case study is conducted to verify the proposed method.

Development of a Prediction Model Based on RBF Neural Network for Sheet Metal Fixture Locating Layout Design and Optimization

PubMed Central

Wang, Zhongqi; Yang, Bo; Kang, Yonggang; Yang, Yuan

2016-01-01

Fixture plays an important part in constraining excessive sheet metal part deformation at machining, assembly, and measuring stages during the whole manufacturing process. However, it is still a difficult and nontrivial task to design and optimize sheet metal fixture locating layout at present because there is always no direct and explicit expression describing sheet metal fixture locating layout and responding deformation. To that end, an RBF neural network prediction model is proposed in this paper to assist design and optimization of sheet metal fixture locating layout. The RBF neural network model is constructed by training data set selected by uniform sampling and finite element simulation analysis. Finally, a case study is conducted to verify the proposed method. PMID:27127499

Spontaneous cortical activity reveals hallmarks of an optimal internal model of the environment.

PubMed

Berkes, Pietro; Orbán, Gergo; Lengyel, Máté; Fiser, József

2011-01-07

The brain maintains internal models of its environment to interpret sensory inputs and to prepare actions. Although behavioral studies have demonstrated that these internal models are optimally adapted to the statistics of the environment, the neural underpinning of this adaptation is unknown. Using a Bayesian model of sensory cortical processing, we related stimulus-evoked and spontaneous neural activities to inferences and prior expectations in an internal model and predicted that they should match if the model is statistically optimal. To test this prediction, we analyzed visual cortical activity of awake ferrets during development. Similarity between spontaneous and evoked activities increased with age and was specific to responses evoked by natural scenes. This demonstrates the progressive adaptation of internal models to the statistics of natural stimuli at the neural level.

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

NASA Technical Reports Server (NTRS)

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

2003-01-01

A method and system for design optimization that incorporates the advantages of both traditional response surface methodology (RSM) and neural networks is disclosed. The present invention employs a unique strategy called parameter-based partitioning of the given design space. In the design procedure, a sequence of composite response surfaces based on both neural networks and polynomial fits is used to traverse the design space to identify an optimal solution. The composite response surface has both the power of neural networks and the economy of low-order polynomials (in terms of the number of simulations needed and the network training requirements). The present invention handles design problems with many more parameters than would be possible using neural networks alone and permits a designer to rapidly perform a variety of trade-off studies before arriving at the final design.

Novel cooperative neural fusion algorithms for image restoration and image fusion.

PubMed

Xia, Youshen; Kamel, Mohamed S

2007-02-01

To deal with the problem of restoring degraded images with non-Gaussian noise, this paper proposes a novel cooperative neural fusion regularization (CNFR) algorithm for image restoration. Compared with conventional regularization algorithms for image restoration, the proposed CNFR algorithm can relax need of the optimal regularization parameter to be estimated. Furthermore, to enhance the quality of restored images, this paper presents a cooperative neural fusion (CNF) algorithm for image fusion. Compared with existing signal-level image fusion algorithms, the proposed CNF algorithm can greatly reduce the loss of contrast information under blind Gaussian noise environments. The performance analysis shows that the proposed two neural fusion algorithms can converge globally to the robust and optimal image estimate. Simulation results confirm that in different noise environments, the proposed two neural fusion algorithms can obtain a better image estimate than several well known image restoration and image fusion methods.

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.

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

NASA Astrophysics Data System (ADS)

Li, Han; Zhen-yu, Zhang

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

The improved business valuation model for RFID company based on the community mining method.

PubMed

Li, Shugang; Yu, Zhaoxu

2017-01-01

Nowadays, the appetite for the investment and mergers and acquisitions (M&A) activity in RFID companies is growing rapidly. Although the huge number of papers have addressed the topic of business valuation models based on statistical methods or neural network methods, only a few are dedicated to constructing a general framework for business valuation that improves the performance with network graph (NG) and the corresponding community mining (CM) method. In this study, an NG based business valuation model is proposed, where real options approach (ROA) integrating CM method is designed to predict the company's net profit as well as estimate the company value. Three improvements are made in the proposed valuation model: Firstly, our model figures out the credibility of the node belonging to each community and clusters the network according to the evolutionary Bayesian method. Secondly, the improved bacterial foraging optimization algorithm (IBFOA) is adopted to calculate the optimized Bayesian posterior probability function. Finally, in IBFOA, bi-objective method is used to assess the accuracy of prediction, and these two objectives are combined into one objective function using a new Pareto boundary method. The proposed method returns lower forecasting error than 10 well-known forecasting models on 3 different time interval valuing tasks for the real-life simulation of RFID companies.

The improved business valuation model for RFID company based on the community mining method

PubMed Central

Li, Shugang; Yu, Zhaoxu

2017-01-01

Nowadays, the appetite for the investment and mergers and acquisitions (M&A) activity in RFID companies is growing rapidly. Although the huge number of papers have addressed the topic of business valuation models based on statistical methods or neural network methods, only a few are dedicated to constructing a general framework for business valuation that improves the performance with network graph (NG) and the corresponding community mining (CM) method. In this study, an NG based business valuation model is proposed, where real options approach (ROA) integrating CM method is designed to predict the company’s net profit as well as estimate the company value. Three improvements are made in the proposed valuation model: Firstly, our model figures out the credibility of the node belonging to each community and clusters the network according to the evolutionary Bayesian method. Secondly, the improved bacterial foraging optimization algorithm (IBFOA) is adopted to calculate the optimized Bayesian posterior probability function. Finally, in IBFOA, bi-objective method is used to assess the accuracy of prediction, and these two objectives are combined into one objective function using a new Pareto boundary method. The proposed method returns lower forecasting error than 10 well-known forecasting models on 3 different time interval valuing tasks for the real-life simulation of RFID companies. PMID:28459815

Multiobjective Particle Swarm Optimization for the optimal design of photovoltaic grid-connected systems

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

Kornelakis, Aris

2010-12-15

Particle Swarm Optimization (PSO) is a highly efficient evolutionary optimization algorithm. In this paper a multiobjective optimization algorithm based on PSO applied to the optimal design of photovoltaic grid-connected systems (PVGCSs) is presented. The proposed methodology intends to suggest the optimal number of system devices and the optimal PV module installation details, such that the economic and environmental benefits achieved during the system's operational lifetime period are both maximized. The objective function describing the economic benefit of the proposed optimization process is the lifetime system's total net profit which is calculated according to the method of the Net Present Valuemore » (NPV). The second objective function, which corresponds to the environmental benefit, equals to the pollutant gas emissions avoided due to the use of the PVGCS. The optimization's decision variables are the optimal number of the PV modules, the PV modules optimal tilt angle, the optimal placement of the PV modules within the available installation area and the optimal distribution of the PV modules among the DC/AC converters. (author)« less

Automated inspection of bread and loaves

NASA Astrophysics Data System (ADS)

Batchelor, Bruce G.

1993-08-01

The prospects for building practical automated inspection machines, capable of detecting the following faults in ordinary, everyday loaves are reviewed: (1) foreign bodies, using X-rays, (2) texture changes, using glancing illumination, mathematical morphology and Neural Net learning techniques, and (3) shape deformations, using structured lighting and simple geometry.

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.

Study on feed forward neural network convex optimization for LiFePO4 battery parameters

NASA Astrophysics Data System (ADS)

Liu, Xuepeng; Zhao, Dongmei

2017-08-01

Based on the modern facility agriculture automatic walking equipment LiFePO4 Battery, the parameter identification of LiFePO4 Battery is analyzed. An improved method for the process model of li battery is proposed, and the on-line estimation algorithm is presented. The parameters of the battery are identified using feed forward network neural convex optimization algorithm.

Performance evaluation of coherent Ising machines against classical neural networks

NASA Astrophysics Data System (ADS)

Haribara, Yoshitaka; Ishikawa, Hitoshi; Utsunomiya, Shoko; Aihara, Kazuyuki; Yamamoto, Yoshihisa

2017-12-01

The coherent Ising machine is expected to find a near-optimal solution in various combinatorial optimization problems, which has been experimentally confirmed with optical parametric oscillators and a field programmable gate array circuit. The similar mathematical models were proposed three decades ago by Hopfield et al in the context of classical neural networks. In this article, we compare the computational performance of both models.

Progress Toward Adaptive Integration and Optimization of Automated and Neural Processing Systems: Establishing Neural and Behavioral Benchmarks of Optimized Performance

DTIC Science & Technology

2014-11-01

Paradigm ............................................................................19 3.4 Collaborative BCI for Improving Overall Performance...interfaces ( BCIs ) provide the biggest improvement in performance? Can we demonstrate clear advantages with BCIs ? 2 2. Simulator Development and...stimuli in real time. Fig. 18 ROC curves for each subject after the combination of 2 trials 3.4 Collaborative BCI for Improving Overall

Cascade Optimization for Aircraft Engines With Regression and Neural Network Analysis - Approximators

NASA Technical Reports Server (NTRS)

Patnaik, Surya N.; Guptill, James D.; Hopkins, Dale A.; Lavelle, Thomas M.

2000-01-01

The NASA Engine Performance Program (NEPP) can configure and analyze almost any type of gas turbine engine that can be generated through the interconnection of a set of standard physical components. In addition, the code can optimize engine performance by changing adjustable variables under a set of constraints. However, for engine cycle problems at certain operating points, the NEPP code can encounter difficulties: nonconvergence in the currently implemented Powell's optimization algorithm and deficiencies in the Newton-Raphson solver during engine balancing. A project was undertaken to correct these deficiencies. Nonconvergence was avoided through a cascade optimization strategy, and deficiencies associated with engine balancing were eliminated through neural network and linear regression methods. An approximation-interspersed cascade strategy was used to optimize the engine's operation over its flight envelope. Replacement of Powell's algorithm by the cascade strategy improved the optimization segment of the NEPP code. The performance of the linear regression and neural network methods as alternative engine analyzers was found to be satisfactory. This report considers two examples-a supersonic mixed-flow turbofan engine and a subsonic waverotor-topped engine-to illustrate the results, and it discusses insights gained from the improved version of the NEPP code.

David Palchak | NREL

Science.gov Websites

Electrical load forecasting with artificial neural networks Demand-side management optimization with Matlab -58491. D. Palchak, S. Suryanarayanan, and D. Zimmerle. "An Artificial Neural Network in Short-Term

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.

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%.

A Collaborative Neurodynamic Approach to Multiple-Objective Distributed Optimization.

PubMed

Yang, Shaofu; Liu, Qingshan; Wang, Jun

2018-04-01

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

A genetic algorithm for optimization of neural network capable of learning to search for food in a maze

NASA Astrophysics Data System (ADS)

Budilova, E. V.; Terekhin, A. T.; Chepurnov, S. A.

1994-09-01

A hypothetical neural scheme is proposed that ensures efficient decision making by an animal searching for food in a maze. Only the general structure of the network is fixed; its quantitative characteristics are found by numerical optimization that simulates the process of natural selection. Selection is aimed at maximization of the expected number of descendants, which is directly related to the energy stored during the reproductive cycle. The main parameters to be optimized are the increments of the interneuronal links and the working-memory constants.