Modeling and Computing of Stock Index Forecasting Based on Neural Network and Markov Chain

PubMed Central

Dai, Yonghui; Han, Dongmei; Dai, Weihui

2014-01-01

The stock index reflects the fluctuation of the stock market. For a long time, there have been a lot of researches on the forecast of stock index. However, the traditional method is limited to achieving an ideal precision in the dynamic market due to the influences of many factors such as the economic situation, policy changes, and emergency events. Therefore, the approach based on adaptive modeling and conditional probability transfer causes the new attention of researchers. This paper presents a new forecast method by the combination of improved back-propagation (BP) neural network and Markov chain, as well as its modeling and computing technology. This method includes initial forecasting by improved BP neural network, division of Markov state region, computing of the state transition probability matrix, and the prediction adjustment. Results of the empirical study show that this method can achieve high accuracy in the stock index prediction, and it could provide a good reference for the investment in stock market. PMID:24782659

Fault Analysis of Space Station DC Power Systems-Using Neural Network Adaptive Wavelets to Detect Faults

NASA Technical Reports Server (NTRS)

Momoh, James A.; Wang, Yanchun; Dolce, James L.

1997-01-01

This paper describes the application of neural network adaptive wavelets for fault diagnosis of space station power system. The method combines wavelet transform with neural network by incorporating daughter wavelets into weights. Therefore, the wavelet transform and neural network training procedure become one stage, which avoids the complex computation of wavelet parameters and makes the procedure more straightforward. The simulation results show that the proposed method is very efficient for the identification of fault locations.

Hardware Acceleration of Adaptive Neural Algorithms.

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

James, Conrad D.

As tradit ional numerical computing has faced challenges, researchers have turned towards alternative computing approaches to reduce power - per - computation metrics and improve algorithm performance. Here, we describe an approach towards non - conventional computing that strengthens the connection between machine learning and neuroscience concepts. The Hardware Acceleration of Adaptive Neural Algorithms (HAANA) project ha s develop ed neural machine learning algorithms and hardware for applications in image processing and cybersecurity. While machine learning methods are effective at extracting relevant features from many types of data, the effectiveness of these algorithms degrades when subjected to real - worldmore » conditions. Our team has generated novel neural - inspired approa ches to improve the resiliency and adaptability of machine learning algorithms. In addition, we have also designed and fabricated hardware architectures and microelectronic devices specifically tuned towards the training and inference operations of neural - inspired algorithms. Finally, our multi - scale simulation framework allows us to assess the impact of microelectronic device properties on algorithm performance.« less

A Direct Position-Determination Approach for Multiple Sources Based on Neural Network Computation.

PubMed

Chen, Xin; Wang, Ding; Yin, Jiexin; Wu, Ying

2018-06-13

The most widely used localization technology is the two-step method that localizes transmitters by measuring one or more specified positioning parameters. Direct position determination (DPD) is a promising technique that directly localizes transmitters from sensor outputs and can offer superior localization performance. However, existing DPD algorithms such as maximum likelihood (ML)-based and multiple signal classification (MUSIC)-based estimations are computationally expensive, making it difficult to satisfy real-time demands. To solve this problem, we propose the use of a modular neural network for multiple-source DPD. In this method, the area of interest is divided into multiple sub-areas. Multilayer perceptron (MLP) neural networks are employed to detect the presence of a source in a sub-area and filter sources in other sub-areas, and radial basis function (RBF) neural networks are utilized for position estimation. Simulation results show that a number of appropriately trained neural networks can be successfully used for DPD. The performance of the proposed MLP-MLP-RBF method is comparable to the performance of the conventional MUSIC-based DPD algorithm for various signal-to-noise ratios and signal power ratios. Furthermore, the MLP-MLP-RBF network is less computationally intensive than the classical DPD algorithm and is therefore an attractive choice for real-time applications.

Optoelectronic Inner-Product Neural Associative Memory

NASA Technical Reports Server (NTRS)

Liu, Hua-Kuang

1993-01-01

Optoelectronic apparatus acts as artificial neural network performing associative recall of binary images. Recall process is iterative one involving optical computation of inner products between binary input vector and one or more reference binary vectors in memory. Inner-product method requires far less memory space than matrix-vector method.

Quantifying the signals contained in heterogeneous neural responses and determining their relationships with task performance

PubMed Central

Pagan, Marino

2014-01-01

The responses of high-level neurons tend to be mixtures of many different types of signals. While this diversity is thought to allow for flexible neural processing, it presents a challenge for understanding how neural responses relate to task performance and to neural computation. To address these challenges, we have developed a new method to parse the responses of individual neurons into weighted sums of intuitive signal components. Our method computes the weights by projecting a neuron's responses onto a predefined orthonormal basis. Once determined, these weights can be combined into measures of signal modulation; however, in their raw form these signal modulation measures are biased by noise. Here we introduce and evaluate two methods for correcting this bias, and we report that an analytically derived approach produces performance that is robust and superior to a bootstrap procedure. Using neural data recorded from inferotemporal cortex and perirhinal cortex as monkeys performed a delayed-match-to-sample target search task, we demonstrate how the method can be used to quantify the amounts of task-relevant signals in heterogeneous neural populations. We also demonstrate how these intuitive quantifications of signal modulation can be related to single-neuron measures of task performance (d′). PMID:24920017

CLIPS on the NeXT computer

NASA Technical Reports Server (NTRS)

Charnock, Elizabeth; Eng, Norman

1990-01-01

This paper discusses the integration of CLIPS into a hybrid expert system neural network AI tool for the NeXT computer. The main discussion is devoted to the joining of these two AI paradigms in a mutually beneficial relationship. We conclude that expert systems and neural networks should not be considered as competing AI implementation methods, but rather as complimentary components of a whole.

Numerical solution of differential equations by artificial neural networks

NASA Technical Reports Server (NTRS)

Meade, Andrew J., Jr.

1995-01-01

Conventionally programmed digital computers can process numbers with great speed and precision, but do not easily recognize patterns or imprecise or contradictory data. Instead of being programmed in the conventional sense, artificial neural networks (ANN's) are capable of self-learning through exposure to repeated examples. However, the training of an ANN can be a time consuming and unpredictable process. A general method is being developed by the author to mate the adaptability of the ANN with the speed and precision of the digital computer. This method has been successful in building feedforward networks that can approximate functions and their partial derivatives from examples in a single iteration. The general method also allows the formation of feedforward networks that can approximate the solution to nonlinear ordinary and partial differential equations to desired accuracy without the need of examples. It is believed that continued research will produce artificial neural networks that can be used with confidence in practical scientific computing and engineering applications.

Distributed computing methodology for training neural networks in an image-guided diagnostic application.

PubMed

Plagianakos, V P; Magoulas, G D; Vrahatis, M N

2006-03-01

Distributed computing is a process through which a set of computers connected by a network is used collectively to solve a single problem. In this paper, we propose a distributed computing methodology for training neural networks for the detection of lesions in colonoscopy. Our approach is based on partitioning the training set across multiple processors using a parallel virtual machine. In this way, interconnected computers of varied architectures can be used for the distributed evaluation of the error function and gradient values, and, thus, training neural networks utilizing various learning methods. The proposed methodology has large granularity and low synchronization, and has been implemented and tested. Our results indicate that the parallel virtual machine implementation of the training algorithms developed leads to considerable speedup, especially when large network architectures and training sets are used.

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.

Soft computing in design and manufacturing of advanced materials

NASA Technical Reports Server (NTRS)

Cios, Krzysztof J.; Baaklini, George Y; Vary, Alex

1993-01-01

The potential of fuzzy sets and neural networks, often referred to as soft computing, for aiding in all aspects of manufacturing of advanced materials like ceramics is addressed. In design and manufacturing of advanced materials, it is desirable to find which of the many processing variables contribute most to the desired properties of the material. There is also interest in real time quality control of parameters that govern material properties during processing stages. The concepts of fuzzy sets and neural networks are briefly introduced and it is shown how they can be used in the design and manufacturing processes. These two computational methods are alternatives to other methods such as the Taguchi method. The two methods are demonstrated by using data collected at NASA Lewis Research Center. Future research directions are also discussed.

Feature extraction using extrema sampling of discrete derivatives for spike sorting in implantable upper-limb neural prostheses.

PubMed

Zamani, Majid; Demosthenous, Andreas

2014-07-01

Next generation neural interfaces for upper-limb (and other) prostheses aim to develop implantable interfaces for one or more nerves, each interface having many neural signal channels that work reliably in the stump without harming the nerves. To achieve real-time multi-channel processing it is important to integrate spike sorting on-chip to overcome limitations in transmission bandwidth. This requires computationally efficient algorithms for feature extraction and clustering suitable for low-power hardware implementation. This paper describes a new feature extraction method for real-time spike sorting based on extrema analysis (namely positive peaks and negative peaks) of spike shapes and their discrete derivatives at different frequency bands. Employing simulation across different datasets, the accuracy and computational complexity of the proposed method are assessed and compared with other methods. The average classification accuracy of the proposed method in conjunction with online sorting (O-Sort) is 91.6%, outperforming all the other methods tested with the O-Sort clustering algorithm. The proposed method offers a better tradeoff between classification error and computational complexity, making it a particularly strong choice for on-chip spike sorting.

Distributed collaborative probabilistic design of multi-failure structure with fluid-structure interaction using fuzzy neural network of regression

NASA Astrophysics Data System (ADS)

Song, Lu-Kai; Wen, Jie; Fei, Cheng-Wei; Bai, Guang-Chen

2018-05-01

To improve the computing efficiency and precision of probabilistic design for multi-failure structure, a distributed collaborative probabilistic design method-based fuzzy neural network of regression (FR) (called as DCFRM) is proposed with the integration of distributed collaborative response surface method and fuzzy neural network regression model. The mathematical model of DCFRM is established and the probabilistic design idea with DCFRM is introduced. The probabilistic analysis of turbine blisk involving multi-failure modes (deformation failure, stress failure and strain failure) was investigated by considering fluid-structure interaction with the proposed method. The distribution characteristics, reliability degree, and sensitivity degree of each failure mode and overall failure mode on turbine blisk are obtained, which provides a useful reference for improving the performance and reliability of aeroengine. Through the comparison of methods shows that the DCFRM reshapes the probability of probabilistic analysis for multi-failure structure and improves the computing efficiency while keeping acceptable computational precision. Moreover, the proposed method offers a useful insight for reliability-based design optimization of multi-failure structure and thereby also enriches the theory and method of mechanical reliability design.

A novel neural network for the synthesis of antennas and microwave devices.

PubMed

Delgado, Heriberto Jose; Thursby, Michael H; Ham, Fredric M

2005-11-01

A novel artificial neural network (SYNTHESIS-ANN) is presented, which has been designed for computationally intensive problems and applied to the optimization of antennas and microwave devices. The antenna example presented is optimized with respect to voltage standing-wave ratio, bandwidth, and frequency of operation. A simple microstrip transmission line problem is used to further describe the ANN effectiveness, in which microstrip line width is optimized with respect to line impedance. The ANNs exploit a unique number representation of input and output data in conjunction with a more standard neural network architecture. An ANN consisting of a heteroassociative memory provided a very efficient method of computing necessary geometrical values for the antenna when used in conjunction with a new randomization process. The number representation used provides significant insight into this new method of fault-tolerant computing. Further work is needed to evaluate the potential of this new paradigm.

Evaluation of a parallel implementation of the learning portion of the backward error propagation neural network: experiments in artifact identification.

PubMed Central

Sittig, D. F.; Orr, J. A.

1991-01-01

Various methods have been proposed in an attempt to solve problems in artifact and/or alarm identification including expert systems, statistical signal processing techniques, and artificial neural networks (ANN). ANNs consist of a large number of simple processing units connected by weighted links. To develop truly robust ANNs, investigators are required to train their networks on huge training data sets, requiring enormous computing power. We implemented a parallel version of the backward error propagation neural network training algorithm in the widely portable parallel programming language C-Linda. A maximum speedup of 4.06 was obtained with six processors. This speedup represents a reduction in total run-time from approximately 6.4 hours to 1.5 hours. We conclude that use of the master-worker model of parallel computation is an excellent method for obtaining speedups in the backward error propagation neural network training algorithm. PMID:1807607

Pulmonary Nodule Classification with Deep Convolutional Neural Networks on Computed Tomography Images.

PubMed

Li, Wei; Cao, Peng; Zhao, Dazhe; Wang, Junbo

2016-01-01

Computer aided detection (CAD) systems can assist radiologists by offering a second opinion on early diagnosis of lung cancer. Classification and feature representation play critical roles in false-positive reduction (FPR) in lung nodule CAD. We design a deep convolutional neural networks method for nodule classification, which has an advantage of autolearning representation and strong generalization ability. A specified network structure for nodule images is proposed to solve the recognition of three types of nodules, that is, solid, semisolid, and ground glass opacity (GGO). Deep convolutional neural networks are trained by 62,492 regions-of-interest (ROIs) samples including 40,772 nodules and 21,720 nonnodules from the Lung Image Database Consortium (LIDC) database. Experimental results demonstrate the effectiveness of the proposed method in terms of sensitivity and overall accuracy and that it consistently outperforms the competing methods.

Dynamic decomposition of spatiotemporal neural signals

PubMed Central

2017-01-01

Neural signals are characterized by rich temporal and spatiotemporal dynamics that reflect the organization of cortical networks. Theoretical research has shown how neural networks can operate at different dynamic ranges that correspond to specific types of information processing. Here we present a data analysis framework that uses a linearized model of these dynamic states in order to decompose the measured neural signal into a series of components that capture both rhythmic and non-rhythmic neural activity. The method is based on stochastic differential equations and Gaussian process regression. Through computer simulations and analysis of magnetoencephalographic data, we demonstrate the efficacy of the method in identifying meaningful modulations of oscillatory signals corrupted by structured temporal and spatiotemporal noise. These results suggest that the method is particularly suitable for the analysis and interpretation of complex temporal and spatiotemporal neural signals. PMID:28558039

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

PubMed

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

2017-01-01

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

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

PubMed Central

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

2017-01-01

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

Deep Learning: A Primer for Radiologists.

PubMed

Chartrand, Gabriel; Cheng, Phillip M; Vorontsov, Eugene; Drozdzal, Michal; Turcotte, Simon; Pal, Christopher J; Kadoury, Samuel; Tang, An

2017-01-01

Deep learning is a class of machine learning methods that are gaining success and attracting interest in many domains, including computer vision, speech recognition, natural language processing, and playing games. Deep learning methods produce a mapping from raw inputs to desired outputs (eg, image classes). Unlike traditional machine learning methods, which require hand-engineered feature extraction from inputs, deep learning methods learn these features directly from data. With the advent of large datasets and increased computing power, these methods can produce models with exceptional performance. These models are multilayer artificial neural networks, loosely inspired by biologic neural systems. Weighted connections between nodes (neurons) in the network are iteratively adjusted based on example pairs of inputs and target outputs by back-propagating a corrective error signal through the network. For computer vision tasks, convolutional neural networks (CNNs) have proven to be effective. Recently, several clinical applications of CNNs have been proposed and studied in radiology for classification, detection, and segmentation tasks. This article reviews the key concepts of deep learning for clinical radiologists, discusses technical requirements, describes emerging applications in clinical radiology, and outlines limitations and future directions in this field. Radiologists should become familiar with the principles and potential applications of deep learning in medical imaging. © RSNA, 2017.

Enabling the First Ever Measurement of Coherent Neutrino Scattering Through Background Neutron Measurements.

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

Reyna, David; Betty, Rita

Using High Performance Computing to Examine the Processes of Neurogenesis Underlying Pattern Separation/Completion of Episodic Information - Sandia researchers developed novel methods and metrics for studying the computational function of neurogenesis,thus generating substantial impact to the neuroscience and neural computing communities. This work could benefit applications in machine learning and other analysis activities. The purpose of this project was to computationally model the impact of neural population dynamics within the neurobiological memory system in order to examine how subareas in the brain enable pattern separation and completion of information in memory across time as associated experiences.

Soft computing methods in design of superalloys

NASA Technical Reports Server (NTRS)

Cios, K. J.; Berke, L.; Vary, A.; Sharma, S.

1995-01-01

Soft computing techniques of neural networks and genetic algorithms are used in the design of superalloys. The cyclic oxidation attack parameter K(sub a), generated from tests at NASA Lewis Research Center, is modeled as a function of the superalloy chemistry and test temperature using a neural network. This model is then used in conjunction with a genetic algorithm to obtain an optimized superalloy composition resulting in low K(sub a) values.

Soft Computing Methods in Design of Superalloys

NASA Technical Reports Server (NTRS)

Cios, K. J.; Berke, L.; Vary, A.; Sharma, S.

1996-01-01

Soft computing techniques of neural networks and genetic algorithms are used in the design of superalloys. The cyclic oxidation attack parameter K(sub a), generated from tests at NASA Lewis Research Center, is modelled as a function of the superalloy chemistry and test temperature using a neural network. This model is then used in conjunction with a genetic algorithm to obtain an optimized superalloy composition resulting in low K(sub a) values.

Water Level Prediction of Lake Cascade Mahakam Using Adaptive Neural Network Backpropagation (ANNBP)

NASA Astrophysics Data System (ADS)

Mislan; Gaffar, A. F. O.; Haviluddin; Puspitasari, N.

2018-04-01

A natural hazard information and flood events are indispensable as a form of prevention and improvement. One of the causes is flooding in the areas around the lake. Therefore, forecasting the surface of Lake water level to anticipate flooding is required. The purpose of this paper is implemented computational intelligence method namely Adaptive Neural Network Backpropagation (ANNBP) to forecasting the Lake Cascade Mahakam. Based on experiment, performance of ANNBP indicated that Lake water level prediction have been accurate by using mean square error (MSE) and mean absolute percentage error (MAPE). In other words, computational intelligence method can produce good accuracy. A hybrid and optimization of computational intelligence are focus in the future work.

Gender Recognition from Human-Body Images Using Visible-Light and Thermal Camera Videos Based on a Convolutional Neural Network for Image Feature Extraction

PubMed Central

Nguyen, Dat Tien; Kim, Ki Wan; Hong, Hyung Gil; Koo, Ja Hyung; Kim, Min Cheol; Park, Kang Ryoung

2017-01-01

Extracting powerful image features plays an important role in computer vision systems. Many methods have previously been proposed to extract image features for various computer vision applications, such as the scale-invariant feature transform (SIFT), speed-up robust feature (SURF), local binary patterns (LBP), histogram of oriented gradients (HOG), and weighted HOG. Recently, the convolutional neural network (CNN) method for image feature extraction and classification in computer vision has been used in various applications. In this research, we propose a new gender recognition method for recognizing males and females in observation scenes of surveillance systems based on feature extraction from visible-light and thermal camera videos through CNN. Experimental results confirm the superiority of our proposed method over state-of-the-art recognition methods for the gender recognition problem using human body images. PMID:28335510

Gender Recognition from Human-Body Images Using Visible-Light and Thermal Camera Videos Based on a Convolutional Neural Network for Image Feature Extraction.

PubMed

Nguyen, Dat Tien; Kim, Ki Wan; Hong, Hyung Gil; Koo, Ja Hyung; Kim, Min Cheol; Park, Kang Ryoung

2017-03-20

Extracting powerful image features plays an important role in computer vision systems. Many methods have previously been proposed to extract image features for various computer vision applications, such as the scale-invariant feature transform (SIFT), speed-up robust feature (SURF), local binary patterns (LBP), histogram of oriented gradients (HOG), and weighted HOG. Recently, the convolutional neural network (CNN) method for image feature extraction and classification in computer vision has been used in various applications. In this research, we propose a new gender recognition method for recognizing males and females in observation scenes of surveillance systems based on feature extraction from visible-light and thermal camera videos through CNN. Experimental results confirm the superiority of our proposed method over state-of-the-art recognition methods for the gender recognition problem using human body images.

From systems biology to dynamical neuropharmacology: proposal for a new methodology.

PubMed

Erdi, P; Kiss, T; Tóth, J; Ujfalussy, B; Zalányi, L

2006-07-01

The concepts and methods of systems biology are extended to neuropharmacology in order to test and design drugs for the treatment of neurological and psychiatric disorders. Computational modelling by integrating compartmental neural modelling techniques and detailed kinetic descriptions of pharmacological modulation of transmitter-receptor interaction is offered as a method to test the electrophysiological and behavioural effects of putative drugs. Even more, an inverse method is suggested as a method for controlling a neural system to realise a prescribed temporal pattern. In particular, as an application of the proposed new methodology, a computational platform is offered to analyse the generation and pharmacological modulation of theta rhythm related to anxiety.

Use of neural image analysis methods in the process to determine the dry matter content in the compost

NASA Astrophysics Data System (ADS)

Wojcieszak, D.; Przybył, J.; Lewicki, A.; Ludwiczak, A.; Przybylak, A.; Boniecki, P.; Koszela, K.; Zaborowicz, M.; Przybył, K.; Witaszek, K.

2015-07-01

The aim of this research was investigate the possibility of using methods of computer image analysis and artificial neural networks for to assess the amount of dry matter in the tested compost samples. The research lead to the conclusion that the neural image analysis may be a useful tool in determining the quantity of dry matter in the compost. Generated neural model may be the beginning of research into the use of neural image analysis assess the content of dry matter and other constituents of compost. The presented model RBF 19:19-2-1:1 characterized by test error 0.092189 may be more efficient.

ChainMail based neural dynamics modeling of soft tissue deformation for surgical simulation.

PubMed

Zhang, Jinao; Zhong, Yongmin; Smith, Julian; Gu, Chengfan

2017-07-20

Realistic and real-time modeling and simulation of soft tissue deformation is a fundamental research issue in the field of surgical simulation. In this paper, a novel cellular neural network approach is presented for modeling and simulation of soft tissue deformation by combining neural dynamics of cellular neural network with ChainMail mechanism. The proposed method formulates the problem of elastic deformation into cellular neural network activities to avoid the complex computation of elasticity. The local position adjustments of ChainMail are incorporated into the cellular neural network as the local connectivity of cells, through which the dynamic behaviors of soft tissue deformation are transformed into the neural dynamics of cellular neural network. Experiments demonstrate that the proposed neural network approach is capable of modeling the soft tissues' nonlinear deformation and typical mechanical behaviors. The proposed method not only improves ChainMail's linear deformation with the nonlinear characteristics of neural dynamics but also enables the cellular neural network to follow the principle of continuum mechanics to simulate soft tissue deformation.

Relabeling exchange method (REM) for learning in neural networks

NASA Astrophysics Data System (ADS)

Wu, Wen; Mammone, Richard J.

1994-02-01

The supervised training of neural networks require the use of output labels which are usually arbitrarily assigned. In this paper it is shown that there is a significant difference in the rms error of learning when `optimal' label assignment schemes are used. We have investigated two efficient random search algorithms to solve the relabeling problem: the simulated annealing and the genetic algorithm. However, we found them to be computationally expensive. Therefore we shall introduce a new heuristic algorithm called the Relabeling Exchange Method (REM) which is computationally more attractive and produces optimal performance. REM has been used to organize the optimal structure for multi-layered perceptrons and neural tree networks. The method is a general one and can be implemented as a modification to standard training algorithms. The motivation of the new relabeling strategy is based on the present interpretation of dyslexia as an encoding problem.

A New Stochastic Technique for Painlevé Equation-I Using Neural Network Optimized with Swarm Intelligence

PubMed Central

Raja, Muhammad Asif Zahoor; Khan, Junaid Ali; Ahmad, Siraj-ul-Islam; Qureshi, Ijaz Mansoor

2012-01-01

A methodology for solution of Painlevé equation-I is presented using computational intelligence technique based on neural networks and particle swarm optimization hybridized with active set algorithm. The mathematical model of the equation is developed with the help of linear combination of feed-forward artificial neural networks that define the unsupervised error of the model. This error is minimized subject to the availability of appropriate weights of the networks. The learning of the weights is carried out using particle swarm optimization algorithm used as a tool for viable global search method, hybridized with active set algorithm for rapid local convergence. The accuracy, convergence rate, and computational complexity of the scheme are analyzed based on large number of independents runs and their comprehensive statistical analysis. The comparative studies of the results obtained are made with MATHEMATICA solutions, as well as, with variational iteration method and homotopy perturbation method. PMID:22919371

Cox-nnet: An artificial neural network method for prognosis prediction of high-throughput omics data.

PubMed

Ching, Travers; Zhu, Xun; Garmire, Lana X

2018-04-01

Artificial neural networks (ANN) are computing architectures with many interconnections of simple neural-inspired computing elements, and have been applied to biomedical fields such as imaging analysis and diagnosis. We have developed a new ANN framework called Cox-nnet to predict patient prognosis from high throughput transcriptomics data. In 10 TCGA RNA-Seq data sets, Cox-nnet achieves the same or better predictive accuracy compared to other methods, including Cox-proportional hazards regression (with LASSO, ridge, and mimimax concave penalty), Random Forests Survival and CoxBoost. Cox-nnet also reveals richer biological information, at both the pathway and gene levels. The outputs from the hidden layer node provide an alternative approach for survival-sensitive dimension reduction. In summary, we have developed a new method for accurate and efficient prognosis prediction on high throughput data, with functional biological insights. The source code is freely available at https://github.com/lanagarmire/cox-nnet.

From biological neural networks to thinking machines: Transitioning biological organizational principles to computer technology

NASA Technical Reports Server (NTRS)

Ross, Muriel D.

1991-01-01

The three-dimensional organization of the vestibular macula is under study by computer assisted reconstruction and simulation methods as a model for more complex neural systems. One goal of this research is to transition knowledge of biological neural network architecture and functioning to computer technology, to contribute to the development of thinking computers. Maculas are organized as weighted neural networks for parallel distributed processing of information. The network is characterized by non-linearity of its terminal/receptive fields. Wiring appears to develop through constrained randomness. A further property is the presence of two main circuits, highly channeled and distributed modifying, that are connected through feedforward-feedback collaterals and biasing subcircuit. Computer simulations demonstrate that differences in geometry of the feedback (afferent) collaterals affects the timing and the magnitude of voltage changes delivered to the spike initiation zone. Feedforward (efferent) collaterals act as voltage followers and likely inhibit neurons of the distributed modifying circuit. These results illustrate the importance of feedforward-feedback loops, of timing, and of inhibition in refining neural network output. They also suggest that it is the distributed modifying network that is most involved in adaptation, memory, and learning. Tests of macular adaptation, through hyper- and microgravitational studies, support this hypothesis since synapses in the distributed modifying circuit, but not the channeled circuit, are altered. Transitioning knowledge of biological systems to computer technology, however, remains problematical.

A Neural Network Aero Design System for Advanced Turbo-Engines

NASA Technical Reports Server (NTRS)

Sanz, Jose M.

1999-01-01

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

Practical approximation method for firing-rate models of coupled neural networks with correlated inputs

NASA Astrophysics Data System (ADS)

Barreiro, Andrea K.; Ly, Cheng

2017-08-01

Rapid experimental advances now enable simultaneous electrophysiological recording of neural activity at single-cell resolution across large regions of the nervous system. Models of this neural network activity will necessarily increase in size and complexity, thus increasing the computational cost of simulating them and the challenge of analyzing them. Here we present a method to approximate the activity and firing statistics of a general firing rate network model (of the Wilson-Cowan type) subject to noisy correlated background inputs. The method requires solving a system of transcendental equations and is fast compared to Monte Carlo simulations of coupled stochastic differential equations. We implement the method with several examples of coupled neural networks and show that the results are quantitatively accurate even with moderate coupling strengths and an appreciable amount of heterogeneity in many parameters. This work should be useful for investigating how various neural attributes qualitatively affect the spiking statistics of coupled neural networks.

The Cognitive, Perceptual, and Neural Bases of Skilled Performance

DTIC Science & Technology

1988-09-01

shunting, masking field, bidirectional associative memory, Volterra - Lotka , Gilpin-Ayala, ani Eigen-Schuster models. The Cohen-Grossberg model thus...field, bidirectional associative memory, Volterra - Lotka , Gilpin-Ayala, and Eigen-Schuster models. A Liapunov functional method is described for...storage by neural networks: A general model and global Liapunov method. In E.L. Schwartz (Ed.), Computational neuroscience. Cambridge, MA: MIT Press

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.

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.

Neural network approach for the calculation of potential coefficients in quantum mechanics

NASA Astrophysics Data System (ADS)

Ossandón, Sebastián; Reyes, Camilo; Cumsille, Patricio; Reyes, Carlos M.

2017-05-01

A numerical method based on artificial neural networks is used to solve the inverse Schrödinger equation for a multi-parameter class of potentials. First, the finite element method was used to solve repeatedly the direct problem for different parametrizations of the chosen potential function. Then, using the attainable eigenvalues as a training set of the direct radial basis neural network a map of new eigenvalues was obtained. This relationship was later inverted and refined by training an inverse radial basis neural network, allowing the calculation of the unknown parameters and therefore estimating the potential function. Three numerical examples are presented in order to prove the effectiveness of the method. The results show that the method proposed has the advantage to use less computational resources without a significant accuracy loss.

A Spiking Neural Simulator Integrating Event-Driven and Time-Driven Computation Schemes Using Parallel CPU-GPU Co-Processing: A Case Study.

PubMed

Naveros, Francisco; Luque, Niceto R; Garrido, Jesús A; Carrillo, Richard R; Anguita, Mancia; Ros, Eduardo

2015-07-01

Time-driven simulation methods in traditional CPU architectures perform well and precisely when simulating small-scale spiking neural networks. Nevertheless, they still have drawbacks when simulating large-scale systems. Conversely, event-driven simulation methods in CPUs and time-driven simulation methods in graphic processing units (GPUs) can outperform CPU time-driven methods under certain conditions. With this performance improvement in mind, we have developed an event-and-time-driven spiking neural network simulator suitable for a hybrid CPU-GPU platform. Our neural simulator is able to efficiently simulate bio-inspired spiking neural networks consisting of different neural models, which can be distributed heterogeneously in both small layers and large layers or subsystems. For the sake of efficiency, the low-activity parts of the neural network can be simulated in CPU using event-driven methods while the high-activity subsystems can be simulated in either CPU (a few neurons) or GPU (thousands or millions of neurons) using time-driven methods. In this brief, we have undertaken a comparative study of these different simulation methods. For benchmarking the different simulation methods and platforms, we have used a cerebellar-inspired neural-network model consisting of a very dense granular layer and a Purkinje layer with a smaller number of cells (according to biological ratios). Thus, this cerebellar-like network includes a dense diverging neural layer (increasing the dimensionality of its internal representation and sparse coding) and a converging neural layer (integration) similar to many other biologically inspired and also artificial neural networks.

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.

Foraging for brain stimulation: toward a neurobiology of computation.

PubMed

Gallistel, C R

1994-01-01

The self-stimulating rat performs foraging tasks mediated by simple computations that use interreward intervals and subjective reward magnitudes to determine stay durations. This is a simplified preparation in which to study the neurobiology of the elementary computational operations that make cognition possible, because the neural signal specifying the value of a computationally relevant variable is produced by direct electrical stimulation of a neural pathway. Newly developed measurement methods yield functions relating the subjective reward magnitude to the parameters of the neural signal. These measurements also show that the decision process that governs foraging behavior divides the subjective reward magnitude by the most recent interreward interval to determine the preferability of an option (a foraging patch). The decision process sets the parameters that determine stay durations (durations of visits to foraging patches) so that the ratios of the stay durations match the ratios of the preferabilities.

Container-code recognition system based on computer vision and deep neural networks

NASA Astrophysics Data System (ADS)

Liu, Yi; Li, Tianjian; Jiang, Li; Liang, Xiaoyao

2018-04-01

Automatic container-code recognition system becomes a crucial requirement for ship transportation industry in recent years. In this paper, an automatic container-code recognition system based on computer vision and deep neural networks is proposed. The system consists of two modules, detection module and recognition module. The detection module applies both algorithms based on computer vision and neural networks, and generates a better detection result through combination to avoid the drawbacks of the two methods. The combined detection results are also collected for online training of the neural networks. The recognition module exploits both character segmentation and end-to-end recognition, and outputs the recognition result which passes the verification. When the recognition module generates false recognition, the result will be corrected and collected for online training of the end-to-end recognition sub-module. By combining several algorithms, the system is able to deal with more situations, and the online training mechanism can improve the performance of the neural networks at runtime. The proposed system is able to achieve 93% of overall recognition accuracy.

Pruning artificial neural networks using neural complexity measures.

PubMed

Jorgensen, Thomas D; Haynes, Barry P; Norlund, Charlotte C F

2008-10-01

This paper describes a new method for pruning artificial neural networks, using a measure of the neural complexity of the neural network. This measure is used to determine the connections that should be pruned. The measure computes the information-theoretic complexity of a neural network, which is similar to, yet different from previous research on pruning. The method proposed here shows how overly large and complex networks can be reduced in size, whilst retaining learnt behaviour and fitness. The technique proposed here helps to discover a network topology that matches the complexity of the problem it is meant to solve. This novel pruning technique is tested in a robot control domain, simulating a racecar. It is shown, that the proposed pruning method is a significant improvement over the most commonly used pruning method Magnitude Based Pruning. Furthermore, some of the pruned networks prove to be faster learners than the benchmark network that they originate from. This means that this pruning method can also help to unleash hidden potential in a network, because the learning time decreases substantially for a pruned a network, due to the reduction of dimensionality of the network.

Neural control of computer cursor velocity by decoding motor cortical spiking activity in humans with tetraplegia*

PubMed Central

Kim, Sung-Phil; Simeral, John D; Hochberg, Leigh R; Donoghue, John P; Black, Michael J

2010-01-01

Computer-mediated connections between human motor cortical neurons and assistive devices promise to improve or restore lost function in people with paralysis. Recently, a pilot clinical study of an intracortical neural interface system demonstrated that a tetraplegic human was able to obtain continuous two-dimensional control of a computer cursor using neural activity recorded from his motor cortex. This control, however, was not sufficiently accurate for reliable use in many common computer control tasks. Here, we studied several central design choices for such a system including the kinematic representation for cursor movement, the decoding method that translates neuronal ensemble spiking activity into a control signal and the cursor control task used during training for optimizing the parameters of the decoding method. In two tetraplegic participants, we found that controlling a cursor's velocity resulted in more accurate closed-loop control than controlling its position directly and that cursor velocity control was achieved more rapidly than position control. Control quality was further improved over conventional linear filters by using a probabilistic method, the Kalman filter, to decode human motor cortical activity. Performance assessment based on standard metrics used for the evaluation of a wide range of pointing devices demonstrated significantly improved cursor control with velocity rather than position decoding. PMID:19015583

Improved Classification of Lung Cancer Using Radial Basis Function Neural Network with Affine Transforms of Voss Representation.

PubMed

Adetiba, Emmanuel; Olugbara, Oludayo O

2015-01-01

Lung cancer is one of the diseases responsible for a large number of cancer related death cases worldwide. The recommended standard for screening and early detection of lung cancer is the low dose computed tomography. However, many patients diagnosed die within one year, which makes it essential to find alternative approaches for screening and early detection of lung cancer. We present computational methods that can be implemented in a functional multi-genomic system for classification, screening and early detection of lung cancer victims. Samples of top ten biomarker genes previously reported to have the highest frequency of lung cancer mutations and sequences of normal biomarker genes were respectively collected from the COSMIC and NCBI databases to validate the computational methods. Experiments were performed based on the combinations of Z-curve and tetrahedron affine transforms, Histogram of Oriented Gradient (HOG), Multilayer perceptron and Gaussian Radial Basis Function (RBF) neural networks to obtain an appropriate combination of computational methods to achieve improved classification of lung cancer biomarker genes. Results show that a combination of affine transforms of Voss representation, HOG genomic features and Gaussian RBF neural network perceptibly improves classification accuracy, specificity and sensitivity of lung cancer biomarker genes as well as achieving low mean square error.

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.

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.

A Rapid Aerodynamic Design Procedure Based on Artificial Neural Networks

NASA Technical Reports Server (NTRS)

Rai, Man Mohan

2001-01-01

An aerodynamic design procedure that uses neural networks to model the functional behavior of the objective function in design space has been developed. This method incorporates several improvements to an earlier method that employed a strategy called parameter-based partitioning of the design space in order to reduce the computational costs associated with design optimization. As with the earlier method, the current method uses a sequence of response surfaces to traverse the design space in search of the optimal solution. The new method yields significant reductions in computational costs by using composite response surfaces with better generalization capabilities and by exploiting synergies between the optimization method and the simulation codes used to generate the training data. These reductions in design optimization costs are demonstrated for a turbine airfoil design study where a generic shape is evolved into an optimal airfoil.

Neural Network Training by Integration of Adjoint Systems of Equations Forward in Time

NASA Technical Reports Server (NTRS)

Toomarian, Nikzad (Inventor); Barhen, Jacob (Inventor)

1999-01-01

A method and apparatus for supervised neural learning of time dependent trajectories exploits the concepts of adjoint operators to enable computation of the gradient of an objective functional with respect to the various parameters of the network architecture in a highly efficient manner. Specifically. it combines the advantage of dramatic reductions in computational complexity inherent in adjoint methods with the ability to solve two adjoint systems of equations together forward in time. Not only is a large amount of computation and storage saved. but the handling of real-time applications becomes also possible. The invention has been applied it to two examples of representative complexity which have recently been analyzed in the open literature and demonstrated that a circular trajectory can be learned in approximately 200 iterations compared to the 12000 reported in the literature. A figure eight trajectory was achieved in under 500 iterations compared to 20000 previously required. Tbc trajectories computed using our new method are much closer to the target trajectories than was reported in previous studies.

Neural network training by integration of adjoint systems of equations forward in time

NASA Technical Reports Server (NTRS)

Toomarian, Nikzad (Inventor); Barhen, Jacob (Inventor)

1992-01-01

A method and apparatus for supervised neural learning of time dependent trajectories exploits the concepts of adjoint operators to enable computation of the gradient of an objective functional with respect to the various parameters of the network architecture in a highly efficient manner. Specifically, it combines the advantage of dramatic reductions in computational complexity inherent in adjoint methods with the ability to solve two adjoint systems of equations together forward in time. Not only is a large amount of computation and storage saved, but the handling of real-time applications becomes also possible. The invention has been applied it to two examples of representative complexity which have recently been analyzed in the open literature and demonstrated that a circular trajectory can be learned in approximately 200 iterations compared to the 12000 reported in the literature. A figure eight trajectory was achieved in under 500 iterations compared to 20000 previously required. The trajectories computed using our new method are much closer to the target trajectories than was reported in previous studies.

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).

Cox-nnet: An artificial neural network method for prognosis prediction of high-throughput omics data

PubMed Central

Ching, Travers; Zhu, Xun

2018-01-01

Artificial neural networks (ANN) are computing architectures with many interconnections of simple neural-inspired computing elements, and have been applied to biomedical fields such as imaging analysis and diagnosis. We have developed a new ANN framework called Cox-nnet to predict patient prognosis from high throughput transcriptomics data. In 10 TCGA RNA-Seq data sets, Cox-nnet achieves the same or better predictive accuracy compared to other methods, including Cox-proportional hazards regression (with LASSO, ridge, and mimimax concave penalty), Random Forests Survival and CoxBoost. Cox-nnet also reveals richer biological information, at both the pathway and gene levels. The outputs from the hidden layer node provide an alternative approach for survival-sensitive dimension reduction. In summary, we have developed a new method for accurate and efficient prognosis prediction on high throughput data, with functional biological insights. The source code is freely available at https://github.com/lanagarmire/cox-nnet. PMID:29634719

Bio-inspired computational heuristics to study Lane-Emden systems arising in astrophysics model.

PubMed

Ahmad, Iftikhar; Raja, Muhammad Asif Zahoor; Bilal, Muhammad; Ashraf, Farooq

2016-01-01

This study reports novel hybrid computational methods for the solutions of nonlinear singular Lane-Emden type differential equation arising in astrophysics models by exploiting the strength of unsupervised neural network models and stochastic optimization techniques. In the scheme the neural network, sub-part of large field called soft computing, is exploited for modelling of the equation in an unsupervised manner. The proposed approximated solutions of higher order ordinary differential equation are calculated with the weights of neural networks trained with genetic algorithm, and pattern search hybrid with sequential quadratic programming for rapid local convergence. The results of proposed solvers for solving the nonlinear singular systems are in good agreements with the standard solutions. Accuracy and convergence the design schemes are demonstrated by the results of statistical performance measures based on the sufficient large number of independent runs.

Brain-Based Devices for Neuromorphic Computer Systems

DTIC Science & Technology

2013-07-01

and Deco, G. (2012). Effective Visual Working Memory Capacity: An Emergent Effect from the Neural Dynamics in an Attractor Network. PLoS ONE 7, e42719...models, apply them to a recognition task, and to demonstrate a working memory . In the course of this work a new analytical method for spiking data was...4 3.4 Spiking Neural Model Simulation of Working Memory ..................................... 5 3.5 A Novel Method for Analysis

Quicklook Constituent Abundance and Stretch Parameter Retrieval for the Juno Microwave Radiometer using Neural Networks

NASA Astrophysics Data System (ADS)

Bellotti, A.; Steffes, P. G.

2016-12-01

The Juno Microwave Radiometer (MWR) has six channels ranging from 1.36-50 cm and the ability to peer deep into the Jovian atmosphere. An Artifical Neural Network algorithm has been developed to rapidly perform inversion for the deep abundance of ammonia, the deep abundance of water vapor, and atmospheric "stretch" (a parameter that reflects the deviation from a wet adiabate in the higher atmosphere). This algorithm is "trained" by using simulated emissions at the six wavelengths computed using the Juno atmospheric microwave radiative transfer (JAMRT) model presented by Oyafuso et al. (This meeting). By exploiting the emission measurements conducted at six wavelengths and at various incident angles, the neural network can provide preliminary results to a useful precison in a computational method hundreds of times faster than conventional methods. This can quickly provide important insights into the variability and structure of the Jovian atmosphere.

The receptive field is dead. Long live the receptive field?

PubMed Central

Fairhall, Adrienne

2014-01-01

Advances in experimental techniques, including behavioral paradigms using rich stimuli under closed loop conditions and the interfacing of neural systems with external inputs and outputs, reveal complex dynamics in the neural code and require a revisiting of standard concepts of representation. High-throughput recording and imaging methods along with the ability to observe and control neuronal subpopulations allow increasingly detailed access to the neural circuitry that subserves these representations and the computations they support. How do we harness theory to build biologically grounded models of complex neural function? PMID:24618227

Prediction of 5-year overall survival in cervical cancer patients treated with radical hysterectomy using computational intelligence methods.

PubMed

Obrzut, Bogdan; Kusy, Maciej; Semczuk, Andrzej; Obrzut, Marzanna; Kluska, Jacek

2017-12-12

Computational intelligence methods, including non-linear classification algorithms, can be used in medical research and practice as a decision making tool. This study aimed to evaluate the usefulness of artificial intelligence models for 5-year overall survival prediction in patients with cervical cancer treated by radical hysterectomy. The data set was collected from 102 patients with cervical cancer FIGO stage IA2-IIB, that underwent primary surgical treatment. Twenty-three demographic, tumor-related parameters and selected perioperative data of each patient were collected. The simulations involved six computational intelligence methods: the probabilistic neural network (PNN), multilayer perceptron network, gene expression programming classifier, support vector machines algorithm, radial basis function neural network and k-Means algorithm. The prediction ability of the models was determined based on the accuracy, sensitivity, specificity, as well as the area under the receiver operating characteristic curve. The results of the computational intelligence methods were compared with the results of linear regression analysis as a reference model. The best results were obtained by the PNN model. This neural network provided very high prediction ability with an accuracy of 0.892 and sensitivity of 0.975. The area under the receiver operating characteristics curve of PNN was also high, 0.818. The outcomes obtained by other classifiers were markedly worse. The PNN model is an effective tool for predicting 5-year overall survival in cervical cancer patients treated with radical hysterectomy.

Prediction of the Thermal Conductivity of Refrigerants by Computational Methods and Artificial Neural Network.

PubMed

Ghaderi, Forouzan; Ghaderi, Amir H; Ghaderi, Noushin; Najafi, Bijan

2017-01-01

Background: The thermal conductivity of fluids can be calculated by several computational methods. However, these methods are reliable only at the confined levels of density, and there is no specific computational method for calculating thermal conductivity in the wide ranges of density. Methods: In this paper, two methods, an Artificial Neural Network (ANN) approach and a computational method established upon the Rainwater-Friend theory, were used to predict the value of thermal conductivity in all ranges of density. The thermal conductivity of six refrigerants, R12, R14, R32, R115, R143, and R152 was predicted by these methods and the effectiveness of models was specified and compared. Results: The results show that the computational method is a usable method for predicting thermal conductivity at low levels of density. However, the efficiency of this model is considerably reduced in the mid-range of density. It means that this model cannot be used at density levels which are higher than 6. On the other hand, the ANN approach is a reliable method for thermal conductivity prediction in all ranges of density. The best accuracy of ANN is achieved when the number of units is increased in the hidden layer. Conclusion: The results of the computational method indicate that the regular dependence between thermal conductivity and density at higher densities is eliminated. It can develop a nonlinear problem. Therefore, analytical approaches are not able to predict thermal conductivity in wide ranges of density. Instead, a nonlinear approach such as, ANN is a valuable method for this purpose.

Prediction of the Thermal Conductivity of Refrigerants by Computational Methods and Artificial Neural Network

PubMed Central

Ghaderi, Forouzan; Ghaderi, Amir H.; Ghaderi, Noushin; Najafi, Bijan

2017-01-01

Background: The thermal conductivity of fluids can be calculated by several computational methods. However, these methods are reliable only at the confined levels of density, and there is no specific computational method for calculating thermal conductivity in the wide ranges of density. Methods: In this paper, two methods, an Artificial Neural Network (ANN) approach and a computational method established upon the Rainwater-Friend theory, were used to predict the value of thermal conductivity in all ranges of density. The thermal conductivity of six refrigerants, R12, R14, R32, R115, R143, and R152 was predicted by these methods and the effectiveness of models was specified and compared. Results: The results show that the computational method is a usable method for predicting thermal conductivity at low levels of density. However, the efficiency of this model is considerably reduced in the mid-range of density. It means that this model cannot be used at density levels which are higher than 6. On the other hand, the ANN approach is a reliable method for thermal conductivity prediction in all ranges of density. The best accuracy of ANN is achieved when the number of units is increased in the hidden layer. Conclusion: The results of the computational method indicate that the regular dependence between thermal conductivity and density at higher densities is eliminated. It can develop a nonlinear problem. Therefore, analytical approaches are not able to predict thermal conductivity in wide ranges of density. Instead, a nonlinear approach such as, ANN is a valuable method for this purpose. PMID:29188217

SAGRAD: A Program for Neural Network Training with Simulated Annealing and the Conjugate Gradient Method.

PubMed

Bernal, Javier; Torres-Jimenez, Jose

2015-01-01

SAGRAD (Simulated Annealing GRADient), a Fortran 77 program for computing neural networks for classification using batch learning, is discussed. Neural network training in SAGRAD is based on a combination of simulated annealing and Møller's scaled conjugate gradient algorithm, the latter a variation of the traditional conjugate gradient method, better suited for the nonquadratic nature of neural networks. Different aspects of the implementation of the training process in SAGRAD are discussed, such as the efficient computation of gradients and multiplication of vectors by Hessian matrices that are required by Møller's algorithm; the (re)initialization of weights with simulated annealing required to (re)start Møller's algorithm the first time and each time thereafter that it shows insufficient progress in reaching a possibly local minimum; and the use of simulated annealing when Møller's algorithm, after possibly making considerable progress, becomes stuck at a local minimum or flat area of weight space. Outlines of the scaled conjugate gradient algorithm, the simulated annealing procedure and the training process used in SAGRAD are presented together with results from running SAGRAD on two examples of training data.

Deep convolutional neural networks for automatic classification of gastric carcinoma using whole slide images in digital histopathology.

PubMed

Sharma, Harshita; Zerbe, Norman; Klempert, Iris; Hellwich, Olaf; Hufnagl, Peter

2017-11-01

Deep learning using convolutional neural networks is an actively emerging field in histological image analysis. This study explores deep learning methods for computer-aided classification in H&E stained histopathological whole slide images of gastric carcinoma. An introductory convolutional neural network architecture is proposed for two computerized applications, namely, cancer classification based on immunohistochemical response and necrosis detection based on the existence of tumor necrosis in the tissue. Classification performance of the developed deep learning approach is quantitatively compared with traditional image analysis methods in digital histopathology requiring prior computation of handcrafted features, such as statistical measures using gray level co-occurrence matrix, Gabor filter-bank responses, LBP histograms, gray histograms, HSV histograms and RGB histograms, followed by random forest machine learning. Additionally, the widely known AlexNet deep convolutional framework is comparatively analyzed for the corresponding classification problems. The proposed convolutional neural network architecture reports favorable results, with an overall classification accuracy of 0.6990 for cancer classification and 0.8144 for necrosis detection. Copyright © 2017 Elsevier Ltd. All rights reserved.

Comparing visual representations across human fMRI and computational vision

PubMed Central

Leeds, Daniel D.; Seibert, Darren A.; Pyles, John A.; Tarr, Michael J.

2013-01-01

Feedforward visual object perception recruits a cortical network that is assumed to be hierarchical, progressing from basic visual features to complete object representations. However, the nature of the intermediate features related to this transformation remains poorly understood. Here, we explore how well different computer vision recognition models account for neural object encoding across the human cortical visual pathway as measured using fMRI. These neural data, collected during the viewing of 60 images of real-world objects, were analyzed with a searchlight procedure as in Kriegeskorte, Goebel, and Bandettini (2006): Within each searchlight sphere, the obtained patterns of neural activity for all 60 objects were compared to model responses for each computer recognition algorithm using representational dissimilarity analysis (Kriegeskorte et al., 2008). Although each of the computer vision methods significantly accounted for some of the neural data, among the different models, the scale invariant feature transform (Lowe, 2004), encoding local visual properties gathered from “interest points,” was best able to accurately and consistently account for stimulus representations within the ventral pathway. More generally, when present, significance was observed in regions of the ventral-temporal cortex associated with intermediate-level object perception. Differences in model effectiveness and the neural location of significant matches may be attributable to the fact that each model implements a different featural basis for representing objects (e.g., more holistic or more parts-based). Overall, we conclude that well-known computer vision recognition systems may serve as viable proxies for theories of intermediate visual object representation. PMID:24273227

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.

Dynamic interactions in neural networks

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

Arbib, M.A.; Amari, S.

The study of neural networks is enjoying a great renaissance, both in computational neuroscience, the development of information processing models of living brains, and in neural computing, the use of neurally inspired concepts in the construction of intelligent machines. This volume presents models and data on the dynamic interactions occurring in the brain, and exhibits the dynamic interactions between research in computational neuroscience and in neural computing. The authors present current research, future trends and open problems.

Developing a multimodal biometric authentication system using soft computing methods.

PubMed

Malcangi, Mario

2015-01-01

Robust personal authentication is becoming ever more important in computer-based applications. Among a variety of methods, biometric offers several advantages, mainly in embedded system applications. Hard and soft multi-biometric, combined with hard and soft computing methods, can be applied to improve the personal authentication process and to generalize the applicability. This chapter describes the embedded implementation of a multi-biometric (voiceprint and fingerprint) multimodal identification system based on hard computing methods (DSP) for feature extraction and matching, an artificial neural network (ANN) for soft feature pattern matching, and a fuzzy logic engine (FLE) for data fusion and decision.

Face Recognition in Humans and Machines

NASA Astrophysics Data System (ADS)

O'Toole, Alice; Tistarelli, Massimo

The study of human face recognition by psychologists and neuroscientists has run parallel to the development of automatic face recognition technologies by computer scientists and engineers. In both cases, there are analogous steps of data acquisition, image processing, and the formation of representations that can support the complex and diverse tasks we accomplish with faces. These processes can be understood and compared in the context of their neural and computational implementations. In this chapter, we present the essential elements of face recognition by humans and machines, taking a perspective that spans psychological, neural, and computational approaches. From the human side, we overview the methods and techniques used in the neurobiology of face recognition, the underlying neural architecture of the system, the role of visual attention, and the nature of the representations that emerges. From the computational side, we discuss face recognition technologies and the strategies they use to overcome challenges to robust operation over viewing parameters. Finally, we conclude the chapter with a look at some recent studies that compare human and machine performances at face recognition.

Delay-slope-dependent stability results of recurrent neural networks.

PubMed

Li, Tao; Zheng, Wei Xing; Lin, Chong

2011-12-01

By using the fact that the neuron activation functions are sector bounded and nondecreasing, this brief presents a new method, named the delay-slope-dependent method, for stability analysis of a class of recurrent neural networks with time-varying delays. This method includes more information on the slope of neuron activation functions and fewer matrix variables in the constructed Lyapunov-Krasovskii functional. Then some improved delay-dependent stability criteria with less computational burden and conservatism are obtained. Numerical examples are given to illustrate the effectiveness and the benefits of the proposed method.

Neural decoding of collective wisdom with multi-brain computing.

PubMed

Eckstein, Miguel P; Das, Koel; Pham, Binh T; Peterson, Matthew F; Abbey, Craig K; Sy, Jocelyn L; Giesbrecht, Barry

2012-01-02

Group decisions and even aggregation of multiple opinions lead to greater decision accuracy, a phenomenon known as collective wisdom. Little is known about the neural basis of collective wisdom and whether its benefits arise in late decision stages or in early sensory coding. Here, we use electroencephalography and multi-brain computing with twenty humans making perceptual decisions to show that combining neural activity across brains increases decision accuracy paralleling the improvements shown by aggregating the observers' opinions. Although the largest gains result from an optimal linear combination of neural decision variables across brains, a simpler neural majority decision rule, ubiquitous in human behavior, results in substantial benefits. In contrast, an extreme neural response rule, akin to a group following the most extreme opinion, results in the least improvement with group size. Analyses controlling for number of electrodes and time-points while increasing number of brains demonstrate unique benefits arising from integrating neural activity across different brains. The benefits of multi-brain integration are present in neural activity as early as 200 ms after stimulus presentation in lateral occipital sites and no additional benefits arise in decision related neural activity. Sensory-related neural activity can predict collective choices reached by aggregating individual opinions, voting results, and decision confidence as accurately as neural activity related to decision components. Estimation of the potential for the collective to execute fast decisions by combining information across numerous brains, a strategy prevalent in many animals, shows large time-savings. Together, the findings suggest that for perceptual decisions the neural activity supporting collective wisdom and decisions arises in early sensory stages and that many properties of collective cognition are explainable by the neural coding of information across multiple brains. Finally, our methods highlight the potential of multi-brain computing as a technique to rapidly and in parallel gather increased information about the environment as well as to access collective perceptual/cognitive choices and mental states. Copyright © 2011 Elsevier Inc. All rights reserved.

Population coding and decoding in a neural field: a computational study.

PubMed

Wu, Si; Amari, Shun-Ichi; Nakahara, Hiroyuki

2002-05-01

This study uses a neural field model to investigate computational aspects of population coding and decoding when the stimulus is a single variable. A general prototype model for the encoding process is proposed, in which neural responses are correlated, with strength specified by a gaussian function of their difference in preferred stimuli. Based on the model, we study the effect of correlation on the Fisher information, compare the performances of three decoding methods that differ in the amount of encoding information being used, and investigate the implementation of the three methods by using a recurrent network. This study not only rediscovers main results in existing literatures in a unified way, but also reveals important new features, especially when the neural correlation is strong. As the neural correlation of firing becomes larger, the Fisher information decreases drastically. We confirm that as the width of correlation increases, the Fisher information saturates and no longer increases in proportion to the number of neurons. However, we prove that as the width increases further--wider than (sqrt)2 times the effective width of the turning function--the Fisher information increases again, and it increases without limit in proportion to the number of neurons. Furthermore, we clarify the asymptotic efficiency of the maximum likelihood inference (MLI) type of decoding methods for correlated neural signals. It shows that when the correlation covers a nonlocal range of population (excepting the uniform correlation and when the noise is extremely small), the MLI type of method, whose decoding error satisfies the Cauchy-type distribution, is not asymptotically efficient. This implies that the variance is no longer adequate to measure decoding accuracy.

Neural Network Optimization of Ligament Stiffnesses for the Enhanced Predictive Ability of a Patient-Specific, Computational Foot/Ankle Model.

PubMed

Chande, Ruchi D; Wayne, Jennifer S

2017-09-01

Computational models of diarthrodial joints serve to inform the biomechanical function of these structures, and as such, must be supplied appropriate inputs for performance that is representative of actual joint function. Inputs for these models are sourced from both imaging modalities as well as literature. The latter is often the source of mechanical properties for soft tissues, like ligament stiffnesses; however, such data are not always available for all the soft tissues nor is it known for patient-specific work. In the current research, a method to improve the ligament stiffness definition for a computational foot/ankle model was sought with the greater goal of improving the predictive ability of the computational model. Specifically, the stiffness values were optimized using artificial neural networks (ANNs); both feedforward and radial basis function networks (RBFNs) were considered. Optimal networks of each type were determined and subsequently used to predict stiffnesses for the foot/ankle model. Ultimately, the predicted stiffnesses were considered reasonable and resulted in enhanced performance of the computational model, suggesting that artificial neural networks can be used to optimize stiffness inputs.

Reinforced Adversarial Neural Computer for de Novo Molecular Design.

PubMed

Putin, Evgeny; Asadulaev, Arip; Ivanenkov, Yan; Aladinskiy, Vladimir; Sanchez-Lengeling, Benjamin; Aspuru-Guzik, Alán; Zhavoronkov, Alex

2018-06-12

In silico modeling is a crucial milestone in modern drug design and development. Although computer-aided approaches in this field are well-studied, the application of deep learning methods in this research area is at the beginning. In this work, we present an original deep neural network (DNN) architecture named RANC (Reinforced Adversarial Neural Computer) for the de novo design of novel small-molecule organic structures based on the generative adversarial network (GAN) paradigm and reinforcement learning (RL). As a generator RANC uses a differentiable neural computer (DNC), a category of neural networks, with increased generation capabilities due to the addition of an explicit memory bank, which can mitigate common problems found in adversarial settings. The comparative results have shown that RANC trained on the SMILES string representation of the molecules outperforms its first DNN-based counterpart ORGANIC by several metrics relevant to drug discovery: the number of unique structures, passing medicinal chemistry filters (MCFs), Muegge criteria, and high QED scores. RANC is able to generate structures that match the distributions of the key chemical features/descriptors (e.g., MW, logP, TPSA) and lengths of the SMILES strings in the training data set. Therefore, RANC can be reasonably regarded as a promising starting point to develop novel molecules with activity against different biological targets or pathways. In addition, this approach allows scientists to save time and covers a broad chemical space populated with novel and diverse compounds.

Computational modeling of neural plasticity for self-organization of neural networks.

PubMed

Chrol-Cannon, Joseph; Jin, Yaochu

2014-11-01

Self-organization in biological nervous systems during the lifetime is known to largely occur through a process of plasticity that is dependent upon the spike-timing activity in connected neurons. In the field of computational neuroscience, much effort has been dedicated to building up computational models of neural plasticity to replicate experimental data. Most recently, increasing attention has been paid to understanding the role of neural plasticity in functional and structural neural self-organization, as well as its influence on the learning performance of neural networks for accomplishing machine learning tasks such as classification and regression. Although many ideas and hypothesis have been suggested, the relationship between the structure, dynamics and learning performance of neural networks remains elusive. The purpose of this article is to review the most important computational models for neural plasticity and discuss various ideas about neural plasticity's role. Finally, we suggest a few promising research directions, in particular those along the line that combines findings in computational neuroscience and systems biology, and their synergetic roles in understanding learning, memory and cognition, thereby bridging the gap between computational neuroscience, systems biology and computational intelligence. Copyright © 2014 Elsevier Ireland Ltd. All rights reserved.

Some comparisons of complexity in dictionary-based and linear computational models.

PubMed

Gnecco, Giorgio; Kůrková, Věra; Sanguineti, Marcello

2011-03-01

Neural networks provide a more flexible approximation of functions than traditional linear regression. In the latter, one can only adjust the coefficients in linear combinations of fixed sets of functions, such as orthogonal polynomials or Hermite functions, while for neural networks, one may also adjust the parameters of the functions which are being combined. However, some useful properties of linear approximators (such as uniqueness, homogeneity, and continuity of best approximation operators) are not satisfied by neural networks. Moreover, optimization of parameters in neural networks becomes more difficult than in linear regression. Experimental results suggest that these drawbacks of neural networks are offset by substantially lower model complexity, allowing accuracy of approximation even in high-dimensional cases. We give some theoretical results comparing requirements on model complexity for two types of approximators, the traditional linear ones and so called variable-basis types, which include neural networks, radial, and kernel models. We compare upper bounds on worst-case errors in variable-basis approximation with lower bounds on such errors for any linear approximator. Using methods from nonlinear approximation and integral representations tailored to computational units, we describe some cases where neural networks outperform any linear approximator. Copyright © 2010 Elsevier Ltd. All rights reserved.

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.

Compact VLSI neural computer integrated with active pixel sensor for real-time ATR applications

NASA Astrophysics Data System (ADS)

Fang, Wai-Chi; Udomkesmalee, Gabriel; Alkalai, Leon

1997-04-01

A compact VLSI neural computer integrated with an active pixel sensor has been under development to mimic what is inherent in biological vision systems. This electronic eye- brain computer is targeted for real-time machine vision applications which require both high-bandwidth communication and high-performance computing for data sensing, synergy of multiple types of sensory information, feature extraction, target detection, target recognition, and control functions. The neural computer is based on a composite structure which combines Annealing Cellular Neural Network (ACNN) and Hierarchical Self-Organization Neural Network (HSONN). The ACNN architecture is a programmable and scalable multi- dimensional array of annealing neurons which are locally connected with their local neurons. Meanwhile, the HSONN adopts a hierarchical structure with nonlinear basis functions. The ACNN+HSONN neural computer is effectively designed to perform programmable functions for machine vision processing in all levels with its embedded host processor. It provides a two order-of-magnitude increase in computation power over the state-of-the-art microcomputer and DSP microelectronics. A compact current-mode VLSI design feasibility of the ACNN+HSONN neural computer is demonstrated by a 3D 16X8X9-cube neural processor chip design in a 2-micrometers CMOS technology. Integration of this neural computer as one slice of a 4'X4' multichip module into the 3D MCM based avionics architecture for NASA's New Millennium Program is also described.

The graph neural network model.

PubMed

Scarselli, Franco; Gori, Marco; Tsoi, Ah Chung; Hagenbuchner, Markus; Monfardini, Gabriele

2009-01-01

Many underlying relationships among data in several areas of science and engineering, e.g., computer vision, molecular chemistry, molecular biology, pattern recognition, and data mining, can be represented in terms of graphs. In this paper, we propose a new neural network model, called graph neural network (GNN) model, that extends existing neural network methods for processing the data represented in graph domains. This GNN model, which can directly process most of the practically useful types of graphs, e.g., acyclic, cyclic, directed, and undirected, implements a function tau(G,n) is an element of IR(m) that maps a graph G and one of its nodes n into an m-dimensional Euclidean space. A supervised learning algorithm is derived to estimate the parameters of the proposed GNN model. The computational cost of the proposed algorithm is also considered. Some experimental results are shown to validate the proposed learning algorithm, and to demonstrate its generalization capabilities.

Fuzzy wavelet plus a quantum neural network as a design base for power system stability enhancement.

PubMed

Ganjefar, Soheil; Tofighi, Morteza; Karami, Hamidreza

2015-11-01

In this study, we introduce an indirect adaptive fuzzy wavelet neural controller (IAFWNC) as a power system stabilizer to damp inter-area modes of oscillations in a multi-machine power system. Quantum computing is an efficient method for improving the computational efficiency of neural networks, so we developed an identifier based on a quantum neural network (QNN) to train the IAFWNC in the proposed scheme. All of the controller parameters are tuned online based on the Lyapunov stability theory to guarantee the closed-loop stability. A two-machine, two-area power system equipped with a static synchronous series compensator as a series flexible ac transmission system was used to demonstrate the effectiveness of the proposed controller. The simulation and experimental results demonstrated that the proposed IAFWNC scheme can achieve favorable control performance. Copyright © 2015 Elsevier Ltd. All rights reserved.

A method of optimized neural network by L-M algorithm to transformer winding hot spot temperature forecasting

NASA Astrophysics Data System (ADS)

Wei, B. G.; Wu, X. Y.; Yao, Z. F.; Huang, H.

2017-11-01

Transformers are essential devices of the power system. The accurate computation of the highest temperature (HST) of a transformer’s windings is very significant, as for the HST is a fundamental parameter in controlling the load operation mode and influencing the life time of the insulation. Based on the analysis of the heat transfer processes and the thermal characteristics inside transformers, there is taken into consideration the influence of factors like the sunshine, external wind speed etc. on the oil-immersed transformers. Experimental data and the neural network are used for modeling and protesting of the HST, and furthermore, investigations are conducted on the optimization of the structure and algorithms of neutral network are conducted. Comparison is made between the measured values and calculated values by using the recommended algorithm of IEC60076 and by using the neural network algorithm proposed by the authors; comparison that shows that the value computed with the neural network algorithm approximates better the measured value than the value computed with the algorithm proposed by IEC60076.

Using High Performance Computing to Examine the Processes of Neurogenesis Underlying Pattern Separation/Completion of Episodic Information.

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

Aimone, James Bradley; Betty, Rita

Using High Performance Computing to Examine the Processes of Neurogenesis Underlying Pattern Separation/Completion of Episodic Information - Sandia researchers developed novel methods and metrics for studying the computational function of neurogenesis, thus generating substantial impact to the neuroscience and neural computing communities. This work could benefit applications in machine learning and other analysis activities.

Neural-Dynamic-Method-Based Dual-Arm CMG Scheme With Time-Varying Constraints Applied to Humanoid Robots.

PubMed

Zhang, Zhijun; Li, Zhijun; Zhang, Yunong; Luo, Yamei; Li, Yuanqing

2015-12-01

We propose a dual-arm cyclic-motion-generation (DACMG) scheme by a neural-dynamic method, which can remedy the joint-angle-drift phenomenon of a humanoid robot. In particular, according to a neural-dynamic design method, first, a cyclic-motion performance index is exploited and applied. This cyclic-motion performance index is then integrated into a quadratic programming (QP)-type scheme with time-varying constraints, called the time-varying-constrained DACMG (TVC-DACMG) scheme. The scheme includes the kinematic motion equations of two arms and the time-varying joint limits. The scheme can not only generate the cyclic motion of two arms for a humanoid robot but also control the arms to move to the desired position. In addition, the scheme considers the physical limit avoidance. To solve the QP problem, a recurrent neural network is presented and used to obtain the optimal solutions. Computer simulations and physical experiments demonstrate the effectiveness and the accuracy of such a TVC-DACMG scheme and the neural network solver.

Concurrent heterogeneous neural model simulation on real-time neuromimetic hardware.

PubMed

Rast, Alexander; Galluppi, Francesco; Davies, Sergio; Plana, Luis; Patterson, Cameron; Sharp, Thomas; Lester, David; Furber, Steve

2011-11-01

Dedicated hardware is becoming increasingly essential to simulate emerging very-large-scale neural models. Equally, however, it needs to be able to support multiple models of the neural dynamics, possibly operating simultaneously within the same system. This may be necessary either to simulate large models with heterogeneous neural types, or to simplify simulation and analysis of detailed, complex models in a large simulation by isolating the new model to a small subpopulation of a larger overall network. The SpiNNaker neuromimetic chip is a dedicated neural processor able to support such heterogeneous simulations. Implementing these models on-chip uses an integrated library-based tool chain incorporating the emerging PyNN interface that allows a modeller to input a high-level description and use an automated process to generate an on-chip simulation. Simulations using both LIF and Izhikevich models demonstrate the ability of the SpiNNaker system to generate and simulate heterogeneous networks on-chip, while illustrating, through the network-scale effects of wavefront synchronisation and burst gating, methods that can provide effective behavioural abstractions for large-scale hardware modelling. SpiNNaker's asynchronous virtual architecture permits greater scope for model exploration, with scalable levels of functional and temporal abstraction, than conventional (or neuromorphic) computing platforms. The complete system illustrates a potential path to understanding the neural model of computation, by building (and breaking) neural models at various scales, connecting the blocks, then comparing them against the biology: computational cognitive neuroscience. Copyright © 2011 Elsevier Ltd. All rights reserved.

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.

The Cluster Variation Method: A Primer for Neuroscientists.

PubMed

Maren, Alianna J

2016-09-30

Effective Brain-Computer Interfaces (BCIs) require that the time-varying activation patterns of 2-D neural ensembles be modelled. The cluster variation method (CVM) offers a means for the characterization of 2-D local pattern distributions. This paper provides neuroscientists and BCI researchers with a CVM tutorial that will help them to understand how the CVM statistical thermodynamics formulation can model 2-D pattern distributions expressing structural and functional dynamics in the brain. The premise is that local-in-time free energy minimization works alongside neural connectivity adaptation, supporting the development and stabilization of consistent stimulus-specific responsive activation patterns. The equilibrium distribution of local patterns, or configuration variables , is defined in terms of a single interaction enthalpy parameter ( h ) for the case of an equiprobable distribution of bistate (neural/neural ensemble) units. Thus, either one enthalpy parameter (or two, for the case of non-equiprobable distribution) yields equilibrium configuration variable values. Modeling 2-D neural activation distribution patterns with the representational layer of a computational engine, we can thus correlate variational free energy minimization with specific configuration variable distributions. The CVM triplet configuration variables also map well to the notion of a M = 3 functional motif. This paper addresses the special case of an equiprobable unit distribution, for which an analytic solution can be found.

Applying Gradient Descent in Convolutional Neural Networks

NASA Astrophysics Data System (ADS)

Cui, Nan

2018-04-01

With the development of the integrated circuit and computer science, people become caring more about solving practical issues via information technologies. Along with that, a new subject called Artificial Intelligent (AI) comes up. One popular research interest of AI is about recognition algorithm. In this paper, one of the most common algorithms, Convolutional Neural Networks (CNNs) will be introduced, for image recognition. Understanding its theory and structure is of great significance for every scholar who is interested in this field. Convolution Neural Network is an artificial neural network which combines the mathematical method of convolution and neural network. The hieratical structure of CNN provides it reliable computer speed and reasonable error rate. The most significant characteristics of CNNs are feature extraction, weight sharing and dimension reduction. Meanwhile, combining with the Back Propagation (BP) mechanism and the Gradient Descent (GD) method, CNNs has the ability to self-study and in-depth learning. Basically, BP provides an opportunity for backwardfeedback for enhancing reliability and GD is used for self-training process. This paper mainly discusses the CNN and the related BP and GD algorithms, including the basic structure and function of CNN, details of each layer, the principles and features of BP and GD, and some examples in practice with a summary in the end.

The Cluster Variation Method: A Primer for Neuroscientists

PubMed Central

Maren, Alianna J.

2016-01-01

Effective Brain–Computer Interfaces (BCIs) require that the time-varying activation patterns of 2-D neural ensembles be modelled. The cluster variation method (CVM) offers a means for the characterization of 2-D local pattern distributions. This paper provides neuroscientists and BCI researchers with a CVM tutorial that will help them to understand how the CVM statistical thermodynamics formulation can model 2-D pattern distributions expressing structural and functional dynamics in the brain. The premise is that local-in-time free energy minimization works alongside neural connectivity adaptation, supporting the development and stabilization of consistent stimulus-specific responsive activation patterns. The equilibrium distribution of local patterns, or configuration variables, is defined in terms of a single interaction enthalpy parameter (h) for the case of an equiprobable distribution of bistate (neural/neural ensemble) units. Thus, either one enthalpy parameter (or two, for the case of non-equiprobable distribution) yields equilibrium configuration variable values. Modeling 2-D neural activation distribution patterns with the representational layer of a computational engine, we can thus correlate variational free energy minimization with specific configuration variable distributions. The CVM triplet configuration variables also map well to the notion of a M = 3 functional motif. This paper addresses the special case of an equiprobable unit distribution, for which an analytic solution can be found. PMID:27706022

A Dynamic Bioinspired Neural Network Based Real-Time Path Planning Method for Autonomous Underwater Vehicles

PubMed Central

2017-01-01

Real-time path planning for autonomous underwater vehicle (AUV) is a very difficult and challenging task. Bioinspired neural network (BINN) has been used to deal with this problem for its many distinct advantages: that is, no learning process is needed and realization is also easy. However, there are some shortcomings when BINN is applied to AUV path planning in a three-dimensional (3D) unknown environment, including complex computing problem when the environment is very large and repeated path problem when the size of obstacles is bigger than the detection range of sensors. To deal with these problems, an improved dynamic BINN is proposed in this paper. In this proposed method, the AUV is regarded as the core of the BINN and the size of the BINN is based on the detection range of sensors. Then the BINN will move with the AUV and the computing could be reduced. A virtual target is proposed in the path planning method to ensure that the AUV can move to the real target effectively and avoid big-size obstacles automatically. Furthermore, a target attractor concept is introduced to improve the computing efficiency of neural activities. Finally, some experiments are conducted under various 3D underwater environments. The experimental results show that the proposed BINN based method can deal with the real-time path planning problem for AUV efficiently. PMID:28255297

A Dynamic Bioinspired Neural Network Based Real-Time Path Planning Method for Autonomous Underwater Vehicles.

PubMed

Ni, Jianjun; Wu, Liuying; Shi, Pengfei; Yang, Simon X

2017-01-01

Real-time path planning for autonomous underwater vehicle (AUV) is a very difficult and challenging task. Bioinspired neural network (BINN) has been used to deal with this problem for its many distinct advantages: that is, no learning process is needed and realization is also easy. However, there are some shortcomings when BINN is applied to AUV path planning in a three-dimensional (3D) unknown environment, including complex computing problem when the environment is very large and repeated path problem when the size of obstacles is bigger than the detection range of sensors. To deal with these problems, an improved dynamic BINN is proposed in this paper. In this proposed method, the AUV is regarded as the core of the BINN and the size of the BINN is based on the detection range of sensors. Then the BINN will move with the AUV and the computing could be reduced. A virtual target is proposed in the path planning method to ensure that the AUV can move to the real target effectively and avoid big-size obstacles automatically. Furthermore, a target attractor concept is introduced to improve the computing efficiency of neural activities. Finally, some experiments are conducted under various 3D underwater environments. The experimental results show that the proposed BINN based method can deal with the real-time path planning problem for AUV efficiently.

A real-time spike sorting method based on the embedded GPU.

PubMed

Zelan Yang; Kedi Xu; Xiang Tian; Shaomin Zhang; Xiaoxiang Zheng

2017-07-01

Microelectrode arrays with hundreds of channels have been widely used to acquire neuron population signals in neuroscience studies. Online spike sorting is becoming one of the most important challenges for high-throughput neural signal acquisition systems. Graphic processing unit (GPU) with high parallel computing capability might provide an alternative solution for increasing real-time computational demands on spike sorting. This study reported a method of real-time spike sorting through computing unified device architecture (CUDA) which was implemented on an embedded GPU (NVIDIA JETSON Tegra K1, TK1). The sorting approach is based on the principal component analysis (PCA) and K-means. By analyzing the parallelism of each process, the method was further optimized in the thread memory model of GPU. Our results showed that the GPU-based classifier on TK1 is 37.92 times faster than the MATLAB-based classifier on PC while their accuracies were the same with each other. The high-performance computing features of embedded GPU demonstrated in our studies suggested that the embedded GPU provide a promising platform for the real-time neural signal processing.

Reduced-Order Modeling for Flutter/LCO Using Recurrent Artificial Neural Network

NASA Technical Reports Server (NTRS)

Yao, Weigang; Liou, Meng-Sing

2012-01-01

The present study demonstrates the efficacy of a recurrent artificial neural network to provide a high fidelity time-dependent nonlinear reduced-order model (ROM) for flutter/limit-cycle oscillation (LCO) modeling. An artificial neural network is a relatively straightforward nonlinear method for modeling an input-output relationship from a set of known data, for which we use the radial basis function (RBF) with its parameters determined through a training process. The resulting RBF neural network, however, is only static and is not yet adequate for an application to problems of dynamic nature. The recurrent neural network method [1] is applied to construct a reduced order model resulting from a series of high-fidelity time-dependent data of aero-elastic simulations. Once the RBF neural network ROM is constructed properly, an accurate approximate solution can be obtained at a fraction of the cost of a full-order computation. The method derived during the study has been validated for predicting nonlinear aerodynamic forces in transonic flow and is capable of accurate flutter/LCO simulations. The obtained results indicate that the present recurrent RBF neural network is accurate and efficient for nonlinear aero-elastic system analysis

Neuromorphic neural interfaces: from neurophysiological inspiration to biohybrid coupling with nervous systems

NASA Astrophysics Data System (ADS)

Broccard, Frédéric D.; Joshi, Siddharth; Wang, Jun; Cauwenberghs, Gert

2017-08-01

Objective. Computation in nervous systems operates with different computational primitives, and on different hardware, than traditional digital computation and is thus subjected to different constraints from its digital counterpart regarding the use of physical resources such as time, space and energy. In an effort to better understand neural computation on a physical medium with similar spatiotemporal and energetic constraints, the field of neuromorphic engineering aims to design and implement electronic systems that emulate in very large-scale integration (VLSI) hardware the organization and functions of neural systems at multiple levels of biological organization, from individual neurons up to large circuits and networks. Mixed analog/digital neuromorphic VLSI systems are compact, consume little power and operate in real time independently of the size and complexity of the model. Approach. This article highlights the current efforts to interface neuromorphic systems with neural systems at multiple levels of biological organization, from the synaptic to the system level, and discusses the prospects for future biohybrid systems with neuromorphic circuits of greater complexity. Main results. Single silicon neurons have been interfaced successfully with invertebrate and vertebrate neural networks. This approach allowed the investigation of neural properties that are inaccessible with traditional techniques while providing a realistic biological context not achievable with traditional numerical modeling methods. At the network level, populations of neurons are envisioned to communicate bidirectionally with neuromorphic processors of hundreds or thousands of silicon neurons. Recent work on brain-machine interfaces suggests that this is feasible with current neuromorphic technology. Significance. Biohybrid interfaces between biological neurons and VLSI neuromorphic systems of varying complexity have started to emerge in the literature. Primarily intended as a computational tool for investigating fundamental questions related to neural dynamics, the sophistication of current neuromorphic systems now allows direct interfaces with large neuronal networks and circuits, resulting in potentially interesting clinical applications for neuroengineering systems, neuroprosthetics and neurorehabilitation.

Hermite Functional Link Neural Network for Solving the Van der Pol-Duffing Oscillator Equation.

PubMed

Mall, Susmita; Chakraverty, S

2016-08-01

Hermite polynomial-based functional link artificial neural network (FLANN) is proposed here to solve the Van der Pol-Duffing oscillator equation. A single-layer hermite neural network (HeNN) model is used, where a hidden layer is replaced by expansion block of input pattern using Hermite orthogonal polynomials. A feedforward neural network model with the unsupervised error backpropagation principle is used for modifying the network parameters and minimizing the computed error function. The Van der Pol-Duffing and Duffing oscillator equations may not be solved exactly. Here, approximate solutions of these types of equations have been obtained by applying the HeNN model for the first time. Three mathematical example problems and two real-life application problems of Van der Pol-Duffing oscillator equation, extracting the features of early mechanical failure signal and weak signal detection problems, are solved using the proposed HeNN method. HeNN approximate solutions have been compared with results obtained by the well known Runge-Kutta method. Computed results are depicted in term of graphs. After training the HeNN model, we may use it as a black box to get numerical results at any arbitrary point in the domain. Thus, the proposed HeNN method is efficient. The results reveal that this method is reliable and can be applied to other nonlinear problems too.

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.

Neural networks and applications tutorial

NASA Astrophysics Data System (ADS)

Guyon, I.

1991-09-01

The importance of neural networks has grown dramatically during this decade. While only a few years ago they were primarily of academic interest, now dozens of companies and many universities are investigating the potential use of these systems and products are beginning to appear. The idea of building a machine whose architecture is inspired by that of the brain has roots which go far back in history. Nowadays, technological advances of computers and the availability of custom integrated circuits, permit simulations of hundreds or even thousands of neurons. In conjunction, the growing interest in learning machines, non-linear dynamics and parallel computation spurred renewed attention in artificial neural networks. Many tentative applications have been proposed, including decision systems (associative memories, classifiers, data compressors and optimizers), or parametric models for signal processing purposes (system identification, automatic control, noise canceling, etc.). While they do not always outperform standard methods, neural network approaches are already used in some real world applications for pattern recognition and signal processing tasks. The tutorial is divided into six lectures, that where presented at the Third Graduate Summer Course on Computational Physics (September 3-7, 1990) on Parallel Architectures and Applications, organized by the European Physical Society: (1) Introduction: machine learning and biological computation. (2) Adaptive artificial neurons (perceptron, ADALINE, sigmoid units, etc.): learning rules and implementations. (3) Neural network systems: architectures, learning algorithms. (4) Applications: pattern recognition, signal processing, etc. (5) Elements of learning theory: how to build networks which generalize. (6) A case study: a neural network for on-line recognition of handwritten alphanumeric characters.

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.

Modular neural networks: a survey.

PubMed

Auda, G; Kamel, M

1999-04-01

Modular Neural Networks (MNNs) is a rapidly growing field in artificial Neural Networks (NNs) research. This paper surveys the different motivations for creating MNNs: biological, psychological, hardware, and computational. Then, the general stages of MNN design are outlined and surveyed as well, viz., task decomposition techniques, learning schemes and multi-module decision-making strategies. Advantages and disadvantages of the surveyed methods are pointed out, and an assessment with respect to practical potential is provided. Finally, some general recommendations for future designs are presented.

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.

A Double Dwell High Sensitivity GPS Acquisition Scheme Using Binarized Convolution Neural Network

PubMed Central

Wang, Zhen; Zhuang, Yuan; Yang, Jun; Zhang, Hengfeng; Dong, Wei; Wang, Min; Hua, Luchi; Liu, Bo; Shi, Longxing

2018-01-01

Conventional GPS acquisition methods, such as Max selection and threshold crossing (MAX/TC), estimate GPS code/Doppler by its correlation peak. Different from MAX/TC, a multi-layer binarized convolution neural network (BCNN) is proposed to recognize the GPS acquisition correlation envelope in this article. The proposed method is a double dwell acquisition in which a short integration is adopted in the first dwell and a long integration is applied in the second one. To reduce the search space for parameters, BCNN detects the possible envelope which contains the auto-correlation peak in the first dwell to compress the initial search space to 1/1023. Although there is a long integration in the second dwell, the acquisition computation overhead is still low due to the compressed search space. Comprehensively, the total computation overhead of the proposed method is only 1/5 of conventional ones. Experiments show that the proposed double dwell/correlation envelope identification (DD/CEI) neural network achieves 2 dB improvement when compared with the MAX/TC under the same specification. PMID:29747373

Computing with Neural Synchrony

PubMed Central

Brette, Romain

2012-01-01

Neurons communicate primarily with spikes, but most theories of neural computation are based on firing rates. Yet, many experimental observations suggest that the temporal coordination of spikes plays a role in sensory processing. Among potential spike-based codes, synchrony appears as a good candidate because neural firing and plasticity are sensitive to fine input correlations. However, it is unclear what role synchrony may play in neural computation, and what functional advantage it may provide. With a theoretical approach, I show that the computational interest of neural synchrony appears when neurons have heterogeneous properties. In this context, the relationship between stimuli and neural synchrony is captured by the concept of synchrony receptive field, the set of stimuli which induce synchronous responses in a group of neurons. In a heterogeneous neural population, it appears that synchrony patterns represent structure or sensory invariants in stimuli, which can then be detected by postsynaptic neurons. The required neural circuitry can spontaneously emerge with spike-timing-dependent plasticity. Using examples in different sensory modalities, I show that this allows simple neural circuits to extract relevant information from realistic sensory stimuli, for example to identify a fluctuating odor in the presence of distractors. This theory of synchrony-based computation shows that relative spike timing may indeed have computational relevance, and suggests new types of neural network models for sensory processing with appealing computational properties. PMID:22719243

Learning-based computing techniques in geoid modeling for precise height transformation

NASA Astrophysics Data System (ADS)

Erol, B.; Erol, S.

2013-03-01

Precise determination of local geoid is of particular importance for establishing height control in geodetic GNSS applications, since the classical leveling technique is too laborious. A geoid model can be accurately obtained employing properly distributed benchmarks having GNSS and leveling observations using an appropriate computing algorithm. Besides the classical multivariable polynomial regression equations (MPRE), this study attempts an evaluation of learning based computing algorithms: artificial neural networks (ANNs), adaptive network-based fuzzy inference system (ANFIS) and especially the wavelet neural networks (WNNs) approach in geoid surface approximation. These algorithms were developed parallel to advances in computer technologies and recently have been used for solving complex nonlinear problems of many applications. However, they are rather new in dealing with precise modeling problem of the Earth gravity field. In the scope of the study, these methods were applied to Istanbul GPS Triangulation Network data. The performances of the methods were assessed considering the validation results of the geoid models at the observation points. In conclusion the ANFIS and WNN revealed higher prediction accuracies compared to ANN and MPRE methods. Beside the prediction capabilities, these methods were also compared and discussed from the practical point of view in conclusions.

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

Modeling of frost crystal growth over a flat plate using artificial neural networks and fractal geometries

NASA Astrophysics Data System (ADS)

Tahavvor, Ali Reza

2017-03-01

In the present study artificial neural network and fractal geometry are used to predict frost thickness and density on a cold flat plate having constant surface temperature under forced convection for different ambient conditions. These methods are very applicable in this area because phase changes such as melting and solidification are simulated by conventional methods but frost formation is a most complicated phase change phenomenon consists of coupled heat and mass transfer. Therefore conventional mathematical techniques cannot capture the effects of all parameters on its growth and development because this process influenced by many factors and it is a time dependent process. Therefore, in this work soft computing method such as artificial neural network and fractal geometry are used to do this manner. The databases for modeling are generated from the experimental measurements. First, multilayer perceptron network is used and it is found that the back-propagation algorithm with Levenberg-Marquardt learning rule is the best choice to estimate frost growth properties due to accurate and faster training procedure. Second, fractal geometry based on the Von-Koch curve is used to model frost growth procedure especially in frost thickness and density. Comparison is performed between experimental measurements and soft computing methods. Results show that soft computing methods can be used more efficiently to determine frost properties over a flat plate. Based on the developed models, wide range of frost formation over flat plates can be determined for various conditions.

Multiscale Quantum Mechanics/Molecular Mechanics Simulations with Neural Networks.

PubMed

Shen, Lin; Wu, Jingheng; Yang, Weitao

2016-10-11

Molecular dynamics simulation with multiscale quantum mechanics/molecular mechanics (QM/MM) methods is a very powerful tool for understanding the mechanism of chemical and biological processes in solution or enzymes. However, its computational cost can be too high for many biochemical systems because of the large number of ab initio QM calculations. Semiempirical QM/MM simulations have much higher efficiency. Its accuracy can be improved with a correction to reach the ab initio QM/MM level. The computational cost on the ab initio calculation for the correction determines the efficiency. In this paper we developed a neural network method for QM/MM calculation as an extension of the neural-network representation reported by Behler and Parrinello. With this approach, the potential energy of any configuration along the reaction path for a given QM/MM system can be predicted at the ab initio QM/MM level based on the semiempirical QM/MM simulations. We further applied this method to three reactions in water to calculate the free energy changes. The free-energy profile obtained from the semiempirical QM/MM simulation is corrected to the ab initio QM/MM level with the potential energies predicted with the constructed neural network. The results are in excellent accordance with the reference data that are obtained from the ab initio QM/MM molecular dynamics simulation or corrected with direct ab initio QM/MM potential energies. Compared with the correction using direct ab initio QM/MM potential energies, our method shows a speed-up of 1 or 2 orders of magnitude. It demonstrates that the neural network method combined with the semiempirical QM/MM calculation can be an efficient and reliable strategy for chemical reaction simulations.

The dynamics of discrete-time computation, with application to recurrent neural networks and finite state machine extraction.

PubMed

Casey, M

1996-08-15

Recurrent neural networks (RNNs) can learn to perform finite state computations. It is shown that an RNN performing a finite state computation must organize its state space to mimic the states in the minimal deterministic finite state machine that can perform that computation, and a precise description of the attractor structure of such systems is given. This knowledge effectively predicts activation space dynamics, which allows one to understand RNN computation dynamics in spite of complexity in activation dynamics. This theory provides a theoretical framework for understanding finite state machine (FSM) extraction techniques and can be used to improve training methods for RNNs performing FSM computations. This provides an example of a successful approach to understanding a general class of complex systems that has not been explicitly designed, e.g., systems that have evolved or learned their internal structure.

Training Deep Spiking Neural Networks Using Backpropagation.

PubMed

Lee, Jun Haeng; Delbruck, Tobi; Pfeiffer, Michael

2016-01-01

Deep spiking neural networks (SNNs) hold the potential for improving the latency and energy efficiency of deep neural networks through data-driven event-based computation. However, training such networks is difficult due to the non-differentiable nature of spike events. In this paper, we introduce a novel technique, which treats the membrane potentials of spiking neurons as differentiable signals, where discontinuities at spike times are considered as noise. This enables an error backpropagation mechanism for deep SNNs that follows the same principles as in conventional deep networks, but works directly on spike signals and membrane potentials. Compared with previous methods relying on indirect training and conversion, our technique has the potential to capture the statistics of spikes more precisely. We evaluate the proposed framework on artificially generated events from the original MNIST handwritten digit benchmark, and also on the N-MNIST benchmark recorded with an event-based dynamic vision sensor, in which the proposed method reduces the error rate by a factor of more than three compared to the best previous SNN, and also achieves a higher accuracy than a conventional convolutional neural network (CNN) trained and tested on the same data. We demonstrate in the context of the MNIST task that thanks to their event-driven operation, deep SNNs (both fully connected and convolutional) trained with our method achieve accuracy equivalent with conventional neural networks. In the N-MNIST example, equivalent accuracy is achieved with about five times fewer computational operations.

Reconstruction of three-dimensional porous media using generative adversarial neural networks

NASA Astrophysics Data System (ADS)

Mosser, Lukas; Dubrule, Olivier; Blunt, Martin J.

2017-10-01

To evaluate the variability of multiphase flow properties of porous media at the pore scale, it is necessary to acquire a number of representative samples of the void-solid structure. While modern x-ray computer tomography has made it possible to extract three-dimensional images of the pore space, assessment of the variability in the inherent material properties is often experimentally not feasible. We present a method to reconstruct the solid-void structure of porous media by applying a generative neural network that allows an implicit description of the probability distribution represented by three-dimensional image data sets. We show, by using an adversarial learning approach for neural networks, that this method of unsupervised learning is able to generate representative samples of porous media that honor their statistics. We successfully compare measures of pore morphology, such as the Euler characteristic, two-point statistics, and directional single-phase permeability of synthetic realizations with the calculated properties of a bead pack, Berea sandstone, and Ketton limestone. Results show that generative adversarial networks can be used to reconstruct high-resolution three-dimensional images of porous media at different scales that are representative of the morphology of the images used to train the neural network. The fully convolutional nature of the trained neural network allows the generation of large samples while maintaining computational efficiency. Compared to classical stochastic methods of image reconstruction, the implicit representation of the learned data distribution can be stored and reused to generate multiple realizations of the pore structure very rapidly.

[Computer aided diagnosis model for lung tumor based on ensemble convolutional neural network].

PubMed

Wang, Yuanyuan; Zhou, Tao; Lu, Huiling; Wu, Cuiying; Yang, Pengfei

2017-08-01

The convolutional neural network (CNN) could be used on computer-aided diagnosis of lung tumor with positron emission tomography (PET)/computed tomography (CT), which can provide accurate quantitative analysis to compensate for visual inertia and defects in gray-scale sensitivity, and help doctors diagnose accurately. Firstly, parameter migration method is used to build three CNNs (CT-CNN, PET-CNN, and PET/CT-CNN) for lung tumor recognition in CT, PET, and PET/CT image, respectively. Then, we aimed at CT-CNN to obtain the appropriate model parameters for CNN training through analysis the influence of model parameters such as epochs, batchsize and image scale on recognition rate and training time. Finally, three single CNNs are used to construct ensemble CNN, and then lung tumor PET/CT recognition was completed through relative majority vote method and the performance between ensemble CNN and single CNN was compared. The experiment results show that the ensemble CNN is better than single CNN on computer-aided diagnosis of lung tumor.

Parallel consensual neural networks.

PubMed

Benediktsson, J A; Sveinsson, J R; Ersoy, O K; Swain, P H

1997-01-01

A new type of a neural-network architecture, the parallel consensual neural network (PCNN), is introduced and applied in classification/data fusion of multisource remote sensing and geographic data. The PCNN architecture is based on statistical consensus theory and involves using stage neural networks with transformed input data. The input data are transformed several times and the different transformed data are used as if they were independent inputs. The independent inputs are first classified using the stage neural networks. The output responses from the stage networks are then weighted and combined to make a consensual decision. In this paper, optimization methods are used in order to weight the outputs from the stage networks. Two approaches are proposed to compute the data transforms for the PCNN, one for binary data and another for analog data. The analog approach uses wavelet packets. The experimental results obtained with the proposed approach show that the PCNN outperforms both a conjugate-gradient backpropagation neural network and conventional statistical methods in terms of overall classification accuracy of test data.

Neural control of computer cursor velocity by decoding motor cortical spiking activity in humans with tetraplegia

NASA Astrophysics Data System (ADS)

Kim, Sung-Phil; Simeral, John D.; Hochberg, Leigh R.; Donoghue, John P.; Black, Michael J.

2008-12-01

Computer-mediated connections between human motor cortical neurons and assistive devices promise to improve or restore lost function in people with paralysis. Recently, a pilot clinical study of an intracortical neural interface system demonstrated that a tetraplegic human was able to obtain continuous two-dimensional control of a computer cursor using neural activity recorded from his motor cortex. This control, however, was not sufficiently accurate for reliable use in many common computer control tasks. Here, we studied several central design choices for such a system including the kinematic representation for cursor movement, the decoding method that translates neuronal ensemble spiking activity into a control signal and the cursor control task used during training for optimizing the parameters of the decoding method. In two tetraplegic participants, we found that controlling a cursor's velocity resulted in more accurate closed-loop control than controlling its position directly and that cursor velocity control was achieved more rapidly than position control. Control quality was further improved over conventional linear filters by using a probabilistic method, the Kalman filter, to decode human motor cortical activity. Performance assessment based on standard metrics used for the evaluation of a wide range of pointing devices demonstrated significantly improved cursor control with velocity rather than position decoding. Disclosure. JPD is the Chief Scientific Officer and a director of Cyberkinetics Neurotechnology Systems (CYKN); he holds stock and receives compensation. JDS has been a consultant for CYKN. LRH receives clinical trial support from CYKN.

A fresh look at functional link neural network for motor imagery-based brain-computer interface.

PubMed

Hettiarachchi, Imali T; Babaei, Toktam; Nguyen, Thanh; Lim, Chee P; Nahavandi, Saeid

2018-05-04

Artificial neural networks (ANNs) are one of the widely used classifiers in the brain-computer interface (BCI) systems-based on noninvasive electroencephalography (EEG) signals. Among the different ANN architectures, the most commonly applied for BCI classifiers is the multilayer perceptron (MLP). When appropriately designed with optimal number of neuron layers and number of neurons per layer, the ANN can act as a universal approximator. However, due to the low signal-to-noise ratio of EEG signal data, overtraining problem may become an inherent issue, causing these universal approximators to fail in real-time applications. In this study we introduce a higher order neural network, namely the functional link neural network (FLNN) as a classifier for motor imagery (MI)-based BCI systems, to remedy the drawbacks in MLP. We compare the proposed method with competing classifiers such as linear decomposition analysis, naïve Bayes, k-nearest neighbours, support vector machine and three MLP architectures. Two multi-class benchmark datasets from the BCI competitions are used. Common spatial pattern algorithm is utilized for feature extraction to build classification models. FLNN reports the highest average Kappa value over multiple subjects for both the BCI competition datasets, under similarly preprocessed data and extracted features. Further, statistical comparison results over multiple subjects show that the proposed FLNN classification method yields the best performance among the competing classifiers. Findings from this study imply that the proposed method, which has less computational complexity compared to the MLP, can be implemented effectively in practical MI-based BCI systems. Copyright © 2018 Elsevier B.V. All rights reserved.

Audio Classification in Speech and Music: A Comparison between a Statistical and a Neural Approach

NASA Astrophysics Data System (ADS)

Bugatti, Alessandro; Flammini, Alessandra; Migliorati, Pierangelo

2002-12-01

We focus the attention on the problem of audio classification in speech and music for multimedia applications. In particular, we present a comparison between two different techniques for speech/music discrimination. The first method is based on Zero crossing rate and Bayesian classification. It is very simple from a computational point of view, and gives good results in case of pure music or speech. The simulation results show that some performance degradation arises when the music segment contains also some speech superimposed on music, or strong rhythmic components. To overcome these problems, we propose a second method, that uses more features, and is based on neural networks (specifically a multi-layer Perceptron). In this case we obtain better performance, at the expense of a limited growth in the computational complexity. In practice, the proposed neural network is simple to be implemented if a suitable polynomial is used as the activation function, and a real-time implementation is possible even if low-cost embedded systems are used.

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.

Neural correlates and neural computations in posterior parietal cortex during perceptual decision-making

PubMed Central

Huk, Alexander C.; Meister, Miriam L. R.

2012-01-01

A recent line of work has found remarkable success in relating perceptual decision-making and the spiking activity in the macaque lateral intraparietal area (LIP). In this review, we focus on questions about the neural computations in LIP that are not answered by demonstrations of neural correlates of psychological processes. We highlight three areas of limitations in our current understanding of the precise neural computations that might underlie neural correlates of decisions: (1) empirical questions not yet answered by existing data; (2) implementation issues related to how neural circuits could actually implement the mechanisms suggested by both extracellular neurophysiology and psychophysics; and (3) ecological constraints related to the use of well-controlled laboratory tasks and whether they provide an accurate window on sensorimotor computation. These issues motivate the adoption of a more general “encoding-decoding framework” that will be fruitful for more detailed contemplation of how neural computations in LIP relate to the formation of perceptual decisions. PMID:23087623

The prediction in computer color matching of dentistry based on GA+BP neural network.

PubMed

Li, Haisheng; Lai, Long; Chen, Li; Lu, Cheng; Cai, Qiang

2015-01-01

Although the use of computer color matching can reduce the influence of subjective factors by technicians, matching the color of a natural tooth with a ceramic restoration is still one of the most challenging topics in esthetic prosthodontics. Back propagation neural network (BPNN) has already been introduced into the computer color matching in dentistry, but it has disadvantages such as unstable and low accuracy. In our study, we adopt genetic algorithm (GA) to optimize the initial weights and threshold values in BPNN for improving the matching precision. To our knowledge, we firstly combine the BPNN with GA in computer color matching in dentistry. Extensive experiments demonstrate that the proposed method improves the precision and prediction robustness of the color matching in restorative dentistry.

Collective Computation of Neural Network

DTIC Science & Technology

1990-03-15

Sciences, Beijing ABSTRACT Computational neuroscience is a new branch of neuroscience originating from current research on the theory of computer...scientists working in artificial intelligence engineering and neuroscience . The paper introduces the collective computational properties of model neural...vision research. On this basis, the authors analyzed the significance of the Hopfield model. Key phrases: Computational Neuroscience , Neural Network, Model

Investigating the Use of Coherence Analysis on Mandibular Electromyograms to Investigate Neural Control of Early Oromandibular Behaviours: A Pilot Study

ERIC Educational Resources Information Center

Steeve, Roger W.; Price, Christiana M.

2010-01-01

An empirical method for investigating differences in neural control of jaw movement across oromandibular behaviours is to compute the coherence function for electromyographic signals obtained from mandibular muscle groups. This procedure has been used with adults but not extended to children. This pilot study investigated if coherence analysis…

SAGRAD: A Program for Neural Network Training with Simulated Annealing and the Conjugate Gradient Method

PubMed Central

Bernal, Javier; Torres-Jimenez, Jose

2015-01-01

SAGRAD (Simulated Annealing GRADient), a Fortran 77 program for computing neural networks for classification using batch learning, is discussed. Neural network training in SAGRAD is based on a combination of simulated annealing and Møller’s scaled conjugate gradient algorithm, the latter a variation of the traditional conjugate gradient method, better suited for the nonquadratic nature of neural networks. Different aspects of the implementation of the training process in SAGRAD are discussed, such as the efficient computation of gradients and multiplication of vectors by Hessian matrices that are required by Møller’s algorithm; the (re)initialization of weights with simulated annealing required to (re)start Møller’s algorithm the first time and each time thereafter that it shows insufficient progress in reaching a possibly local minimum; and the use of simulated annealing when Møller’s algorithm, after possibly making considerable progress, becomes stuck at a local minimum or flat area of weight space. Outlines of the scaled conjugate gradient algorithm, the simulated annealing procedure and the training process used in SAGRAD are presented together with results from running SAGRAD on two examples of training data. PMID:26958442

Tomography and generative training with quantum Boltzmann machines

NASA Astrophysics Data System (ADS)

Kieferová, Mária; Wiebe, Nathan

2017-12-01

The promise of quantum neural nets, which utilize quantum effects to model complex data sets, has made their development an aspirational goal for quantum machine learning and quantum computing in general. Here we provide methods of training quantum Boltzmann machines. Our work generalizes existing methods and provides additional approaches for training quantum neural networks that compare favorably to existing methods. We further demonstrate that quantum Boltzmann machines enable a form of partial quantum state tomography that further provides a generative model for the input quantum state. Classical Boltzmann machines are incapable of this. This verifies the long-conjectured connection between tomography and quantum machine learning. Finally, we prove that classical computers cannot simulate our training process in general unless BQP=BPP , provide lower bounds on the complexity of the training procedures and numerically investigate training for small nonstoquastic Hamiltonians.

Neurosecurity: security and privacy for neural devices.

PubMed

Denning, Tamara; Matsuoka, Yoky; Kohno, Tadayoshi

2009-07-01

An increasing number of neural implantable devices will become available in the near future due to advances in neural engineering. This discipline holds the potential to improve many patients' lives dramatically by offering improved-and in some cases entirely new-forms of rehabilitation for conditions ranging from missing limbs to degenerative cognitive diseases. The use of standard engineering practices, medical trials, and neuroethical evaluations during the design process can create systems that are safe and that follow ethical guidelines; unfortunately, none of these disciplines currently ensure that neural devices are robust against adversarial entities trying to exploit these devices to alter, block, or eavesdrop on neural signals. The authors define "neurosecurity"-a version of computer science security principles and methods applied to neural engineering-and discuss why neurosecurity should be a critical consideration in the design of future neural devices.

Multi-criteria decision making development of ion chromatographic method for determination of inorganic anions in oilfield waters based on artificial neural networks retention model.

PubMed

Stefanović, Stefica Cerjan; Bolanča, Tomislav; Luša, Melita; Ukić, Sime; Rogošić, Marko

2012-02-24

This paper describes the development of ad hoc methodology for determination of inorganic anions in oilfield water, since their composition often significantly differs from the average (concentration of components and/or matrix). Therefore, fast and reliable method development has to be performed in order to ensure the monitoring of desired properties under new conditions. The method development was based on computer assisted multi-criteria decision making strategy. The used criteria were: maximal value of objective functions used, maximal robustness of the separation method, minimal analysis time, and maximal retention distance between two nearest components. Artificial neural networks were used for modeling of anion retention. The reliability of developed method was extensively tested by the validation of performance characteristics. Based on validation results, the developed method shows satisfactory performance characteristics, proving the successful application of computer assisted methodology in the described case study. Copyright © 2011 Elsevier B.V. All rights reserved.

Ab initio potential-energy surfaces for complex, multichannel systems using modified novelty sampling and feedforward neural networks

NASA Astrophysics Data System (ADS)

Raff, L. M.; Malshe, M.; Hagan, M.; Doughan, D. I.; Rockley, M. G.; Komanduri, R.

2005-02-01

A neural network/trajectory approach is presented for the development of accurate potential-energy hypersurfaces that can be utilized to conduct ab initio molecular dynamics (AIMD) and Monte Carlo studies of gas-phase chemical reactions, nanometric cutting, and nanotribology, and of a variety of mechanical properties of importance in potential microelectromechanical systems applications. The method is sufficiently robust that it can be applied to a wide range of polyatomic systems. The overall method integrates ab initio electronic structure calculations with importance sampling techniques that permit the critical regions of configuration space to be determined. The computed ab initio energies and gradients are then accurately interpolated using neural networks (NN) rather than arbitrary parametrized analytical functional forms, moving interpolation or least-squares methods. The sampling method involves a tight integration of molecular dynamics calculations with neural networks that employ early stopping and regularization procedures to improve network performance and test for convergence. The procedure can be initiated using an empirical potential surface or direct dynamics. The accuracy and interpolation power of the method has been tested for two cases, the global potential surface for vinyl bromide undergoing unimolecular decomposition via four different reaction channels and nanometric cutting of silicon. The results show that the sampling methods permit the important regions of configuration space to be easily and rapidly identified, that convergence of the NN fit to the ab initio electronic structure database can be easily monitored, and that the interpolation accuracy of the NN fits is excellent, even for systems involving five atoms or more. The method permits a substantial computational speed and accuracy advantage over existing methods, is robust, and relatively easy to implement.

Neural assembly computing.

PubMed

Ranhel, João

2012-06-01

Spiking neurons can realize several computational operations when firing cooperatively. This is a prevalent notion, although the mechanisms are not yet understood. A way by which neural assemblies compute is proposed in this paper. It is shown how neural coalitions represent things (and world states), memorize them, and control their hierarchical relations in order to perform algorithms. It is described how neural groups perform statistic logic functions as they form assemblies. Neural coalitions can reverberate, becoming bistable loops. Such bistable neural assemblies become short- or long-term memories that represent the event that triggers them. In addition, assemblies can branch and dismantle other neural groups generating new events that trigger other coalitions. Hence, such capabilities and the interaction among assemblies allow neural networks to create and control hierarchical cascades of causal activities, giving rise to parallel algorithms. Computing and algorithms are used here as in a nonstandard computation approach. In this sense, neural assembly computing (NAC) can be seen as a new class of spiking neural network machines. NAC can explain the following points: 1) how neuron groups represent things and states; 2) how they retain binary states in memories that do not require any plasticity mechanism; and 3) how branching, disbanding, and interaction among assemblies may result in algorithms and behavioral responses. Simulations were carried out and the results are in agreement with the hypothesis presented. A MATLAB code is available as a supplementary material.

Computational Evaluation of Cochlear Implant Surgery Outcomes Accounting for Uncertainty and Parameter Variability.

PubMed

Mangado, Nerea; Pons-Prats, Jordi; Coma, Martí; Mistrík, Pavel; Piella, Gemma; Ceresa, Mario; González Ballester, Miguel Á

2018-01-01

Cochlear implantation (CI) is a complex surgical procedure that restores hearing in patients with severe deafness. The successful outcome of the implanted device relies on a group of factors, some of them unpredictable or difficult to control. Uncertainties on the electrode array position and the electrical properties of the bone make it difficult to accurately compute the current propagation delivered by the implant and the resulting neural activation. In this context, we use uncertainty quantification methods to explore how these uncertainties propagate through all the stages of CI computational simulations. To this end, we employ an automatic framework, encompassing from the finite element generation of CI models to the assessment of the neural response induced by the implant stimulation. To estimate the confidence intervals of the simulated neural response, we propose two approaches. First, we encode the variability of the cochlear morphology among the population through a statistical shape model. This allows us to generate a population of virtual patients using Monte Carlo sampling and to assign to each of them a set of parameter values according to a statistical distribution. The framework is implemented and parallelized in a High Throughput Computing environment that enables to maximize the available computing resources. Secondly, we perform a patient-specific study to evaluate the computed neural response to seek the optimal post-implantation stimulus levels. Considering a single cochlear morphology, the uncertainty in tissue electrical resistivity and surgical insertion parameters is propagated using the Probabilistic Collocation method, which reduces the number of samples to evaluate. Results show that bone resistivity has the highest influence on CI outcomes. In conjunction with the variability of the cochlear length, worst outcomes are obtained for small cochleae with high resistivity values. However, the effect of the surgical insertion length on the CI outcomes could not be clearly observed, since its impact may be concealed by the other considered parameters. Whereas the Monte Carlo approach implies a high computational cost, Probabilistic Collocation presents a suitable trade-off between precision and computational time. Results suggest that the proposed framework has a great potential to help in both surgical planning decisions and in the audiological setting process.

Deep convolutional neural networks for estimating porous material parameters with ultrasound tomography

NASA Astrophysics Data System (ADS)

Lähivaara, Timo; Kärkkäinen, Leo; Huttunen, Janne M. J.; Hesthaven, Jan S.

2018-02-01

We study the feasibility of data based machine learning applied to ultrasound tomography to estimate water-saturated porous material parameters. In this work, the data to train the neural networks is simulated by solving wave propagation in coupled poroviscoelastic-viscoelastic-acoustic media. As the forward model, we consider a high-order discontinuous Galerkin method while deep convolutional neural networks are used to solve the parameter estimation problem. In the numerical experiment, we estimate the material porosity and tortuosity while the remaining parameters which are of less interest are successfully marginalized in the neural networks-based inversion. Computational examples confirms the feasibility and accuracy of this approach.

Reduction of the dimension of neural network models in problems of pattern recognition and forecasting

NASA Astrophysics Data System (ADS)

Nasertdinova, A. D.; Bochkarev, V. V.

2017-11-01

Deep neural networks with a large number of parameters are a powerful tool for solving problems of pattern recognition, prediction and classification. Nevertheless, overfitting remains a serious problem in the use of such networks. A method of solving the problem of overfitting is proposed in this article. This method is based on reducing the number of independent parameters of a neural network model using the principal component analysis, and can be implemented using existing libraries of neural computing. The algorithm was tested on the problem of recognition of handwritten symbols from the MNIST database, as well as on the task of predicting time series (rows of the average monthly number of sunspots and series of the Lorentz system were used). It is shown that the application of the principal component analysis enables reducing the number of parameters of the neural network model when the results are good. The average error rate for the recognition of handwritten figures from the MNIST database was 1.12% (which is comparable to the results obtained using the "Deep training" methods), while the number of parameters of the neural network can be reduced to 130 times.

Multi-Connection Pattern Analysis: Decoding the representational content of neural communication.

PubMed

Li, Yuanning; Richardson, Robert Mark; Ghuman, Avniel Singh

2017-11-15

The lack of multivariate methods for decoding the representational content of interregional neural communication has left it difficult to know what information is represented in distributed brain circuit interactions. Here we present Multi-Connection Pattern Analysis (MCPA), which works by learning mappings between the activity patterns of the populations as a factor of the information being processed. These maps are used to predict the activity from one neural population based on the activity from the other population. Successful MCPA-based decoding indicates the involvement of distributed computational processing and provides a framework for probing the representational structure of the interaction. Simulations demonstrate the efficacy of MCPA in realistic circumstances. In addition, we demonstrate that MCPA can be applied to different signal modalities to evaluate a variety of hypothesis associated with information coding in neural communications. We apply MCPA to fMRI and human intracranial electrophysiological data to provide a proof-of-concept of the utility of this method for decoding individual natural images and faces in functional connectivity data. We further use a MCPA-based representational similarity analysis to illustrate how MCPA may be used to test computational models of information transfer among regions of the visual processing stream. Thus, MCPA can be used to assess the information represented in the coupled activity of interacting neural circuits and probe the underlying principles of information transformation between regions. Copyright © 2017 Elsevier Inc. All rights reserved.

Adaptive neural control for a class of nonlinear time-varying delay systems with unknown hysteresis.

PubMed

Liu, Zhi; Lai, Guanyu; Zhang, Yun; Chen, Xin; Chen, Chun Lung Philip

2014-12-01

This paper investigates the fusion of unknown direction hysteresis model with adaptive neural control techniques in face of time-delayed continuous time nonlinear systems without strict-feedback form. Compared with previous works on the hysteresis phenomenon, the direction of the modified Bouc-Wen hysteresis model investigated in the literature is unknown. To reduce the computation burden in adaptation mechanism, an optimized adaptation method is successfully applied to the control design. Based on the Lyapunov-Krasovskii method, two neural-network-based adaptive control algorithms are constructed to guarantee that all the system states and adaptive parameters remain bounded, and the tracking error converges to an adjustable neighborhood of the origin. In final, some numerical examples are provided to validate the effectiveness of the proposed control methods.

Review On Applications Of Neural Network To Computer Vision

NASA Astrophysics Data System (ADS)

Li, Wei; Nasrabadi, Nasser M.

1989-03-01

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

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.

The iso-response method: measuring neuronal stimulus integration with closed-loop experiments

PubMed Central

Gollisch, Tim; Herz, Andreas V. M.

2012-01-01

Throughout the nervous system, neurons integrate high-dimensional input streams and transform them into an output of their own. This integration of incoming signals involves filtering processes and complex non-linear operations. The shapes of these filters and non-linearities determine the computational features of single neurons and their functional roles within larger networks. A detailed characterization of signal integration is thus a central ingredient to understanding information processing in neural circuits. Conventional methods for measuring single-neuron response properties, such as reverse correlation, however, are often limited by the implicit assumption that stimulus integration occurs in a linear fashion. Here, we review a conceptual and experimental alternative that is based on exploring the space of those sensory stimuli that result in the same neural output. As demonstrated by recent results in the auditory and visual system, such iso-response stimuli can be used to identify the non-linearities relevant for stimulus integration, disentangle consecutive neural processing steps, and determine their characteristics with unprecedented precision. Automated closed-loop experiments are crucial for this advance, allowing rapid search strategies for identifying iso-response stimuli during experiments. Prime targets for the method are feed-forward neural signaling chains in sensory systems, but the method has also been successfully applied to feedback systems. Depending on the specific question, “iso-response” may refer to a predefined firing rate, single-spike probability, first-spike latency, or other output measures. Examples from different studies show that substantial progress in understanding neural dynamics and coding can be achieved once rapid online data analysis and stimulus generation, adaptive sampling, and computational modeling are tightly integrated into experiments. PMID:23267315

Calculations of dose distributions using a neural network model

NASA Astrophysics Data System (ADS)

Mathieu, R.; Martin, E.; Gschwind, R.; Makovicka, L.; Contassot-Vivier, S.; Bahi, J.

2005-03-01

The main goal of external beam radiotherapy is the treatment of tumours, while sparing, as much as possible, surrounding healthy tissues. In order to master and optimize the dose distribution within the patient, dosimetric planning has to be carried out. Thus, for determining the most accurate dose distribution during treatment planning, a compromise must be found between the precision and the speed of calculation. Current techniques, using analytic methods, models and databases, are rapid but lack precision. Enhanced precision can be achieved by using calculation codes based, for example, on Monte Carlo methods. However, in spite of all efforts to optimize speed (methods and computer improvements), Monte Carlo based methods remain painfully slow. A newer way to handle all of these problems is to use a new approach in dosimetric calculation by employing neural networks. Neural networks (Wu and Zhu 2000 Phys. Med. Biol. 45 913-22) provide the advantages of those various approaches while avoiding their main inconveniences, i.e., time-consumption calculations. This permits us to obtain quick and accurate results during clinical treatment planning. Currently, results obtained for a single depth-dose calculation using a Monte Carlo based code (such as BEAM (Rogers et al 2003 NRCC Report PIRS-0509(A) rev G)) require hours of computing. By contrast, the practical use of neural networks (Mathieu et al 2003 Proceedings Journées Scientifiques Francophones, SFRP) provides almost instant results and quite low errors (less than 2%) for a two-dimensional dosimetric map.

Calculations of dose distributions using a neural network model.

PubMed

Mathieu, R; Martin, E; Gschwind, R; Makovicka, L; Contassot-Vivier, S; Bahi, J

2005-03-07

The main goal of external beam radiotherapy is the treatment of tumours, while sparing, as much as possible, surrounding healthy tissues. In order to master and optimize the dose distribution within the patient, dosimetric planning has to be carried out. Thus, for determining the most accurate dose distribution during treatment planning, a compromise must be found between the precision and the speed of calculation. Current techniques, using analytic methods, models and databases, are rapid but lack precision. Enhanced precision can be achieved by using calculation codes based, for example, on Monte Carlo methods. However, in spite of all efforts to optimize speed (methods and computer improvements), Monte Carlo based methods remain painfully slow. A newer way to handle all of these problems is to use a new approach in dosimetric calculation by employing neural networks. Neural networks (Wu and Zhu 2000 Phys. Med. Biol. 45 913-22) provide the advantages of those various approaches while avoiding their main inconveniences, i.e., time-consumption calculations. This permits us to obtain quick and accurate results during clinical treatment planning. Currently, results obtained for a single depth-dose calculation using a Monte Carlo based code (such as BEAM (Rogers et al 2003 NRCC Report PIRS-0509(A) rev G)) require hours of computing. By contrast, the practical use of neural networks (Mathieu et al 2003 Proceedings Journees Scientifiques Francophones, SFRP) provides almost instant results and quite low errors (less than 2%) for a two-dimensional dosimetric map.

Construction of multi-agent mobile robots control system in the problem of persecution with using a modified reinforcement learning method based on neural networks

NASA Astrophysics Data System (ADS)

Patkin, M. L.; Rogachev, G. N.

2018-02-01

A method for constructing a multi-agent control system for mobile robots based on training with reinforcement using deep neural networks is considered. Synthesis of the management system is proposed to be carried out with reinforcement training and the modified Actor-Critic method, in which the Actor module is divided into Action Actor and Communication Actor in order to simultaneously manage mobile robots and communicate with partners. Communication is carried out by sending partners at each step a vector of real numbers that are added to the observation vector and affect the behaviour. Functions of Actors and Critic are approximated by deep neural networks. The Critics value function is trained by using the TD-error method and the Actor’s function by using DDPG. The Communication Actor’s neural network is trained through gradients received from partner agents. An environment in which a cooperative multi-agent interaction is present was developed, computer simulation of the application of this method in the control problem of two robots pursuing two goals was carried out.

Asymptotic stability of delay-difference system of hopfield neural networks via matrix inequalities and application.

PubMed

Ratchagit, Kreangkri

2007-10-01

In this paper, we derive a sufficient condition for asymptotic stability of the zero solution of delay-difference system of Hopfield neural networks in terms of certain matrix inequalities by using a discrete version of the Lyapunov second method. The result is applied to obtain new asymptotic stability condition for some class of delay-difference system such as delay-difference system of Hopfield neural networks with multiple delays in terms of certain matrix inequalities. Our results can be well suited for computational purposes.

Deep learning for brain tumor classification

NASA Astrophysics Data System (ADS)

Paul, Justin S.; Plassard, Andrew J.; Landman, Bennett A.; Fabbri, Daniel

2017-03-01

Recent research has shown that deep learning methods have performed well on supervised machine learning, image classification tasks. The purpose of this study is to apply deep learning methods to classify brain images with different tumor types: meningioma, glioma, and pituitary. A dataset was publicly released containing 3,064 T1-weighted contrast enhanced MRI (CE-MRI) brain images from 233 patients with either meningioma, glioma, or pituitary tumors split across axial, coronal, or sagittal planes. This research focuses on the 989 axial images from 191 patients in order to avoid confusing the neural networks with three different planes containing the same diagnosis. Two types of neural networks were used in classification: fully connected and convolutional neural networks. Within these two categories, further tests were computed via the augmentation of the original 512×512 axial images. Training neural networks over the axial data has proven to be accurate in its classifications with an average five-fold cross validation of 91.43% on the best trained neural network. This result demonstrates that a more general method (i.e. deep learning) can outperform specialized methods that require image dilation and ring-forming subregions on tumors.

Artificial Neural Network Metamodels of Stochastic Computer Simulations

DTIC Science & Technology

1994-08-10

SUBTITLE r 5. FUNDING NUMBERS Artificial Neural Network Metamodels of Stochastic I () Computer Simulations 6. AUTHOR(S) AD- A285 951 Robert Allen...8217!298*1C2 ARTIFICIAL NEURAL NETWORK METAMODELS OF STOCHASTIC COMPUTER SIMULATIONS by Robert Allen Kilmer B.S. in Education Mathematics, Indiana...dedicate this document to the memory of my father, William Ralph Kilmer. mi ABSTRACT Signature ARTIFICIAL NEURAL NETWORK METAMODELS OF STOCHASTIC

Neural Dynamics as Sampling: A Model for Stochastic Computation in Recurrent Networks of Spiking Neurons

PubMed Central

Buesing, Lars; Bill, Johannes; Nessler, Bernhard; Maass, Wolfgang

2011-01-01

The organization of computations in networks of spiking neurons in the brain is still largely unknown, in particular in view of the inherently stochastic features of their firing activity and the experimentally observed trial-to-trial variability of neural systems in the brain. In principle there exists a powerful computational framework for stochastic computations, probabilistic inference by sampling, which can explain a large number of macroscopic experimental data in neuroscience and cognitive science. But it has turned out to be surprisingly difficult to create a link between these abstract models for stochastic computations and more detailed models of the dynamics of networks of spiking neurons. Here we create such a link and show that under some conditions the stochastic firing activity of networks of spiking neurons can be interpreted as probabilistic inference via Markov chain Monte Carlo (MCMC) sampling. Since common methods for MCMC sampling in distributed systems, such as Gibbs sampling, are inconsistent with the dynamics of spiking neurons, we introduce a different approach based on non-reversible Markov chains that is able to reflect inherent temporal processes of spiking neuronal activity through a suitable choice of random variables. We propose a neural network model and show by a rigorous theoretical analysis that its neural activity implements MCMC sampling of a given distribution, both for the case of discrete and continuous time. This provides a step towards closing the gap between abstract functional models of cortical computation and more detailed models of networks of spiking neurons. PMID:22096452

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.

Automated Agatston score computation in non-ECG gated CT scans using deep learning

NASA Astrophysics Data System (ADS)

Cano-Espinosa, Carlos; González, Germán.; Washko, George R.; Cazorla, Miguel; San José Estépar, Raúl

2018-03-01

Introduction: The Agatston score is a well-established metric of cardiovascular disease related to clinical outcomes. It is computed from CT scans by a) measuring the volume and intensity of the atherosclerotic plaques and b) aggregating such information in an index. Objective: To generate a convolutional neural network that inputs a non-contrast chest CT scan and outputs the Agatston score associated with it directly, without a prior segmentation of Coronary Artery Calcifications (CAC). Materials and methods: We use a database of 5973 non-contrast non-ECG gated chest CT scans where the Agatston score has been manually computed. The heart of each scan is cropped automatically using an object detector. The database is split in 4973 cases for training and 1000 for testing. We train a 3D deep convolutional neural network to regress the Agatston score directly from the extracted hearts. Results: The proposed method yields a Pearson correlation coefficient of r = 0.93; p <= 0.0001 against manual reference standard in the 1000 test cases. It further stratifies correctly 72.6% of the cases with respect to standard risk groups. This compares to more complex state-of-the-art methods based on prior segmentations of the CACs, which achieve r = 0.94 in ECG-gated pulmonary CT. Conclusions: A convolutional neural network can regress the Agatston score from the image of the heart directly, without a prior segmentation of the CACs. This is a new and simpler paradigm in the Agatston score computation that yields similar results to the state-of-the-art literature.

Multisensory visual servoing by a neural network.

PubMed

Wei, G Q; Hirzinger, G

1999-01-01

Conventional computer vision methods for determining a robot's end-effector motion based on sensory data needs sensor calibration (e.g., camera calibration) and sensor-to-hand calibration (e.g., hand-eye calibration). This involves many computations and even some difficulties, especially when different kinds of sensors are involved. In this correspondence, we present a neural network approach to the motion determination problem without any calibration. Two kinds of sensory data, namely, camera images and laser range data, are used as the input to a multilayer feedforward network to associate the direct transformation from the sensory data to the required motions. This provides a practical sensor fusion method. Using a recursive motion strategy and in terms of a network correction, we relax the requirement for the exactness of the learned transformation. Another important feature of our work is that the goal position can be changed without having to do network retraining. Experimental results show the effectiveness of our method.

On the Computational Power of Spiking Neural P Systems with Self-Organization.

PubMed

Wang, Xun; Song, Tao; Gong, Faming; Zheng, Pan

2016-06-10

Neural-like computing models are versatile computing mechanisms in the field of artificial intelligence. Spiking neural P systems (SN P systems for short) are one of the recently developed spiking neural network models inspired by the way neurons communicate. The communications among neurons are essentially achieved by spikes, i. e. short electrical pulses. In terms of motivation, SN P systems fall into the third generation of neural network models. In this study, a novel variant of SN P systems, namely SN P systems with self-organization, is introduced, and the computational power of the system is investigated and evaluated. It is proved that SN P systems with self-organization are capable of computing and accept the family of sets of Turing computable natural numbers. Moreover, with 87 neurons the system can compute any Turing computable recursive function, thus achieves Turing universality. These results demonstrate promising initiatives to solve an open problem arisen by Gh Păun.

On the Computational Power of Spiking Neural P Systems with Self-Organization

PubMed Central

Wang, Xun; Song, Tao; Gong, Faming; Zheng, Pan

2016-01-01

Neural-like computing models are versatile computing mechanisms in the field of artificial intelligence. Spiking neural P systems (SN P systems for short) are one of the recently developed spiking neural network models inspired by the way neurons communicate. The communications among neurons are essentially achieved by spikes, i. e. short electrical pulses. In terms of motivation, SN P systems fall into the third generation of neural network models. In this study, a novel variant of SN P systems, namely SN P systems with self-organization, is introduced, and the computational power of the system is investigated and evaluated. It is proved that SN P systems with self-organization are capable of computing and accept the family of sets of Turing computable natural numbers. Moreover, with 87 neurons the system can compute any Turing computable recursive function, thus achieves Turing universality. These results demonstrate promising initiatives to solve an open problem arisen by Gh Păun. PMID:27283843

On the Computational Power of Spiking Neural P Systems with Self-Organization

NASA Astrophysics Data System (ADS)

Wang, Xun; Song, Tao; Gong, Faming; Zheng, Pan

2016-06-01

Neural-like computing models are versatile computing mechanisms in the field of artificial intelligence. Spiking neural P systems (SN P systems for short) are one of the recently developed spiking neural network models inspired by the way neurons communicate. The communications among neurons are essentially achieved by spikes, i. e. short electrical pulses. In terms of motivation, SN P systems fall into the third generation of neural network models. In this study, a novel variant of SN P systems, namely SN P systems with self-organization, is introduced, and the computational power of the system is investigated and evaluated. It is proved that SN P systems with self-organization are capable of computing and accept the family of sets of Turing computable natural numbers. Moreover, with 87 neurons the system can compute any Turing computable recursive function, thus achieves Turing universality. These results demonstrate promising initiatives to solve an open problem arisen by Gh Păun.

A reactive, scalable, and transferable model for molecular energies from a neural network approach based on local information

NASA Astrophysics Data System (ADS)

Unke, Oliver T.; Meuwly, Markus

2018-06-01

Despite the ever-increasing computer power, accurate ab initio calculations for large systems (thousands to millions of atoms) remain infeasible. Instead, approximate empirical energy functions are used. Most current approaches are either transferable between different chemical systems, but not particularly accurate, or they are fine-tuned to a specific application. In this work, a data-driven method to construct a potential energy surface based on neural networks is presented. Since the total energy is decomposed into local atomic contributions, the evaluation is easily parallelizable and scales linearly with system size. With prediction errors below 0.5 kcal mol-1 for both unknown molecules and configurations, the method is accurate across chemical and configurational space, which is demonstrated by applying it to datasets from nonreactive and reactive molecular dynamics simulations and a diverse database of equilibrium structures. The possibility to use small molecules as reference data to predict larger structures is also explored. Since the descriptor only uses local information, high-level ab initio methods, which are computationally too expensive for large molecules, become feasible for generating the necessary reference data used to train the neural network.

Mapping the Information Trace in Local Field Potentials by a Computational Method of Two-Dimensional Time-Shifting Synchronization Likelihood Based on Graphic Processing Unit Acceleration.

PubMed

Zhao, Zi-Fang; Li, Xue-Zhu; Wan, You

2017-12-01

The local field potential (LFP) is a signal reflecting the electrical activity of neurons surrounding the electrode tip. Synchronization between LFP signals provides important details about how neural networks are organized. Synchronization between two distant brain regions is hard to detect using linear synchronization algorithms like correlation and coherence. Synchronization likelihood (SL) is a non-linear synchronization-detecting algorithm widely used in studies of neural signals from two distant brain areas. One drawback of non-linear algorithms is the heavy computational burden. In the present study, we proposed a graphic processing unit (GPU)-accelerated implementation of an SL algorithm with optional 2-dimensional time-shifting. We tested the algorithm with both artificial data and raw LFP data. The results showed that this method revealed detailed information from original data with the synchronization values of two temporal axes, delay time and onset time, and thus can be used to reconstruct the temporal structure of a neural network. Our results suggest that this GPU-accelerated method can be extended to other algorithms for processing time-series signals (like EEG and fMRI) using similar recording techniques.

Convolutional neural network for high-accuracy functional near-infrared spectroscopy in a brain-computer interface: three-class classification of rest, right-, and left-hand motor execution.

PubMed

Trakoolwilaiwan, Thanawin; Behboodi, Bahareh; Lee, Jaeseok; Kim, Kyungsoo; Choi, Ji-Woong

2018-01-01

The aim of this work is to develop an effective brain-computer interface (BCI) method based on functional near-infrared spectroscopy (fNIRS). In order to improve the performance of the BCI system in terms of accuracy, the ability to discriminate features from input signals and proper classification are desired. Previous studies have mainly extracted features from the signal manually, but proper features need to be selected carefully. To avoid performance degradation caused by manual feature selection, we applied convolutional neural networks (CNNs) as the automatic feature extractor and classifier for fNIRS-based BCI. In this study, the hemodynamic responses evoked by performing rest, right-, and left-hand motor execution tasks were measured on eight healthy subjects to compare performances. Our CNN-based method provided improvements in classification accuracy over conventional methods employing the most commonly used features of mean, peak, slope, variance, kurtosis, and skewness, classified by support vector machine (SVM) and artificial neural network (ANN). Specifically, up to 6.49% and 3.33% improvement in classification accuracy was achieved by CNN compared with SVM and ANN, respectively.

Sensorless control for permanent magnet synchronous motor using a neural network based adaptive estimator

NASA Astrophysics Data System (ADS)

Kwon, Chung-Jin; Kim, Sung-Joong; Han, Woo-Young; Min, Won-Kyoung

2005-12-01

The rotor position and speed estimation of permanent-magnet synchronous motor(PMSM) was dealt with. By measuring the phase voltages and currents of the PMSM drive, two diagonally recurrent neural network(DRNN) based observers, a neural current observer and a neural velocity observer were developed. DRNN which has self-feedback of the hidden neurons ensures that the outputs of DRNN contain the whole past information of the system even if the inputs of DRNN are only the present states and inputs of the system. Thus the structure of DRNN may be simpler than that of feedforward and fully recurrent neural networks. If the backpropagation method was used for the training of the DRNN the problem of slow convergence arise. In order to reduce this problem, recursive prediction error(RPE) based learning method for the DRNN was presented. The simulation results show that the proposed approach gives a good estimation of rotor speed and position, and RPE based training has requires a shorter computation time compared to backpropagation based training.

Neural networks for data compression and invariant image recognition

NASA Technical Reports Server (NTRS)

Gardner, Sheldon

1989-01-01

An approach to invariant image recognition (I2R), based upon a model of biological vision in the mammalian visual system (MVS), is described. The complete I2R model incorporates several biologically inspired features: exponential mapping of retinal images, Gabor spatial filtering, and a neural network associative memory. In the I2R model, exponentially mapped retinal images are filtered by a hierarchical set of Gabor spatial filters (GSF) which provide compression of the information contained within a pixel-based image. A neural network associative memory (AM) is used to process the GSF coded images. We describe a 1-D shape function method for coding of scale and rotationally invariant shape information. This method reduces image shape information to a periodic waveform suitable for coding as an input vector to a neural network AM. The shape function method is suitable for near term applications on conventional computing architectures equipped with VLSI FFT chips to provide a rapid image search capability.

Neural Computation and the Computational Theory of Cognition

ERIC Educational Resources Information Center

Piccinini, Gualtiero; Bahar, Sonya

2013-01-01

We begin by distinguishing computationalism from a number of other theses that are sometimes conflated with it. We also distinguish between several important kinds of computation: computation in a generic sense, digital computation, and analog computation. Then, we defend a weak version of computationalism--neural processes are computations in the…

Determining electrically evoked compound action potential thresholds: a comparison of computer versus human analysis methods.

PubMed

Glassman, E Katelyn; Hughes, Michelle L

2013-01-01

Current cochlear implants (CIs) have telemetry capabilities for measuring the electrically evoked compound action potential (ECAP). Neural Response Telemetry (Cochlear) and Neural Response Imaging (Advanced Bionics [AB]) can measure ECAP responses across a range of stimulus levels to obtain an amplitude growth function. Software-specific algorithms automatically mark the leading negative peak, N1, and the following positive peak/plateau, P2, and apply linear regression to estimate ECAP threshold. Alternatively, clinicians may apply expert judgments to modify the peak markers placed by the software algorithms, or use visual detection to identify the lowest level yielding a measurable ECAP response. The goals of this study were to: (1) assess the variability between human and computer decisions for (a) marking N1 and P2 and (b) determining linear-regression threshold (LRT) and visual-detection threshold (VDT); and (2) compare LRT and VDT methods within and across human- and computer-decision methods. ECAP amplitude-growth functions were measured for three electrodes in each of 20 ears (10 Cochlear Nucleus® 24RE/CI512, and 10 AB CII/90K). LRT, defined as the current level yielding an ECAP with zero amplitude, was calculated for both computer- (C-LRT) and human-picked peaks (H-LRT). VDT, defined as the lowest level resulting in a measurable ECAP response, was also calculated for both computer- (C-VDT) and human-picked peaks (H-VDT). Because Neural Response Imaging assigns peak markers to all waveforms but does not include waveforms with amplitudes less than 20 μV in its regression calculation, C-VDT for AB subjects was defined as the lowest current level yielding an amplitude of 20 μV or more. Overall, there were significant correlations between human and computer decisions for peak-marker placement, LRT, and VDT for both manufacturers (r = 0.78-1.00, p < 0.001). For Cochlear devices, LRT and VDT correlated equally well for both computer- and human-picked peaks (r = 0.98-0.99, p < 0.001), which likely reflects the well-defined Neural Response Telemetry algorithm and the lower noise floor in the 24RE and CI512 devices. For AB devices, correlations between LRT and VDT for both peak-picker methods were weaker than for Cochlear devices (r = 0.69-0.85, p < 0.001), which likely reflect the higher noise floor of the system. Disagreement between computer and human decisions regarding the presence of an ECAP response occurred for 5 % of traces for Cochlear devices and 2.1 % of traces for AB devices. Results indicate that human and computer peak-picking methods can be used with similar accuracy for both Cochlear and AB devices. Either C-VDT or C-LRT can be used with equal confidence for Cochlear 24RE and CI512 recipients because both methods are strongly correlated with human decisions. However, for AB devices, greater variability exists between different threshold-determination methods. This finding should be considered in the context of using ECAP measures to assist with programming CIs.

System and method for embedding emotion in logic systems

NASA Technical Reports Server (NTRS)

Curtis, Steven A. (Inventor)

2012-01-01

A system, method, and computer readable-media for creating a stable synthetic neural system. The method includes training an intellectual choice-driven synthetic neural system (SNS), training an emotional rule-driven SNS by generating emotions from rules, incorporating the rule-driven SNS into the choice-driven SNS through an evolvable interface, and balancing the emotional SNS and the intellectual SNS to achieve stability in a nontrivial autonomous environment with a Stability Algorithm for Neural Entities (SANE). Generating emotions from rules can include coding the rules into the rule-driven SNS in a self-consistent way. Training the emotional rule-driven SNS can occur during a training stage in parallel with training the choice-driven SNS. The training stage can include a self assessment loop which measures performance characteristics of the rule-driven SNS against core genetic code. The method uses a stability threshold to measure stability of the incorporated rule-driven SNS and choice-driven SNS using SANE.

Optical Interconnection Via Computer-Generated Holograms

NASA Technical Reports Server (NTRS)

Liu, Hua-Kuang; Zhou, Shaomin

1995-01-01

Method of free-space optical interconnection developed for data-processing applications like parallel optical computing, neural-network computing, and switching in optical communication networks. In method, multiple optical connections between multiple sources of light in one array and multiple photodetectors in another array made via computer-generated holograms in electrically addressed spatial light modulators (ESLMs). Offers potential advantages of massive parallelism, high space-bandwidth product, high time-bandwidth product, low power consumption, low cross talk, and low time skew. Also offers advantage of programmability with flexibility of reconfiguration, including variation of strengths of optical connections in real time.

Spatiotemporal Computations of an Excitable and Plastic Brain: Neuronal Plasticity Leads to Noise-Robust and Noise-Constructive Computations

PubMed Central

Toutounji, Hazem; Pipa, Gordon

2014-01-01

It is a long-established fact that neuronal plasticity occupies the central role in generating neural function and computation. Nevertheless, no unifying account exists of how neurons in a recurrent cortical network learn to compute on temporally and spatially extended stimuli. However, these stimuli constitute the norm, rather than the exception, of the brain's input. Here, we introduce a geometric theory of learning spatiotemporal computations through neuronal plasticity. To that end, we rigorously formulate the problem of neural representations as a relation in space between stimulus-induced neural activity and the asymptotic dynamics of excitable cortical networks. Backed up by computer simulations and numerical analysis, we show that two canonical and widely spread forms of neuronal plasticity, that is, spike-timing-dependent synaptic plasticity and intrinsic plasticity, are both necessary for creating neural representations, such that these computations become realizable. Interestingly, the effects of these forms of plasticity on the emerging neural code relate to properties necessary for both combating and utilizing noise. The neural dynamics also exhibits features of the most likely stimulus in the network's spontaneous activity. These properties of the spatiotemporal neural code resulting from plasticity, having their grounding in nature, further consolidate the biological relevance of our findings. PMID:24651447

Computer aided detection of ureteral stones in thin slice computed tomography volumes using Convolutional Neural Networks.

PubMed

Längkvist, Martin; Jendeberg, Johan; Thunberg, Per; Loutfi, Amy; Lidén, Mats

2018-06-01

Computed tomography (CT) is the method of choice for diagnosing ureteral stones - kidney stones that obstruct the ureter. The purpose of this study is to develop a computer aided detection (CAD) algorithm for identifying a ureteral stone in thin slice CT volumes. The challenge in CAD for urinary stones lies in the similarity in shape and intensity of stones with non-stone structures and how to efficiently deal with large high-resolution CT volumes. We address these challenges by using a Convolutional Neural Network (CNN) that works directly on the high resolution CT volumes. The method is evaluated on a large data base of 465 clinically acquired high-resolution CT volumes of the urinary tract with labeling of ureteral stones performed by a radiologist. The best model using 2.5D input data and anatomical information achieved a sensitivity of 100% and an average of 2.68 false-positives per patient on a test set of 88 scans. Copyright © 2018 The Authors. Published by Elsevier Ltd.. All rights reserved.

EDITORIAL: Focus on the neural interface Focus on the neural interface

NASA Astrophysics Data System (ADS)

Durand, Dominique M.

2009-10-01

The possibility of an effective connection between neural tissue and computers has inspired scientists and engineers to develop new ways of controlling and obtaining information from the nervous system. These applications range from `brain hacking' to neural control of artificial limbs with brain signals. Notwithstanding the significant advances in neural prosthetics in the last few decades and the success of some stimulation devices such as cochlear prosthesis, neurotechnology remains below its potential for restoring neural function in patients with nervous system disorders. One of the reasons for this limited impact can be found at the neural interface and close attention to the integration between electrodes and tissue should improve the possibility of successful outcomes. The neural interfaces research community consists of investigators working in areas such as deep brain stimulation, functional neuromuscular/electrical stimulation, auditory prostheses, cortical prostheses, neuromodulation, microelectrode array technology, brain-computer/machine interfaces. Following the success of previous neuroprostheses and neural interfaces workshops, funding (from NIH) was obtained to establish a biennial conference in the area of neural interfaces. The first Neural Interfaces Conference took place in Cleveland, OH in 2008 and several topics from this conference have been selected for publication in this special section of the Journal of Neural Engineering. Three `perspectives' review the areas of neural regeneration (Corredor and Goldberg), cochlear implants (O'Leary et al) and neural prostheses (Anderson). Seven articles focus on various aspects of neural interfacing. One of the most popular of these areas is the field of brain-computer interfaces. Fraser et al, report on a method to generate robust control with simple signal processing algorithms of signals obtained with electrodes implanted in the brain. One problem with implanted electrode arrays, however, is that they can fail to record reliably neural signals for long periods of time. McConnell et al show that by measuring the impedance of the tissue, one can evaluate the extent of the tissue response to the presence of the electrode. Another problem with the neural interface is the mismatch of the mechanical properties between electrode and tissue. Basinger et al use finite element modeling to analyze this mismatch in retinal prostheses and guide the design of new implantable devices. Electrical stimulation has been the method of choice to activate externally the nervous system. However, Zhang et al show that a novel dual hybrid device integrating electrical and optical stimulation can provide an effective interface for simultaneous recording and stimulation. By interfacing an EMG recording system and a movement detection system, Johnson and Fuglevand develop a model capable of predicting muscle activity during movement that could be important for the development of motor prostheses. Sensory restoration is another unsolved problem in neural prostheses. By developing a novel interface between the dorsal root ganglia and electrodes arrays, Gaunt et al show that it is possible to recruit afferent fibers for sensory substitution. Finally, by interfacing directly with muscles, Jung and colleagues show that stimulation of muscles involved in locomotion following spinal cord damage in rats can provide an effective treatment modality for incomplete spinal cord injury. This series of articles clearly shows that the interface is indeed one of the keys to successful therapeutic neural devices. The next Neural Interfaces Conference will take place in Los Angeles, CA in June 2010 and one can expect to see new developments in neural engineering obtained by focusing on the neural interface.

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.

European Science Notes, Volume 41, Number 1.

DTIC Science & Technology

1987-01-01

extract which also *body, HNKI, stains dorsal root ganglion exhibited a trophic effect could be re- (DRG) cells and is selective for neural placed by... effect on central as well as peripheral to migrate just after the neural tube neurons. closes and that these cells migrate Neuronal Development...viscous effects which are ex- tions used pseudounsteady, cell -centered cluded from the computation-. In some finite volume methods. Quite different

A robust cloud registration method based on redundant data reduction using backpropagation neural network and shift window

NASA Astrophysics Data System (ADS)

Xin, Meiting; Li, Bing; Yan, Xiao; Chen, Lei; Wei, Xiang

2018-02-01

A robust coarse-to-fine registration method based on the backpropagation (BP) neural network and shift window technology is proposed in this study. Specifically, there are three steps: coarse alignment between the model data and measured data, data simplification based on the BP neural network and point reservation in the contour region of point clouds, and fine registration with the reweighted iterative closest point algorithm. In the process of rough alignment, the initial rotation matrix and the translation vector between the two datasets are obtained. After performing subsequent simplification operations, the number of points can be reduced greatly. Therefore, the time and space complexity of the accurate registration can be significantly reduced. The experimental results show that the proposed method improves the computational efficiency without loss of accuracy.

Neural Network Machine Learning and Dimension Reduction for Data Visualization

NASA Technical Reports Server (NTRS)

Liles, Charles A.

2014-01-01

Neural network machine learning in computer science is a continuously developing field of study. Although neural network models have been developed which can accurately predict a numeric value or nominal classification, a general purpose method for constructing neural network architecture has yet to be developed. Computer scientists are often forced to rely on a trial-and-error process of developing and improving accurate neural network models. In many cases, models are constructed from a large number of input parameters. Understanding which input parameters have the greatest impact on the prediction of the model is often difficult to surmise, especially when the number of input variables is very high. This challenge is often labeled the "curse of dimensionality" in scientific fields. However, techniques exist for reducing the dimensionality of problems to just two dimensions. Once a problem's dimensions have been mapped to two dimensions, it can be easily plotted and understood by humans. The ability to visualize a multi-dimensional dataset can provide a means of identifying which input variables have the highest effect on determining a nominal or numeric output. Identifying these variables can provide a better means of training neural network models; models can be more easily and quickly trained using only input variables which appear to affect the outcome variable. The purpose of this project is to explore varying means of training neural networks and to utilize dimensional reduction for visualizing and understanding complex datasets.

Constructive autoassociative neural network for facial recognition.

PubMed

Fernandes, Bruno J T; Cavalcanti, George D C; Ren, Tsang I

2014-01-01

Autoassociative artificial neural networks have been used in many different computer vision applications. However, it is difficult to define the most suitable neural network architecture because this definition is based on previous knowledge and depends on the problem domain. To address this problem, we propose a constructive autoassociative neural network called CANet (Constructive Autoassociative Neural Network). CANet integrates the concepts of receptive fields and autoassociative memory in a dynamic architecture that changes the configuration of the receptive fields by adding new neurons in the hidden layer, while a pruning algorithm removes neurons from the output layer. Neurons in the CANet output layer present lateral inhibitory connections that improve the recognition rate. Experiments in face recognition and facial expression recognition show that the CANet outperforms other methods presented in the literature.

A Wireless Sensor Network with Soft Computing Localization Techniques for Track Cycling Applications.

PubMed

Gharghan, Sadik Kamel; Nordin, Rosdiadee; Ismail, Mahamod

2016-08-06

In this paper, we propose two soft computing localization techniques for wireless sensor networks (WSNs). The two techniques, Neural Fuzzy Inference System (ANFIS) and Artificial Neural Network (ANN), focus on a range-based localization method which relies on the measurement of the received signal strength indicator (RSSI) from the three ZigBee anchor nodes distributed throughout the track cycling field. The soft computing techniques aim to estimate the distance between bicycles moving on the cycle track for outdoor and indoor velodromes. In the first approach the ANFIS was considered, whereas in the second approach the ANN was hybridized individually with three optimization algorithms, namely Particle Swarm Optimization (PSO), Gravitational Search Algorithm (GSA), and Backtracking Search Algorithm (BSA). The results revealed that the hybrid GSA-ANN outperforms the other methods adopted in this paper in terms of accuracy localization and distance estimation accuracy. The hybrid GSA-ANN achieves a mean absolute distance estimation error of 0.02 m and 0.2 m for outdoor and indoor velodromes, respectively.

A Wireless Sensor Network with Soft Computing Localization Techniques for Track Cycling Applications

PubMed Central

Gharghan, Sadik Kamel; Nordin, Rosdiadee; Ismail, Mahamod

2016-01-01

In this paper, we propose two soft computing localization techniques for wireless sensor networks (WSNs). The two techniques, Neural Fuzzy Inference System (ANFIS) and Artificial Neural Network (ANN), focus on a range-based localization method which relies on the measurement of the received signal strength indicator (RSSI) from the three ZigBee anchor nodes distributed throughout the track cycling field. The soft computing techniques aim to estimate the distance between bicycles moving on the cycle track for outdoor and indoor velodromes. In the first approach the ANFIS was considered, whereas in the second approach the ANN was hybridized individually with three optimization algorithms, namely Particle Swarm Optimization (PSO), Gravitational Search Algorithm (GSA), and Backtracking Search Algorithm (BSA). The results revealed that the hybrid GSA-ANN outperforms the other methods adopted in this paper in terms of accuracy localization and distance estimation accuracy. The hybrid GSA-ANN achieves a mean absolute distance estimation error of 0.02 m and 0.2 m for outdoor and indoor velodromes, respectively. PMID:27509495

A case for spiking neural network simulation based on configurable multiple-FPGA systems.

PubMed

Yang, Shufan; Wu, Qiang; Li, Renfa

2011-09-01

Recent neuropsychological research has begun to reveal that neurons encode information in the timing of spikes. Spiking neural network simulations are a flexible and powerful method for investigating the behaviour of neuronal systems. Simulation of the spiking neural networks in software is unable to rapidly generate output spikes in large-scale of neural network. An alternative approach, hardware implementation of such system, provides the possibility to generate independent spikes precisely and simultaneously output spike waves in real time, under the premise that spiking neural network can take full advantage of hardware inherent parallelism. We introduce a configurable FPGA-oriented hardware platform for spiking neural network simulation in this work. We aim to use this platform to combine the speed of dedicated hardware with the programmability of software so that it might allow neuroscientists to put together sophisticated computation experiments of their own model. A feed-forward hierarchy network is developed as a case study to describe the operation of biological neural systems (such as orientation selectivity of visual cortex) and computational models of such systems. This model demonstrates how a feed-forward neural network constructs the circuitry required for orientation selectivity and provides platform for reaching a deeper understanding of the primate visual system. In the future, larger scale models based on this framework can be used to replicate the actual architecture in visual cortex, leading to more detailed predictions and insights into visual perception phenomenon.

CPU architecture for a fast and energy-saving calculation of convolution neural networks

NASA Astrophysics Data System (ADS)

Knoll, Florian J.; Grelcke, Michael; Czymmek, Vitali; Holtorf, Tim; Hussmann, Stephan

2017-06-01

One of the most difficult problem in the use of artificial neural networks is the computational capacity. Although large search engine companies own specially developed hardware to provide the necessary computing power, for the conventional user only remains the state of the art method, which is the use of a graphic processing unit (GPU) as a computational basis. Although these processors are well suited for large matrix computations, they need massive energy. Therefore a new processor on the basis of a field programmable gate array (FPGA) has been developed and is optimized for the application of deep learning. This processor is presented in this paper. The processor can be adapted for a particular application (in this paper to an organic farming application). The power consumption is only a fraction of a GPU application and should therefore be well suited for energy-saving applications.

Training-free compressed sensing for wireless neural recording using analysis model and group weighted {{\\ell}_{1}} -minimization

NASA Astrophysics Data System (ADS)

Sun, Biao; Zhao, Wenfeng; Zhu, Xinshan

2017-06-01

Objective. Data compression is crucial for resource-constrained wireless neural recording applications with limited data bandwidth, and compressed sensing (CS) theory has successfully demonstrated its potential in neural recording applications. In this paper, an analytical, training-free CS recovery method, termed group weighted analysis {{\\ell}1} -minimization (GWALM), is proposed for wireless neural recording. Approach. The GWALM method consists of three parts: (1) the analysis model is adopted to enforce sparsity of the neural signals, therefore overcoming the drawbacks of conventional synthesis models and enhancing the recovery performance. (2) A multi-fractional-order difference matrix is constructed as the analysis operator, thus avoiding the dictionary learning procedure and reducing the need for previously acquired data and computational complexities. (3) By exploiting the statistical properties of the analysis coefficients, a group weighting approach is developed to enhance the performance of analysis {{\\ell}1} -minimization. Main results. Experimental results on synthetic and real datasets reveal that the proposed approach outperforms state-of-the-art CS-based methods in terms of both spike recovery quality and classification accuracy. Significance. Energy and area efficiency of the GWALM make it an ideal candidate for resource-constrained, large scale wireless neural recording applications. The training-free feature of the GWALM further improves its robustness to spike shape variation, thus making it more practical for long term wireless neural recording.

Training-free compressed sensing for wireless neural recording using analysis model and group weighted [Formula: see text]-minimization.

PubMed

Sun, Biao; Zhao, Wenfeng; Zhu, Xinshan

2017-06-01

Data compression is crucial for resource-constrained wireless neural recording applications with limited data bandwidth, and compressed sensing (CS) theory has successfully demonstrated its potential in neural recording applications. In this paper, an analytical, training-free CS recovery method, termed group weighted analysis [Formula: see text]-minimization (GWALM), is proposed for wireless neural recording. The GWALM method consists of three parts: (1) the analysis model is adopted to enforce sparsity of the neural signals, therefore overcoming the drawbacks of conventional synthesis models and enhancing the recovery performance. (2) A multi-fractional-order difference matrix is constructed as the analysis operator, thus avoiding the dictionary learning procedure and reducing the need for previously acquired data and computational complexities. (3) By exploiting the statistical properties of the analysis coefficients, a group weighting approach is developed to enhance the performance of analysis [Formula: see text]-minimization. Experimental results on synthetic and real datasets reveal that the proposed approach outperforms state-of-the-art CS-based methods in terms of both spike recovery quality and classification accuracy. Energy and area efficiency of the GWALM make it an ideal candidate for resource-constrained, large scale wireless neural recording applications. The training-free feature of the GWALM further improves its robustness to spike shape variation, thus making it more practical for long term wireless neural recording.

Neural modeling and functional neuroimaging.

PubMed

Horwitz, B; Sporns, O

1994-01-01

Two research areas that so far have had little interaction with one another are functional neuroimaging and computational neuroscience. The application of computational models and techniques to the inherently rich data sets generated by "standard" neurophysiological methods has proven useful for interpreting these data sets and for providing predictions and hypotheses for further experiments. We suggest that both theory- and data-driven computational modeling of neuronal systems can help to interpret data generated by functional neuroimaging methods, especially those used with human subjects. In this article, we point out four sets of questions, addressable by computational neuroscientists whose answere would be of value and interest to those who perform functional neuroimaging. The first set consist of determining the neurobiological substrate of the signals measured by functional neuroimaging. The second set concerns developing systems-level models of functional neuroimaging data. The third set of questions involves integrating functional neuroimaging data across modalities, with a particular emphasis on relating electromagnetic with hemodynamic data. The last set asks how one can relate systems-level models to those at the neuronal and neural ensemble levels. We feel that there are ample reasons to link functional neuroimaging and neural modeling, and that combining the results from the two disciplines will result in furthering our understanding of the central nervous system. © 1994 Wiley-Liss, Inc. This Article is a US Goverment work and, as such, is in the public domain in the United State of America. Copyright © 1994 Wiley-Liss, Inc.

A Feasibility Study of Synthesizing Subsurfaces Modeled with Computational Neural Networks

NASA Technical Reports Server (NTRS)

Wang, John T.; Housner, Jerrold M.; Szewczyk, Z. Peter

1998-01-01

This paper investigates the feasibility of synthesizing substructures modeled with computational neural networks. Substructures are modeled individually with computational neural networks and the response of the assembled structure is predicted by synthesizing the neural networks. A superposition approach is applied to synthesize models for statically determinate substructures while an interface displacement collocation approach is used to synthesize statically indeterminate substructure models. Beam and plate substructures along with components of a complicated Next Generation Space Telescope (NGST) model are used in this feasibility study. In this paper, the limitations and difficulties of synthesizing substructures modeled with neural networks are also discussed.

Neural-Network Simulator

NASA Technical Reports Server (NTRS)

Mitchell, Paul H.

1991-01-01

F77NNS (FORTRAN 77 Neural Network Simulator) computer program simulates popular back-error-propagation neural network. Designed to take advantage of vectorization when used on computers having this capability, also used on any computer equipped with ANSI-77 FORTRAN Compiler. Problems involving matching of patterns or mathematical modeling of systems fit class of problems F77NNS designed to solve. Program has restart capability so neural network solved in stages suitable to user's resources and desires. Enables user to customize patterns of connections between layers of network. Size of neural network F77NNS applied to limited only by amount of random-access memory available to user.

Connectivity inference from neural recording data: Challenges, mathematical bases and research directions.

PubMed

Magrans de Abril, Ildefons; Yoshimoto, Junichiro; Doya, Kenji

2018-06-01

This article presents a review of computational methods for connectivity inference from neural activity data derived from multi-electrode recordings or fluorescence imaging. We first identify biophysical and technical challenges in connectivity inference along the data processing pipeline. We then review connectivity inference methods based on two major mathematical foundations, namely, descriptive model-free approaches and generative model-based approaches. We investigate representative studies in both categories and clarify which challenges have been addressed by which method. We further identify critical open issues and possible research directions. Copyright © 2018 The Author(s). Published by Elsevier Ltd.. All rights reserved.

New Computer Simulations of Macular Neural Functioning

NASA Technical Reports Server (NTRS)

Ross, Muriel D.; Doshay, D.; Linton, S.; Parnas, B.; Montgomery, K.; Chimento, T.

1994-01-01

We use high performance graphics workstations and supercomputers to study the functional significance of the three-dimensional (3-D) organization of gravity sensors. These sensors have a prototypic architecture foreshadowing more complex systems. Scaled-down simulations run on a Silicon Graphics workstation and scaled-up, 3-D versions run on a Cray Y-MP supercomputer. A semi-automated method of reconstruction of neural tissue from serial sections studied in a transmission electron microscope has been developed to eliminate tedious conventional photography. The reconstructions use a mesh as a step in generating a neural surface for visualization. Two meshes are required to model calyx surfaces. The meshes are connected and the resulting prisms represent the cytoplasm and the bounding membranes. A finite volume analysis method is employed to simulate voltage changes along the calyx in response to synapse activation on the calyx or on calyceal processes. The finite volume method insures that charge is conserved at the calyx-process junction. These and other models indicate that efferent processes act as voltage followers, and that the morphology of some afferent processes affects their functioning. In a final application, morphological information is symbolically represented in three dimensions in a computer. The possible functioning of the connectivities is tested using mathematical interpretations of physiological parameters taken from the literature. Symbolic, 3-D simulations are in progress to probe the functional significance of the connectivities. This research is expected to advance computer-based studies of macular functioning and of synaptic plasticity.

Baseline estimation in flame's spectra by using neural networks and robust statistics

NASA Astrophysics Data System (ADS)

Garces, Hugo; Arias, Luis; Rojas, Alejandro

2014-09-01

This work presents a baseline estimation method in flame spectra based on artificial intelligence structure as a neural network, combining robust statistics with multivariate analysis to automatically discriminate measured wavelengths belonging to continuous feature for model adaptation, surpassing restriction of measuring target baseline for training. The main contributions of this paper are: to analyze a flame spectra database computing Jolliffe statistics from Principal Components Analysis detecting wavelengths not correlated with most of the measured data corresponding to baseline; to systematically determine the optimal number of neurons in hidden layers based on Akaike's Final Prediction Error; to estimate baseline in full wavelength range sampling measured spectra; and to train an artificial intelligence structure as a Neural Network which allows to generalize the relation between measured and baseline spectra. The main application of our research is to compute total radiation with baseline information, allowing to diagnose combustion process state for optimization in early stages.

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.

An evolutionary algorithm that constructs recurrent neural networks.

PubMed

Angeline, P J; Saunders, G M; Pollack, J B

1994-01-01

Standard methods for simultaneously inducing the structure and weights of recurrent neural networks limit every task to an assumed class of architectures. Such a simplification is necessary since the interactions between network structure and function are not well understood. Evolutionary computations, which include genetic algorithms and evolutionary programming, are population-based search methods that have shown promise in many similarly complex tasks. This paper argues that genetic algorithms are inappropriate for network acquisition and describes an evolutionary program, called GNARL, that simultaneously acquires both the structure and weights for recurrent networks. GNARL's empirical acquisition method allows for the emergence of complex behaviors and topologies that are potentially excluded by the artificial architectural constraints imposed in standard network induction methods.

Artificial neural systems for interpretation and inversion of seismic data

NASA Astrophysics Data System (ADS)

Calderon-Macias, Carlos

The goal of this work is to investigate the feasibility of using neural network (NN) models for solving geophysical exploration problems. First, a feedforward neural network (FNN) is used to solve inverse problems. The operational characteristics of a FNN are primarily controlled by a set of weights and a nonlinear function that performs a mapping between two sets of data. In a process known as training, the FNN weights are iteratively adjusted to perform the mapping. After training, the computed weights encode important features of the data that enable one pattern to be distinguished from another. Synthetic data computed from an ensemble of earth models and the corresponding models provide the training data. Two training methods are studied: the backpropagation method which is a gradient scheme, and a global optimization method called very fast simulated annealing (VFSA). A trained network is then used to predict models from new data (e.g., data from a new location) in a one-step procedure. The application of this method to the problems of obtaining formation resistivities and layer thicknesses from resistivity sounding data and 1D velocity models from seismic data shows that trained FNNs produce reasonably accurate earth models when observed data are input to the FNNs. In a second application, a FNN is used for automating the NMO correction process of seismic reflection data. The task of the FNN is to map CMP data at control locations along a seismic line into subsurface velocities. The network is trained while the velocity analyses are performed at the control locations. Once trained, the computed weights are used as an operator that acts on the remaining CMP data as a velocity interpolator, resulting in a fast method for NMO correction. The second part of this dissertation describes the application of a Hopfield neural network (HNN) to the problems of deconvolution and multiple attenuation. In these applications, the unknown parameters (reflection coefficients and source wavelet in the first problem and an operator in the second) are mapped as neurons of the HNN. The proposed deconvolution method attempts to reproduce the data with a limited number of events. The multiple attenuation method resembles the predictive deconvolution method. Results of this method are compared with a multiple elimination method based on estimating the source wavelet from the seismic data.

Computed tomography of x-ray images using neural networks

NASA Astrophysics Data System (ADS)

Allred, Lloyd G.; Jones, Martin H.; Sheats, Matthew J.; Davis, Anthony W.

2000-03-01

Traditional CT reconstruction is done using the technique of Filtered Backprojection. While this technique is widely employed in industrial and medical applications, it is not generally understood that FB has a fundamental flaw. Gibbs phenomena states any Fourier reconstruction will produce errors in the vicinity of all discontinuities, and that the error will equal 28 percent of the discontinuity. A number of years back, one of the authors proposed a biological perception model whereby biological neural networks perceive 3D images from stereo vision. The perception model proports an internal hard-wired neural network which emulates the external physical process. A process is repeated whereby erroneous unknown internal values are used to generate an emulated signal with is compared to external sensed data, generating an error signal. Feedback from the error signal is then sued to update the erroneous internal values. The process is repeated until the error signal no longer decrease. It was soon realized that the same method could be used to obtain CT from x-rays without having to do Fourier transforms. Neural networks have the additional potential for handling non-linearities and missing data. The technique has been applied to some coral images, collected at the Los Alamos high-energy x-ray facility. The initial images show considerable promise, in some instances showing more detail than the FB images obtained from the same data. Although routine production using this new method would require a massively parallel computer, the method shows promise, especially where refined detail is required.

Efficient Training of Supervised Spiking Neural Network via Accurate Synaptic-Efficiency Adjustment Method.

PubMed

Xie, Xiurui; Qu, Hong; Yi, Zhang; Kurths, Jurgen

2017-06-01

The spiking neural network (SNN) is the third generation of neural networks and performs remarkably well in cognitive tasks, such as pattern recognition. The temporal neural encode mechanism found in biological hippocampus enables SNN to possess more powerful computation capability than networks with other encoding schemes. However, this temporal encoding approach requires neurons to process information serially on time, which reduces learning efficiency significantly. To keep the powerful computation capability of the temporal encoding mechanism and to overcome its low efficiency in the training of SNNs, a new training algorithm, the accurate synaptic-efficiency adjustment method is proposed in this paper. Inspired by the selective attention mechanism of the primate visual system, our algorithm selects only the target spike time as attention areas, and ignores voltage states of the untarget ones, resulting in a significant reduction of training time. Besides, our algorithm employs a cost function based on the voltage difference between the potential of the output neuron and the firing threshold of the SNN, instead of the traditional precise firing time distance. A normalized spike-timing-dependent-plasticity learning window is applied to assigning this error to different synapses for instructing their training. Comprehensive simulations are conducted to investigate the learning properties of our algorithm, with input neurons emitting both single spike and multiple spikes. Simulation results indicate that our algorithm possesses higher learning performance than the existing other methods and achieves the state-of-the-art efficiency in the training of SNN.

Local-learning-based neuron selection for grasping gesture prediction in motor brain machine interfaces

NASA Astrophysics Data System (ADS)

Xu, Kai; Wang, Yiwen; Wang, Yueming; Wang, Fang; Hao, Yaoyao; Zhang, Shaomin; Zhang, Qiaosheng; Chen, Weidong; Zheng, Xiaoxiang

2013-04-01

Objective. The high-dimensional neural recordings bring computational challenges to movement decoding in motor brain machine interfaces (mBMI), especially for portable applications. However, not all recorded neural activities relate to the execution of a certain movement task. This paper proposes to use a local-learning-based method to perform neuron selection for the gesture prediction in a reaching and grasping task. Approach. Nonlinear neural activities are decomposed into a set of linear ones in a weighted feature space. A margin is defined to measure the distance between inter-class and intra-class neural patterns. The weights, reflecting the importance of neurons, are obtained by minimizing a margin-based exponential error function. To find the most dominant neurons in the task, 1-norm regularization is introduced to the objective function for sparse weights, where near-zero weights indicate irrelevant neurons. Main results. The signals of only 10 neurons out of 70 selected by the proposed method could achieve over 95% of the full recording's decoding accuracy of gesture predictions, no matter which different decoding methods are used (support vector machine and K-nearest neighbor). The temporal activities of the selected neurons show visually distinguishable patterns associated with various hand states. Compared with other algorithms, the proposed method can better eliminate the irrelevant neurons with near-zero weights and provides the important neuron subset with the best decoding performance in statistics. The weights of important neurons converge usually within 10-20 iterations. In addition, we study the temporal and spatial variation of neuron importance along a period of one and a half months in the same task. A high decoding performance can be maintained by updating the neuron subset. Significance. The proposed algorithm effectively ascertains the neuronal importance without assuming any coding model and provides a high performance with different decoding models. It shows better robustness of identifying the important neurons with noisy signals presented. The low demand of computational resources which, reflected by the fast convergence, indicates the feasibility of the method applied in portable BMI systems. The ascertainment of the important neurons helps to inspect neural patterns visually associated with the movement task. The elimination of irrelevant neurons greatly reduces the computational burden of mBMI systems and maintains the performance with better robustness.

Neural Network Prediction of Failure of Damaged Composite Pressure Vessels from Strain Field Data Acquired by a Computer Vision Method

NASA Technical Reports Server (NTRS)

Russell, Samuel S.; Lansing, Matthew D.

1997-01-01

This effort used a new and novel method of acquiring strains called Sub-pixel Digital Video Image Correlation (SDVIC) on impact damaged Kevlar/epoxy filament wound pressure vessels during a proof test. To predict the burst pressure, the hoop strain field distribution around the impact location from three vessels was used to train a neural network. The network was then tested on additional pressure vessels. Several variations on the network were tried. The best results were obtained using a single hidden layer. SDVIC is a fill-field non-contact computer vision technique which provides in-plane deformation and strain data over a load differential. This method was used to determine hoop and axial displacements, hoop and axial linear strains, the in-plane shear strains and rotations in the regions surrounding impact sites in filament wound pressure vessels (FWPV) during proof loading by internal pressurization. The relationship between these deformation measurement values and the remaining life of the pressure vessels, however, requires a complex theoretical model or numerical simulation. Both of these techniques are time consuming and complicated. Previous results using neural network methods had been successful in predicting the burst pressure for graphite/epoxy pressure vessels based upon acoustic emission (AE) measurements in similar tests. The neural network associates the character of the AE amplitude distribution, which depends upon the extent of impact damage, with the burst pressure. Similarly, higher amounts of impact damage are theorized to cause a higher amount of strain concentration in the damage effected zone at a given pressure and result in lower burst pressures. This relationship suggests that a neural network might be able to find an empirical relationship between the SDVIC strain field data and the burst pressure, analogous to the AE method, with greater speed and simplicity than theoretical or finite element modeling. The process of testing SDVIC neural network analysis and some encouraging preliminary results are presented in this paper. Details are given concerning the processing of SDVIC output data such that it may be used as back propagation neural network (BPNN) input data. The software written to perform this processing and the BPNN algorithm are also discussed. It will be shown that, with limited training, test results indicate an average error in burst pressure prediction of approximately six percent,

Improved result on stability analysis of discrete stochastic neural networks with time delay

NASA Astrophysics Data System (ADS)

Wu, Zhengguang; Su, Hongye; Chu, Jian; Zhou, Wuneng

2009-04-01

This Letter investigates the problem of exponential stability for discrete stochastic time-delay neural networks. By defining a novel Lyapunov functional, an improved delay-dependent exponential stability criterion is established in terms of linear matrix inequality (LMI) approach. Meanwhile, the computational complexity of the newly established stability condition is reduced because less variables are involved. Numerical example is given to illustrate the effectiveness and the benefits of the proposed method.

Key considerations in designing a speech brain-computer interface.

PubMed

Bocquelet, Florent; Hueber, Thomas; Girin, Laurent; Chabardès, Stéphan; Yvert, Blaise

2016-11-01

Restoring communication in case of aphasia is a key challenge for neurotechnologies. To this end, brain-computer strategies can be envisioned to allow artificial speech synthesis from the continuous decoding of neural signals underlying speech imagination. Such speech brain-computer interfaces do not exist yet and their design should consider three key choices that need to be made: the choice of appropriate brain regions to record neural activity from, the choice of an appropriate recording technique, and the choice of a neural decoding scheme in association with an appropriate speech synthesis method. These key considerations are discussed here in light of (1) the current understanding of the functional neuroanatomy of cortical areas underlying overt and covert speech production, (2) the available literature making use of a variety of brain recording techniques to better characterize and address the challenge of decoding cortical speech signals, and (3) the different speech synthesis approaches that can be considered depending on the level of speech representation (phonetic, acoustic or articulatory) envisioned to be decoded at the core of a speech BCI paradigm. Copyright © 2017 The Author(s). Published by Elsevier Ltd.. All rights reserved.

A fully parallel in time and space algorithm for simulating the electrical activity of a neural tissue.

PubMed

Bedez, Mathieu; Belhachmi, Zakaria; Haeberlé, Olivier; Greget, Renaud; Moussaoui, Saliha; Bouteiller, Jean-Marie; Bischoff, Serge

2016-01-15

The resolution of a model describing the electrical activity of neural tissue and its propagation within this tissue is highly consuming in term of computing time and requires strong computing power to achieve good results. In this study, we present a method to solve a model describing the electrical propagation in neuronal tissue, using parareal algorithm, coupling with parallelization space using CUDA in graphical processing unit (GPU). We applied the method of resolution to different dimensions of the geometry of our model (1-D, 2-D and 3-D). The GPU results are compared with simulations from a multi-core processor cluster, using message-passing interface (MPI), where the spatial scale was parallelized in order to reach a comparable calculation time than that of the presented method using GPU. A gain of a factor 100 in term of computational time between sequential results and those obtained using the GPU has been obtained, in the case of 3-D geometry. Given the structure of the GPU, this factor increases according to the fineness of the geometry used in the computation. To the best of our knowledge, it is the first time such a method is used, even in the case of neuroscience. Parallelization time coupled with GPU parallelization space allows for drastically reducing computational time with a fine resolution of the model describing the propagation of the electrical signal in a neuronal tissue. Copyright © 2015 Elsevier B.V. All rights reserved.

Evidence for Neural Computations of Temporal Coherence in an Auditory Scene and Their Enhancement during Active Listening.

PubMed

O'Sullivan, James A; Shamma, Shihab A; Lalor, Edmund C

2015-05-06

The human brain has evolved to operate effectively in highly complex acoustic environments, segregating multiple sound sources into perceptually distinct auditory objects. A recent theory seeks to explain this ability by arguing that stream segregation occurs primarily due to the temporal coherence of the neural populations that encode the various features of an individual acoustic source. This theory has received support from both psychoacoustic and functional magnetic resonance imaging (fMRI) studies that use stimuli which model complex acoustic environments. Termed stochastic figure-ground (SFG) stimuli, they are composed of a "figure" and background that overlap in spectrotemporal space, such that the only way to segregate the figure is by computing the coherence of its frequency components over time. Here, we extend these psychoacoustic and fMRI findings by using the greater temporal resolution of electroencephalography to investigate the neural computation of temporal coherence. We present subjects with modified SFG stimuli wherein the temporal coherence of the figure is modulated stochastically over time, which allows us to use linear regression methods to extract a signature of the neural processing of this temporal coherence. We do this under both active and passive listening conditions. Our findings show an early effect of coherence during passive listening, lasting from ∼115 to 185 ms post-stimulus. When subjects are actively listening to the stimuli, these responses are larger and last longer, up to ∼265 ms. These findings provide evidence for early and preattentive neural computations of temporal coherence that are enhanced by active analysis of an auditory scene. Copyright © 2015 the authors 0270-6474/15/357256-08$15.00/0.

MapReduce Based Parallel Neural Networks in Enabling Large Scale Machine Learning

PubMed Central

Yang, Jie; Huang, Yuan; Xu, Lixiong; Li, Siguang; Qi, Man

2015-01-01

Artificial neural networks (ANNs) have been widely used in pattern recognition and classification applications. However, ANNs are notably slow in computation especially when the size of data is large. Nowadays, big data has received a momentum from both industry and academia. To fulfill the potentials of ANNs for big data applications, the computation process must be speeded up. For this purpose, this paper parallelizes neural networks based on MapReduce, which has become a major computing model to facilitate data intensive applications. Three data intensive scenarios are considered in the parallelization process in terms of the volume of classification data, the size of the training data, and the number of neurons in the neural network. The performance of the parallelized neural networks is evaluated in an experimental MapReduce computer cluster from the aspects of accuracy in classification and efficiency in computation. PMID:26681933

MapReduce Based Parallel Neural Networks in Enabling Large Scale Machine Learning.

PubMed

Liu, Yang; Yang, Jie; Huang, Yuan; Xu, Lixiong; Li, Siguang; Qi, Man

2015-01-01

Artificial neural networks (ANNs) have been widely used in pattern recognition and classification applications. However, ANNs are notably slow in computation especially when the size of data is large. Nowadays, big data has received a momentum from both industry and academia. To fulfill the potentials of ANNs for big data applications, the computation process must be speeded up. For this purpose, this paper parallelizes neural networks based on MapReduce, which has become a major computing model to facilitate data intensive applications. Three data intensive scenarios are considered in the parallelization process in terms of the volume of classification data, the size of the training data, and the number of neurons in the neural network. The performance of the parallelized neural networks is evaluated in an experimental MapReduce computer cluster from the aspects of accuracy in classification and efficiency in computation.

Deep learning for computational chemistry

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

Goh, Garrett B.; Hodas, Nathan O.; Vishnu, Abhinav

The rise and fall of artificial neural networks is well documented in the scientific literature of both the fields of computer science and computational chemistry. Yet almost two decades later, we are now seeing a resurgence of interest in deep learning, a machine learning algorithm based on “deep” neural networks. Within the last few years, we have seen the transformative impact of deep learning the computer science domain, notably in speech recognition and computer vision, to the extent that the majority of practitioners in those field are now regularly eschewing prior established models in favor of deep learning models. Inmore » this review, we provide an introductory overview into the theory of deep neural networks and their unique properties as compared to traditional machine learning algorithms used in cheminformatics. By providing an overview of the variety of emerging applications of deep neural networks, we highlight its ubiquity and broad applicability to a wide range of challenges in the field, including QSAR, virtual screening, protein structure modeling, QM calculations, materials synthesis and property prediction. In reviewing the performance of deep neural networks, we observed a consistent outperformance against non neural networks state-of-the-art models across disparate research topics, and deep neural network based models often exceeded the “glass ceiling” expectations of their respective tasks. Coupled with the maturity of GPU-accelerated computing for training deep neural networks and the exponential growth of chemical data on which to train these networks on, we anticipate that deep learning algorithms will be a useful tool and may grow into a pivotal role for various challenges in the computational chemistry field.« less

Inverse simulation system for manual-controlled rendezvous and docking based on artificial neural network

NASA Astrophysics Data System (ADS)

Zhou, Wanmeng; Wang, Hua; Tang, Guojin; Guo, Shuai

2016-09-01

The time-consuming experimental method for handling qualities assessment cannot meet the increasing fast design requirements for the manned space flight. As a tool for the aircraft handling qualities research, the model-predictive-control structured inverse simulation (MPC-IS) has potential applications in the aerospace field to guide the astronauts' operations and evaluate the handling qualities more effectively. Therefore, this paper establishes MPC-IS for the manual-controlled rendezvous and docking (RVD) and proposes a novel artificial neural network inverse simulation system (ANN-IS) to further decrease the computational cost. The novel system was obtained by replacing the inverse model of MPC-IS with the artificial neural network. The optimal neural network was trained by the genetic Levenberg-Marquardt algorithm, and finally determined by the Levenberg-Marquardt algorithm. In order to validate MPC-IS and ANN-IS, the manual-controlled RVD experiments on the simulator were carried out. The comparisons between simulation results and experimental data demonstrated the validity of two systems and the high computational efficiency of ANN-IS.

Deep Learning Methods for Improved Decoding of Linear Codes

NASA Astrophysics Data System (ADS)

Nachmani, Eliya; Marciano, Elad; Lugosch, Loren; Gross, Warren J.; Burshtein, David; Be'ery, Yair

2018-02-01

The problem of low complexity, close to optimal, channel decoding of linear codes with short to moderate block length is considered. It is shown that deep learning methods can be used to improve a standard belief propagation decoder, despite the large example space. Similar improvements are obtained for the min-sum algorithm. It is also shown that tying the parameters of the decoders across iterations, so as to form a recurrent neural network architecture, can be implemented with comparable results. The advantage is that significantly less parameters are required. We also introduce a recurrent neural decoder architecture based on the method of successive relaxation. Improvements over standard belief propagation are also observed on sparser Tanner graph representations of the codes. Furthermore, we demonstrate that the neural belief propagation decoder can be used to improve the performance, or alternatively reduce the computational complexity, of a close to optimal decoder of short BCH codes.

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.

Instrumentation for Scientific Computing in Neural Networks, Information Science, Artificial Intelligence, and Applied Mathematics.

DTIC Science & Technology

1987-10-01

include Security Classification) Instrumentation for scientific computing in neural networks, information science, artificial intelligence, and...instrumentation grant to purchase equipment for support of research in neural networks, information science, artificail intellignece , and applied mathematics...in Neural Networks, Information Science, Artificial Intelligence, and Applied Mathematics Contract AFOSR 86-0282 Principal Investigator: Stephen

Space shuttle main engine fault detection using neural networks

NASA Technical Reports Server (NTRS)

Bishop, Thomas; Greenwood, Dan; Shew, Kenneth; Stevenson, Fareed

1991-01-01

A method for on-line Space Shuttle Main Engine (SSME) anomaly detection and fault typing using a feedback neural network is described. The method involves the computation of features representing time-variance of SSME sensor parameters, using historical test case data. The network is trained, using backpropagation, to recognize a set of fault cases. The network is then able to diagnose new fault cases correctly. An essential element of the training technique is the inclusion of randomly generated data along with the real data, in order to span the entire input space of potential non-nominal data.

Segmentation of retinal blood vessels using artificial neural networks for early detection of diabetic retinopathy

NASA Astrophysics Data System (ADS)

Mann, Kulwinder S.; Kaur, Sukhpreet

2017-06-01

There are various eye diseases in the patients suffering from the diabetes which includes Diabetic Retinopathy, Glaucoma, Hypertension etc. These all are the most common sight threatening eye diseases due to the changes in the blood vessel structure. The proposed method using supervised methods concluded that the segmentation of the retinal blood vessels can be performed accurately using neural networks training. It uses features which include Gray level features; Moment Invariant based features, Gabor filtering, Intensity feature, Vesselness feature for feature vector computation. Then the feature vector is calculated using only the prominent features.

Alcoholism detection in magnetic resonance imaging by Haar wavelet transform and back propagation neural network

NASA Astrophysics Data System (ADS)

Yu, Yali; Wang, Mengxia; Lima, Dimas

2018-04-01

In order to develop a novel alcoholism detection method, we proposed a magnetic resonance imaging (MRI)-based computer vision approach. We first use contrast equalization to increase the contrast of brain slices. Then, we perform Haar wavelet transform and principal component analysis. Finally, we use back propagation neural network (BPNN) as the classification tool. Our method yields a sensitivity of 81.71±4.51%, a specificity of 81.43±4.52%, and an accuracy of 81.57±2.18%. The Haar wavelet gives better performance than db4 wavelet and sym3 wavelet.

FPGA-Based Stochastic Echo State Networks for Time-Series Forecasting.

PubMed

Alomar, Miquel L; Canals, Vincent; Perez-Mora, Nicolas; Martínez-Moll, Víctor; Rosselló, Josep L

2016-01-01

Hardware implementation of artificial neural networks (ANNs) allows exploiting the inherent parallelism of these systems. Nevertheless, they require a large amount of resources in terms of area and power dissipation. Recently, Reservoir Computing (RC) has arisen as a strategic technique to design recurrent neural networks (RNNs) with simple learning capabilities. In this work, we show a new approach to implement RC systems with digital gates. The proposed method is based on the use of probabilistic computing concepts to reduce the hardware required to implement different arithmetic operations. The result is the development of a highly functional system with low hardware resources. The presented methodology is applied to chaotic time-series forecasting.

FPGA-Based Stochastic Echo State Networks for Time-Series Forecasting

PubMed Central

Alomar, Miquel L.; Canals, Vincent; Perez-Mora, Nicolas; Martínez-Moll, Víctor; Rosselló, Josep L.

2016-01-01

Hardware implementation of artificial neural networks (ANNs) allows exploiting the inherent parallelism of these systems. Nevertheless, they require a large amount of resources in terms of area and power dissipation. Recently, Reservoir Computing (RC) has arisen as a strategic technique to design recurrent neural networks (RNNs) with simple learning capabilities. In this work, we show a new approach to implement RC systems with digital gates. The proposed method is based on the use of probabilistic computing concepts to reduce the hardware required to implement different arithmetic operations. The result is the development of a highly functional system with low hardware resources. The presented methodology is applied to chaotic time-series forecasting. PMID:26880876

Collective Properties of Neural Systems and Their Relation to Other Physical Models

DTIC Science & Technology

1988-08-05

been computed explicitly. This has been achieved algorithmically by utilizing methods introduced earlier. It should be emphasized that in addition to...Research Institute for Mathematical Sciences. K’oto Universin. K roto 606. .apan and E. BAROUCH Department of Mathematics and Computer Sciene. Clarkon...Mathematics and Computer Science, Clarkson University, where this work was collaborated. References I. IBabu, S. V. and Barouch E., An exact soIlution for the

Modular representation of layered neural networks.

PubMed

Watanabe, Chihiro; Hiramatsu, Kaoru; Kashino, Kunio

2018-01-01

Layered neural networks have greatly improved the performance of various applications including image processing, speech recognition, natural language processing, and bioinformatics. However, it is still difficult to discover or interpret knowledge from the inference provided by a layered neural network, since its internal representation has many nonlinear and complex parameters embedded in hierarchical layers. Therefore, it becomes important to establish a new methodology by which layered neural networks can be understood. In this paper, we propose a new method for extracting a global and simplified structure from a layered neural network. Based on network analysis, the proposed method detects communities or clusters of units with similar connection patterns. We show its effectiveness by applying it to three use cases. (1) Network decomposition: it can decompose a trained neural network into multiple small independent networks thus dividing the problem and reducing the computation time. (2) Training assessment: the appropriateness of a trained result with a given hyperparameter or randomly chosen initial parameters can be evaluated by using a modularity index. And (3) data analysis: in practical data it reveals the community structure in the input, hidden, and output layers, which serves as a clue for discovering knowledge from a trained neural network. Copyright © 2017 Elsevier Ltd. All rights reserved.

Characterization of physiological networks in sleep apnea patients using artificial neural networks for Granger causality computation

NASA Astrophysics Data System (ADS)

Cárdenas, Jhon; Orjuela-Cañón, Alvaro D.; Cerquera, Alexander; Ravelo, Antonio

2017-11-01

Different studies have used Transfer Entropy (TE) and Granger Causality (GC) computation to quantify interconnection between physiological systems. These methods have disadvantages in parametrization and availability in analytic formulas to evaluate the significance of the results. Other inconvenience is related with the assumptions in the distribution of the models generated from the data. In this document, the authors present a way to measure the causality that connect the Central Nervous System (CNS) and the Cardiac System (CS) in people diagnosed with obstructive sleep apnea syndrome (OSA) before and during treatment with continuous positive air pressure (CPAP). For this purpose, artificial neural networks were used to obtain models for GC computation, based on time series of normalized powers calculated from electrocardiography (EKG) and electroencephalography (EEG) signals recorded in polysomnography (PSG) studies.

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

PubMed

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

2017-01-01

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

Computing moment to moment BOLD activation for real-time neurofeedback

PubMed Central

Hinds, Oliver; Ghosh, Satrajit; Thompson, Todd W.; Yoo, Julie J.; Whitfield-Gabrieli, Susan; Triantafyllou, Christina; Gabrieli, John D.E.

2013-01-01

Estimating moment to moment changes in blood oxygenation level dependent (BOLD) activation levels from functional magnetic resonance imaging (fMRI) data has applications for learned regulation of regional activation, brain state monitoring, and brain-machine interfaces. In each of these contexts, accurate estimation of the BOLD signal in as little time as possible is desired. This is a challenging problem due to the low signal-to-noise ratio of fMRI data. Previous methods for real-time fMRI analysis have either sacrificed the ability to compute moment to moment activation changes by averaging several acquisitions into a single activation estimate or have sacrificed accuracy by failing to account for prominent sources of noise in the fMRI signal. Here we present a new method for computing the amount of activation present in a single fMRI acquisition that separates moment to moment changes in the fMRI signal intensity attributable to neural sources from those due to noise, resulting in a feedback signal more reflective of neural activation. This method computes an incremental general linear model fit to the fMRI timeseries, which is used to calculate the expected signal intensity at each new acquisition. The difference between the measured intensity and the expected intensity is scaled by the variance of the estimator in order to transform this residual difference into a statistic. Both synthetic and real data were used to validate this method and compare it to the only other published real-time fMRI method. PMID:20682350

Real-time identification of indoor pollutant source positions based on neural network locator of contaminant sources and optimized sensor networks.

PubMed

Vukovic, Vladimir; Tabares-Velasco, Paulo Cesar; Srebric, Jelena

2010-09-01

A growing interest in security and occupant exposure to contaminants revealed a need for fast and reliable identification of contaminant sources during incidental situations. To determine potential contaminant source positions in outdoor environments, current state-of-the-art modeling methods use computational fluid dynamic simulations on parallel processors. In indoor environments, current tools match accidental contaminant distributions with cases from precomputed databases of possible concentration distributions. These methods require intensive computations in pre- and postprocessing. On the other hand, neural networks emerged as a tool for rapid concentration forecasting of outdoor environmental contaminants such as nitrogen oxides or sulfur dioxide. All of these modeling methods depend on the type of sensors used for real-time measurements of contaminant concentrations. A review of the existing sensor technologies revealed that no perfect sensor exists, but intensity of work in this area provides promising results in the near future. The main goal of the presented research study was to extend neural network modeling from the outdoor to the indoor identification of source positions, making this technology applicable to building indoor environments. The developed neural network Locator of Contaminant Sources was also used to optimize number and allocation of contaminant concentration sensors for real-time prediction of indoor contaminant source positions. Such prediction should take place within seconds after receiving real-time contaminant concentration sensor data. For the purpose of neural network training, a multizone program provided distributions of contaminant concentrations for known source positions throughout a test building. Trained networks had an output indicating contaminant source positions based on measured concentrations in different building zones. A validation case based on a real building layout and experimental data demonstrated the ability of this method to identify contaminant source positions. Future research intentions are focused on integration with real sensor networks and model improvements for much more complicated contamination scenarios.

Accuracy Maximization Analysis for Sensory-Perceptual Tasks: Computational Improvements, Filter Robustness, and Coding Advantages for Scaled Additive Noise

PubMed Central

Burge, Johannes

2017-01-01

Accuracy Maximization Analysis (AMA) is a recently developed Bayesian ideal observer method for task-specific dimensionality reduction. Given a training set of proximal stimuli (e.g. retinal images), a response noise model, and a cost function, AMA returns the filters (i.e. receptive fields) that extract the most useful stimulus features for estimating a user-specified latent variable from those stimuli. Here, we first contribute two technical advances that significantly reduce AMA’s compute time: we derive gradients of cost functions for which two popular estimators are appropriate, and we implement a stochastic gradient descent (AMA-SGD) routine for filter learning. Next, we show how the method can be used to simultaneously probe the impact on neural encoding of natural stimulus variability, the prior over the latent variable, noise power, and the choice of cost function. Then, we examine the geometry of AMA’s unique combination of properties that distinguish it from better-known statistical methods. Using binocular disparity estimation as a concrete test case, we develop insights that have general implications for understanding neural encoding and decoding in a broad class of fundamental sensory-perceptual tasks connected to the energy model. Specifically, we find that non-orthogonal (partially redundant) filters with scaled additive noise tend to outperform orthogonal filters with constant additive noise; non-orthogonal filters and scaled additive noise can interact to sculpt noise-induced stimulus encoding uncertainty to match task-irrelevant stimulus variability. Thus, we show that some properties of neural response thought to be biophysical nuisances can confer coding advantages to neural systems. Finally, we speculate that, if repurposed for the problem of neural systems identification, AMA may be able to overcome a fundamental limitation of standard subunit model estimation. As natural stimuli become more widely used in the study of psychophysical and neurophysiological performance, we expect that task-specific methods for feature learning like AMA will become increasingly important. PMID:28178266

Statistical mechanics of complex neural systems and high dimensional data

NASA Astrophysics Data System (ADS)

Advani, Madhu; Lahiri, Subhaneil; Ganguli, Surya

2013-03-01

Recent experimental advances in neuroscience have opened new vistas into the immense complexity of neuronal networks. This proliferation of data challenges us on two parallel fronts. First, how can we form adequate theoretical frameworks for understanding how dynamical network processes cooperate across widely disparate spatiotemporal scales to solve important computational problems? Second, how can we extract meaningful models of neuronal systems from high dimensional datasets? To aid in these challenges, we give a pedagogical review of a collection of ideas and theoretical methods arising at the intersection of statistical physics, computer science and neurobiology. We introduce the interrelated replica and cavity methods, which originated in statistical physics as powerful ways to quantitatively analyze large highly heterogeneous systems of many interacting degrees of freedom. We also introduce the closely related notion of message passing in graphical models, which originated in computer science as a distributed algorithm capable of solving large inference and optimization problems involving many coupled variables. We then show how both the statistical physics and computer science perspectives can be applied in a wide diversity of contexts to problems arising in theoretical neuroscience and data analysis. Along the way we discuss spin glasses, learning theory, illusions of structure in noise, random matrices, dimensionality reduction and compressed sensing, all within the unified formalism of the replica method. Moreover, we review recent conceptual connections between message passing in graphical models, and neural computation and learning. Overall, these ideas illustrate how statistical physics and computer science might provide a lens through which we can uncover emergent computational functions buried deep within the dynamical complexities of neuronal networks.

A novel method to acquire 3D data from serial 2D images of a dental cast

NASA Astrophysics Data System (ADS)

Yi, Yaxing; Li, Zhongke; Chen, Qi; Shao, Jun; Li, Xinshe; Liu, Zhiqin

2007-05-01

This paper introduced a newly developed method to acquire three-dimensional data from serial two-dimensional images of a dental cast. The system consists of a computer and a set of data acquiring device. The data acquiring device is used to take serial pictures of the a dental cast; an artificial neural network works to translate two-dimensional pictures to three-dimensional data; then three-dimensional image can reconstruct by the computer. The three-dimensional data acquiring of dental casts is the foundation of computer-aided diagnosis and treatment planning in orthodontics.

Modulation Depth Estimation and Variable Selection in State-Space Models for Neural Interfaces

PubMed Central

Hochberg, Leigh R.; Donoghue, John P.; Brown, Emery N.

2015-01-01

Rapid developments in neural interface technology are making it possible to record increasingly large signal sets of neural activity. Various factors such as asymmetrical information distribution and across-channel redundancy may, however, limit the benefit of high-dimensional signal sets, and the increased computational complexity may not yield corresponding improvement in system performance. High-dimensional system models may also lead to overfitting and lack of generalizability. To address these issues, we present a generalized modulation depth measure using the state-space framework that quantifies the tuning of a neural signal channel to relevant behavioral covariates. For a dynamical system, we develop computationally efficient procedures for estimating modulation depth from multivariate data. We show that this measure can be used to rank neural signals and select an optimal channel subset for inclusion in the neural decoding algorithm. We present a scheme for choosing the optimal subset based on model order selection criteria. We apply this method to neuronal ensemble spike-rate decoding in neural interfaces, using our framework to relate motor cortical activity with intended movement kinematics. With offline analysis of intracortical motor imagery data obtained from individuals with tetraplegia using the BrainGate neural interface, we demonstrate that our variable selection scheme is useful for identifying and ranking the most information-rich neural signals. We demonstrate that our approach offers several orders of magnitude lower complexity but virtually identical decoding performance compared to greedy search and other selection schemes. Our statistical analysis shows that the modulation depth of human motor cortical single-unit signals is well characterized by the generalized Pareto distribution. Our variable selection scheme has wide applicability in problems involving multisensor signal modeling and estimation in biomedical engineering systems. PMID:25265627

A practical comparison of algorithms for the measurement of multiscale entropy in neural time series data.

PubMed

Kuntzelman, Karl; Jack Rhodes, L; Harrington, Lillian N; Miskovic, Vladimir

2018-06-01

There is a broad family of statistical methods for capturing time series regularity, with increasingly widespread adoption by the neuroscientific community. A common feature of these methods is that they permit investigators to quantify the entropy of brain signals - an index of unpredictability/complexity. Despite the proliferation of algorithms for computing entropy from neural time series data there is scant evidence concerning their relative stability and efficiency. Here we evaluated several different algorithmic implementations (sample, fuzzy, dispersion and permutation) of multiscale entropy in terms of their stability across sessions, internal consistency and computational speed, accuracy and precision using a combination of electroencephalogram (EEG) and synthetic 1/ƒ noise signals. Overall, we report fair to excellent internal consistency and longitudinal stability over a one-week period for the majority of entropy estimates, with several caveats. Computational timing estimates suggest distinct advantages for dispersion and permutation entropy over other entropy estimates. Considered alongside the psychometric evidence, we suggest several ways in which researchers can maximize computational resources (without sacrificing reliability), especially when working with high-density M/EEG data or multivoxel BOLD time series signals. Copyright © 2018 Elsevier Inc. All rights reserved.

A convolutional neural network approach to calibrating the rotation axis for X-ray computed tomography.

PubMed

Yang, Xiaogang; De Carlo, Francesco; Phatak, Charudatta; Gürsoy, Dogˇa

2017-03-01

This paper presents an algorithm to calibrate the center-of-rotation for X-ray tomography by using a machine learning approach, the Convolutional Neural Network (CNN). The algorithm shows excellent accuracy from the evaluation of synthetic data with various noise ratios. It is further validated with experimental data of four different shale samples measured at the Advanced Photon Source and at the Swiss Light Source. The results are as good as those determined by visual inspection and show better robustness than conventional methods. CNN has also great potential for reducing or removing other artifacts caused by instrument instability, detector non-linearity, etc. An open-source toolbox, which integrates the CNN methods described in this paper, is freely available through GitHub at tomography/xlearn and can be easily integrated into existing computational pipelines available at various synchrotron facilities. Source code, documentation and information on how to contribute are also provided.

The recognition of potato varieties using of neural image analysis method

NASA Astrophysics Data System (ADS)

Przybył, K.; Górna, K.; Wojcieszak, D.; Czekała, W.; Ludwiczak, A.; Przybylak, A.; Boniecki, P.; Koszela, K.; Zaborowicz, M.; Janczak, D.; Lewicki, A.

2015-07-01

The aim of this paper was to extract the representative features and generate an appropriate neural model for classification of varieties of edible potato. Potatoes of variety the Vineta and the Denar were the empirical object of this thesis. The main concept of the project was to develop and prepare an image database using the computer image analysis software. The choice of appropriate neural model the one which will have the greatest abilities to identify the selected variety. The aim of this project is ultimately to conduct assistance and accelerate work of the expert, who classifies and keeps different varieties of potatoes in heaps.

Neural network feedforward control of a closed-circuit wind tunnel

NASA Astrophysics Data System (ADS)

Sutcliffe, Peter

Accurate control of wind-tunnel test conditions can be dramatically enhanced using feedforward control architectures which allow operating conditions to be maintained at a desired setpoint through the use of mathematical models as the primary source of prediction. However, as the desired accuracy of the feedforward prediction increases, the model complexity also increases, so that an ever increasing computational load is incurred. This drawback can be avoided by employing a neural network that is trained offline using the output of a high fidelity wind-tunnel mathematical model, so that the neural network can rapidly reproduce the predictions of the model with a greatly reduced computational overhead. A novel neural network database generation method, developed through the use of fractional factorial arrays, was employed such that a neural network can accurately predict wind-tunnel parameters across a wide range of operating conditions whilst trained upon a highly efficient database. The subsequent network was incorporated into a Neural Network Model Predictive Control (NNMPC) framework to allow an optimised output schedule capable of providing accurate control of the wind-tunnel operating parameters. Facilitation of an optimised path through the solution space is achieved through the use of a chaos optimisation algorithm such that a more globally optimum solution is likely to be found with less computational expense than the gradient descent method. The parameters associated with the NNMPC such as the control horizon are determined through the use of a Taguchi methodology enabling the minimum number of experiments to be carried out to determine the optimal combination. The resultant NNMPC scheme was employed upon the Hessert Low Speed Wind Tunnel at the University of Notre Dame to control the test-section temperature such that it follows a pre-determined reference trajectory during changes in the test-section velocity. Experimental testing revealed that the derived NNMPC controller provided an excellent level of control over the test-section temperature in adherence to a reference trajectory even when faced with unforeseen disturbances such as rapid changes in the operating environment.

Deep neural network-based bandwidth enhancement of photoacoustic data.

PubMed

Gutta, Sreedevi; Kadimesetty, Venkata Suryanarayana; Kalva, Sandeep Kumar; Pramanik, Manojit; Ganapathy, Sriram; Yalavarthy, Phaneendra K

2017-11-01

Photoacoustic (PA) signals collected at the boundary of tissue are always band-limited. A deep neural network was proposed to enhance the bandwidth (BW) of the detected PA signal, thereby improving the quantitative accuracy of the reconstructed PA images. A least square-based deconvolution method that utilizes the Tikhonov regularization framework was used for comparison with the proposed network. The proposed method was evaluated using both numerical and experimental data. The results indicate that the proposed method was capable of enhancing the BW of the detected PA signal, which inturn improves the contrast recovery and quality of reconstructed PA images without adding any significant computational burden. (2017) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE).

A principled dimension-reduction method for the population density approach to modeling networks of neurons with synaptic dynamics.

PubMed

Ly, Cheng

2013-10-01

The population density approach to neural network modeling has been utilized in a variety of contexts. The idea is to group many similar noisy neurons into populations and track the probability density function for each population that encompasses the proportion of neurons with a particular state rather than simulating individual neurons (i.e., Monte Carlo). It is commonly used for both analytic insight and as a time-saving computational tool. The main shortcoming of this method is that when realistic attributes are incorporated in the underlying neuron model, the dimension of the probability density function increases, leading to intractable equations or, at best, computationally intensive simulations. Thus, developing principled dimension-reduction methods is essential for the robustness of these powerful methods. As a more pragmatic tool, it would be of great value for the larger theoretical neuroscience community. For exposition of this method, we consider a single uncoupled population of leaky integrate-and-fire neurons receiving external excitatory synaptic input only. We present a dimension-reduction method that reduces a two-dimensional partial differential-integral equation to a computationally efficient one-dimensional system and gives qualitatively accurate results in both the steady-state and nonequilibrium regimes. The method, termed modified mean-field method, is based entirely on the governing equations and not on any auxiliary variables or parameters, and it does not require fine-tuning. The principles of the modified mean-field method have potential applicability to more realistic (i.e., higher-dimensional) neural networks.

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

PubMed Central

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

2012-01-01

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

Neural Network Computing and Natural Language Processing.

ERIC Educational Resources Information Center

Borchardt, Frank

1988-01-01

Considers the application of neural network concepts to traditional natural language processing and demonstrates that neural network computing architecture can: (1) learn from actual spoken language; (2) observe rules of pronunciation; and (3) reproduce sounds from the patterns derived by its own processes. (Author/CB)

Neural networks for feedback feedforward nonlinear control systems.

PubMed

Parisini, T; Zoppoli, R

1994-01-01

This paper deals with the problem of designing feedback feedforward control strategies to drive the state of a dynamic system (in general, nonlinear) so as to track any desired trajectory joining the points of given compact sets, while minimizing a certain cost function (in general, nonquadratic). Due to the generality of the problem, conventional methods are difficult to apply. Thus, an approximate solution is sought by constraining control strategies to take on the structure of multilayer feedforward neural networks. After discussing the approximation properties of neural control strategies, a particular neural architecture is presented, which is based on what has been called the "linear-structure preserving principle". The original functional problem is then reduced to a nonlinear programming one, and backpropagation is applied to derive the optimal values of the synaptic weights. Recursive equations to compute the gradient components are presented, which generalize the classical adjoint system equations of N-stage optimal control theory. Simulation results related to nonlinear nonquadratic problems show the effectiveness of the proposed method.

An Algebra-Based Introductory Computational Neuroscience Course with Lab.

PubMed

Fink, Christian G

2017-01-01

A course in computational neuroscience has been developed at Ohio Wesleyan University which requires no previous experience with calculus or computer programming, and which exposes students to theoretical models of neural information processing and techniques for analyzing neural data. The exploration of theoretical models of neural processes is conducted in the classroom portion of the course, while data analysis techniques are covered in lab. Students learn to program in MATLAB and are offered the opportunity to conclude the course with a final project in which they explore a topic of their choice within computational neuroscience. Results from a questionnaire administered at the beginning and end of the course indicate significant gains in student facility with core concepts in computational neuroscience, as well as with analysis techniques applied to neural data.

Collaborative filtering for brain-computer interaction using transfer learning and active class selection.

PubMed

Wu, Dongrui; Lance, Brent J; Parsons, Thomas D

2013-01-01

Brain-computer interaction (BCI) and physiological computing are terms that refer to using processed neural or physiological signals to influence human interaction with computers, environment, and each other. A major challenge in developing these systems arises from the large individual differences typically seen in the neural/physiological responses. As a result, many researchers use individually-trained recognition algorithms to process this data. In order to minimize time, cost, and barriers to use, there is a need to minimize the amount of individual training data required, or equivalently, to increase the recognition accuracy without increasing the number of user-specific training samples. One promising method for achieving this is collaborative filtering, which combines training data from the individual subject with additional training data from other, similar subjects. This paper describes a successful application of a collaborative filtering approach intended for a BCI system. This approach is based on transfer learning (TL), active class selection (ACS), and a mean squared difference user-similarity heuristic. The resulting BCI system uses neural and physiological signals for automatic task difficulty recognition. TL improves the learning performance by combining a small number of user-specific training samples with a large number of auxiliary training samples from other similar subjects. ACS optimally selects the classes to generate user-specific training samples. Experimental results on 18 subjects, using both k nearest neighbors and support vector machine classifiers, demonstrate that the proposed approach can significantly reduce the number of user-specific training data samples. This collaborative filtering approach will also be generalizable to handling individual differences in many other applications that involve human neural or physiological data, such as affective computing.

Collaborative Filtering for Brain-Computer Interaction Using Transfer Learning and Active Class Selection

PubMed Central

Wu, Dongrui; Lance, Brent J.; Parsons, Thomas D.

2013-01-01

Brain-computer interaction (BCI) and physiological computing are terms that refer to using processed neural or physiological signals to influence human interaction with computers, environment, and each other. A major challenge in developing these systems arises from the large individual differences typically seen in the neural/physiological responses. As a result, many researchers use individually-trained recognition algorithms to process this data. In order to minimize time, cost, and barriers to use, there is a need to minimize the amount of individual training data required, or equivalently, to increase the recognition accuracy without increasing the number of user-specific training samples. One promising method for achieving this is collaborative filtering, which combines training data from the individual subject with additional training data from other, similar subjects. This paper describes a successful application of a collaborative filtering approach intended for a BCI system. This approach is based on transfer learning (TL), active class selection (ACS), and a mean squared difference user-similarity heuristic. The resulting BCI system uses neural and physiological signals for automatic task difficulty recognition. TL improves the learning performance by combining a small number of user-specific training samples with a large number of auxiliary training samples from other similar subjects. ACS optimally selects the classes to generate user-specific training samples. Experimental results on 18 subjects, using both nearest neighbors and support vector machine classifiers, demonstrate that the proposed approach can significantly reduce the number of user-specific training data samples. This collaborative filtering approach will also be generalizable to handling individual differences in many other applications that involve human neural or physiological data, such as affective computing. PMID:23437188

Neural attractor network for application in visual field data classification.

PubMed

Fink, Wolfgang

2004-07-07

The purpose was to introduce a novel method for computer-based classification of visual field data derived from perimetric examination, that may act as a 'counsellor', providing an independent 'second opinion' to the diagnosing physician. The classification system consists of a Hopfield-type neural attractor network that obtains its input data from perimetric examination results. An iterative relaxation process determines the states of the neurons dynamically. Therefore, even 'noisy' perimetric output, e.g., early stages of a disease, may eventually be classified correctly according to the predefined idealized visual field defect (scotoma) patterns, stored as attractors of the network, that are found with diseases of the eye, optic nerve and the central nervous system. Preliminary tests of the classification system on real visual field data derived from perimetric examinations have shown a classification success of over 80%. Some of the main advantages of the Hopfield-attractor-network-based approach over feed-forward type neural networks are: (1) network architecture is defined by the classification problem; (2) no training is required to determine the neural coupling strengths; (3) assignment of an auto-diagnosis confidence level is possible by means of an overlap parameter and the Hamming distance. In conclusion, the novel method for computer-based classification of visual field data, presented here, furnishes a valuable first overview and an independent 'second opinion' in judging perimetric examination results, pointing towards a final diagnosis by a physician. It should not be considered a substitute for the diagnosing physician. Thanks to the worldwide accessibility of the Internet, the classification system offers a promising perspective towards modern computer-assisted diagnosis in both medicine and tele-medicine, for example and in particular, with respect to non-ophthalmic clinics or in communities where perimetric expertise is not readily available.

Using soft computing techniques to predict corrected air permeability using Thomeer parameters, air porosity and grain density

NASA Astrophysics Data System (ADS)

Nooruddin, Hasan A.; Anifowose, Fatai; Abdulraheem, Abdulazeez

2014-03-01

Soft computing techniques are recently becoming very popular in the oil industry. A number of computational intelligence-based predictive methods have been widely applied in the industry with high prediction capabilities. Some of the popular methods include feed-forward neural networks, radial basis function network, generalized regression neural network, functional networks, support vector regression and adaptive network fuzzy inference system. A comparative study among most popular soft computing techniques is presented using a large dataset published in literature describing multimodal pore systems in the Arab D formation. The inputs to the models are air porosity, grain density, and Thomeer parameters obtained using mercury injection capillary pressure profiles. Corrected air permeability is the target variable. Applying developed permeability models in recent reservoir characterization workflow ensures consistency between micro and macro scale information represented mainly by Thomeer parameters and absolute permeability. The dataset was divided into two parts with 80% of data used for training and 20% for testing. The target permeability variable was transformed to the logarithmic scale as a pre-processing step and to show better correlations with the input variables. Statistical and graphical analysis of the results including permeability cross-plots and detailed error measures were created. In general, the comparative study showed very close results among the developed models. The feed-forward neural network permeability model showed the lowest average relative error, average absolute relative error, standard deviations of error and root means squares making it the best model for such problems. Adaptive network fuzzy inference system also showed very good results.

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.

Deep learning for computational chemistry.

PubMed

Goh, Garrett B; Hodas, Nathan O; Vishnu, Abhinav

2017-06-15

The rise and fall of artificial neural networks is well documented in the scientific literature of both computer science and computational chemistry. Yet almost two decades later, we are now seeing a resurgence of interest in deep learning, a machine learning algorithm based on multilayer neural networks. Within the last few years, we have seen the transformative impact of deep learning in many domains, particularly in speech recognition and computer vision, to the extent that the majority of expert practitioners in those field are now regularly eschewing prior established models in favor of deep learning models. In this review, we provide an introductory overview into the theory of deep neural networks and their unique properties that distinguish them from traditional machine learning algorithms used in cheminformatics. By providing an overview of the variety of emerging applications of deep neural networks, we highlight its ubiquity and broad applicability to a wide range of challenges in the field, including quantitative structure activity relationship, virtual screening, protein structure prediction, quantum chemistry, materials design, and property prediction. In reviewing the performance of deep neural networks, we observed a consistent outperformance against non-neural networks state-of-the-art models across disparate research topics, and deep neural network-based models often exceeded the "glass ceiling" expectations of their respective tasks. Coupled with the maturity of GPU-accelerated computing for training deep neural networks and the exponential growth of chemical data on which to train these networks on, we anticipate that deep learning algorithms will be a valuable tool for computational chemistry. © 2017 Wiley Periodicals, Inc. © 2017 Wiley Periodicals, Inc.

Efficient Monte Carlo sampling of inverse problems using a neural network-based forward—applied to GPR crosshole traveltime inversion

NASA Astrophysics Data System (ADS)

Hansen, T. M.; Cordua, K. S.

2017-12-01

Probabilistically formulated inverse problems can be solved using Monte Carlo-based sampling methods. In principle, both advanced prior information, based on for example, complex geostatistical models and non-linear forward models can be considered using such methods. However, Monte Carlo methods may be associated with huge computational costs that, in practice, limit their application. This is not least due to the computational requirements related to solving the forward problem, where the physical forward response of some earth model has to be evaluated. Here, it is suggested to replace a numerical complex evaluation of the forward problem, with a trained neural network that can be evaluated very fast. This will introduce a modeling error that is quantified probabilistically such that it can be accounted for during inversion. This allows a very fast and efficient Monte Carlo sampling of the solution to an inverse problem. We demonstrate the methodology for first arrival traveltime inversion of crosshole ground penetrating radar data. An accurate forward model, based on 2-D full-waveform modeling followed by automatic traveltime picking, is replaced by a fast neural network. This provides a sampling algorithm three orders of magnitude faster than using the accurate and computationally expensive forward model, and also considerably faster and more accurate (i.e. with better resolution), than commonly used approximate forward models. The methodology has the potential to dramatically change the complexity of non-linear and non-Gaussian inverse problems that have to be solved using Monte Carlo sampling techniques.

Stereo-vision-based cooperative-vehicle positioning using OCC and neural networks

NASA Astrophysics Data System (ADS)

Ifthekhar, Md. Shareef; Saha, Nirzhar; Jang, Yeong Min

2015-10-01

Vehicle positioning has been subjected to extensive research regarding driving safety measures and assistance as well as autonomous navigation. The most common positioning technique used in automotive positioning is the global positioning system (GPS). However, GPS is not reliably accurate because of signal blockage caused by high-rise buildings. In addition, GPS is error prone when a vehicle is inside a tunnel. Moreover, GPS and other radio-frequency-based approaches cannot provide orientation information or the position of neighboring vehicles. In this study, we propose a cooperative-vehicle positioning (CVP) technique by using the newly developed optical camera communications (OCC). The OCC technique utilizes image sensors and cameras to receive and decode light-modulated information from light-emitting diodes (LEDs). A vehicle equipped with an OCC transceiver can receive positioning and other information such as speed, lane change, driver's condition, etc., through optical wireless links of neighboring vehicles. Thus, the target vehicle position that is too far away to establish an OCC link can be determined by a computer-vision-based technique combined with the cooperation of neighboring vehicles. In addition, we have devised a back-propagation (BP) neural-network learning method for positioning and range estimation for CVP. The proposed neural-network-based technique can estimate target vehicle position from only two image points of target vehicles using stereo vision. For this, we use rear LEDs on target vehicles as image points. We show from simulation results that our neural-network-based method achieves better accuracy than that of the computer-vision method.

Artificial Neural Networks as an Architectural Design Tool-Generating New Detail Forms Based On the Roman Corinthian Order Capital

NASA Astrophysics Data System (ADS)

Radziszewski, Kacper

2017-10-01

The following paper presents the results of the research in the field of the machine learning, investigating the scope of application of the artificial neural networks algorithms as a tool in architectural design. The computational experiment was held using the backward propagation of errors method of training the artificial neural network, which was trained based on the geometry of the details of the Roman Corinthian order capital. During the experiment, as an input training data set, five local geometry parameters combined has given the best results: Theta, Pi, Rho in spherical coordinate system based on the capital volume centroid, followed by Z value of the Cartesian coordinate system and a distance from vertical planes created based on the capital symmetry. Additionally during the experiment, artificial neural network hidden layers optimal count and structure was found, giving results of the error below 0.2% for the mentioned before input parameters. Once successfully trained artificial network, was able to mimic the details composition on any other geometry type given. Despite of calculating the transformed geometry locally and separately for each of the thousands of surface points, system could create visually attractive and diverse, complex patterns. Designed tool, based on the supervised learning method of machine learning, gives possibility of generating new architectural forms- free of the designer’s imagination bounds. Implementing the infinitely broad computational methods of machine learning, or Artificial Intelligence in general, not only could accelerate and simplify the design process, but give an opportunity to explore never seen before, unpredictable forms or everyday architectural practice solutions.

PREDICTION OF THE ACUTE TOXICITY OF ORGANIC COMPOUNDS TO THE FATHEAD MINNOW (PIMEPHALES PROMALAS) USING A GROUP CONTRIBUTION METHOD

EPA Science Inventory

A group contribution method has been developed to correlate the acute toxicity (96 h LC50) to the fathead minnow (Pimephales promelas) for 379 organic chemicals. Multilinear regression and computational neural networks (CNNs) were used for model building. The multilinear linear m...

Holographic imaging and photostimulation of neural activity.

PubMed

Yang, Weijian; Yuste, Rafael

2018-06-01

Optical imaging methods are powerful tools in neuroscience as they can systematically monitor the activity of neuronal populations with high spatiotemporal resolution using calcium or voltage indicators. Moreover, caged compounds and optogenetic actuators enable to optically manipulate neural activity. Among optical methods, computer-generated holography offers an enormous flexibility to sculpt the excitation light in three-dimensions (3D), particularly when combined with two-photon light sources. By projecting holographic light patterns on the sample, the activity of multiple neurons across a 3D brain volume can be simultaneously imaged or optically manipulated with single-cell precision. This flexibility makes two-photon holographic microscopy an ideal all-optical platform to simultaneously read and write activity in neuronal populations in vivo in 3D, a critical ability to dissect the function of neural circuits. Copyright © 2018 Elsevier Ltd. All rights reserved.

Connecting Neural Coding to Number Cognition: A Computational Account

ERIC Educational Resources Information Center

Prather, Richard W.

2012-01-01

The current study presents a series of computational simulations that demonstrate how the neural coding of numerical magnitude may influence number cognition and development. This includes behavioral phenomena cataloged in cognitive literature such as the development of numerical estimation and operational momentum. Though neural research has…

A fast image registration approach of neural activities in light-sheet fluorescence microscopy images

NASA Astrophysics Data System (ADS)

Meng, Hui; Hui, Hui; Hu, Chaoen; Yang, Xin; Tian, Jie

2017-03-01

The ability of fast and single-neuron resolution imaging of neural activities enables light-sheet fluorescence microscopy (LSFM) as a powerful imaging technique in functional neural connection applications. The state-of-art LSFM imaging system can record the neuronal activities of entire brain for small animal, such as zebrafish or C. elegans at single-neuron resolution. However, the stimulated and spontaneous movements in animal brain result in inconsistent neuron positions during recording process. It is time consuming to register the acquired large-scale images with conventional method. In this work, we address the problem of fast registration of neural positions in stacks of LSFM images. This is necessary to register brain structures and activities. To achieve fast registration of neural activities, we present a rigid registration architecture by implementation of Graphics Processing Unit (GPU). In this approach, the image stacks were preprocessed on GPU by mean stretching to reduce the computation effort. The present image was registered to the previous image stack that considered as reference. A fast Fourier transform (FFT) algorithm was used for calculating the shift of the image stack. The calculations for image registration were performed in different threads while the preparation functionality was refactored and called only once by the master thread. We implemented our registration algorithm on NVIDIA Quadro K4200 GPU under Compute Unified Device Architecture (CUDA) programming environment. The experimental results showed that the registration computation can speed-up to 550ms for a full high-resolution brain image. Our approach also has potential to be used for other dynamic image registrations in biomedical applications.

Force Field for Water Based on Neural Network.

PubMed

Wang, Hao; Yang, Weitao

2018-05-18

We developed a novel neural network based force field for water based on training with high level ab initio theory. The force field was built based on electrostatically embedded many-body expansion method truncated at binary interactions. Many-body expansion method is a common strategy to partition the total Hamiltonian of large systems into a hierarchy of few-body terms. Neural networks were trained to represent electrostatically embedded one-body and two-body interactions, which require as input only one and two water molecule calculations at the level of ab initio electronic structure method CCSD/aug-cc-pVDZ embedded in the molecular mechanics water environment, making it efficient as a general force field construction approach. Structural and dynamic properties of liquid water calculated with our force field show good agreement with experimental results. We constructed two sets of neural network based force fields: non-polarizable and polarizable force fields. Simulation results show that the non-polarizable force field using fixed TIP3P charges has already behaved well, since polarization effects and many-body effects are implicitly included due to the electrostatic embedding scheme. Our results demonstrate that the electrostatically embedded many-body expansion combined with neural network provides a promising and systematic way to build the next generation force fields at high accuracy and low computational costs, especially for large systems.

Estimation of effective connectivity via data-driven neural modeling

PubMed Central

Freestone, Dean R.; Karoly, Philippa J.; Nešić, Dragan; Aram, Parham; Cook, Mark J.; Grayden, David B.

2014-01-01

This research introduces a new method for functional brain imaging via a process of model inversion. By estimating parameters of a computational model, we are able to track effective connectivity and mean membrane potential dynamics that cannot be directly measured using electrophysiological measurements alone. The ability to track the hidden aspects of neurophysiology will have a profound impact on the way we understand and treat epilepsy. For example, under the assumption the model captures the key features of the cortical circuits of interest, the framework will provide insights into seizure initiation and termination on a patient-specific basis. It will enable investigation into the effect a particular drug has on specific neural populations and connectivity structures using minimally invasive measurements. The method is based on approximating brain networks using an interconnected neural population model. The neural population model is based on a neural mass model that describes the functional activity of the brain, capturing the mesoscopic biophysics and anatomical structure. The model is made subject-specific by estimating the strength of intra-cortical connections within a region and inter-cortical connections between regions using a novel Kalman filtering method. We demonstrate through simulation how the framework can be used to track the mechanisms involved in seizure initiation and termination. PMID:25506315

Temporal Correlations and Neural Spike Train Entropy

NASA Astrophysics Data System (ADS)

Schultz, Simon R.; Panzeri, Stefano

2001-06-01

Sampling considerations limit the experimental conditions under which information theoretic analyses of neurophysiological data yield reliable results. We develop a procedure for computing the full temporal entropy and information of ensembles of neural spike trains, which performs reliably for limited samples of data. This approach also yields insight to the role of correlations between spikes in temporal coding mechanisms. The method, when applied to recordings from complex cells of the monkey primary visual cortex, results in lower rms error information estimates in comparison to a ``brute force'' approach.

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

PubMed Central

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

2015-01-01

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

Modified neural networks for rapid recovery of tokamak plasma parameters for real time control

NASA Astrophysics Data System (ADS)

Sengupta, A.; Ranjan, P.

2002-07-01

Two modified neural network techniques are used for the identification of the equilibrium plasma parameters of the Superconducting Steady State Tokamak I from external magnetic measurements. This is expected to ultimately assist in a real time plasma control. As different from the conventional network structure where a single network with the optimum number of processing elements calculates the outputs, a multinetwork system connected in parallel does the calculations here in one of the methods. This network is called the double neural network. The accuracy of the recovered parameters is clearly more than the conventional network. The other type of neural network used here is based on the statistical function parametrization combined with a neural network. The principal component transformation removes linear dependences from the measurements and a dimensional reduction process reduces the dimensionality of the input space. This reduced and transformed input set, rather than the entire set, is fed into the neural network input. This is known as the principal component transformation-based neural network. The accuracy of the recovered parameters in the latter type of modified network is found to be a further improvement over the accuracy of the double neural network. This result differs from that obtained in an earlier work where the double neural network showed better performance. The conventional network and the function parametrization methods have also been used for comparison. The conventional network has been used for an optimization of the set of magnetic diagnostics. The effective set of sensors, as assessed by this network, are compared with the principal component based network. Fault tolerance of the neural networks has been tested. The double neural network showed the maximum resistance to faults in the diagnostics, while the principal component based network performed poorly. Finally the processing times of the methods have been compared. The double network and the principal component network involve the minimum computation time, although the conventional network also performs well enough to be used in real time.

Neural networks for link prediction in realistic biomedical graphs: a multi-dimensional evaluation of graph embedding-based approaches.

PubMed

Crichton, Gamal; Guo, Yufan; Pyysalo, Sampo; Korhonen, Anna

2018-05-21

Link prediction in biomedical graphs has several important applications including predicting Drug-Target Interactions (DTI), Protein-Protein Interaction (PPI) prediction and Literature-Based Discovery (LBD). It can be done using a classifier to output the probability of link formation between nodes. Recently several works have used neural networks to create node representations which allow rich inputs to neural classifiers. Preliminary works were done on this and report promising results. However they did not use realistic settings like time-slicing, evaluate performances with comprehensive metrics or explain when or why neural network methods outperform. We investigated how inputs from four node representation algorithms affect performance of a neural link predictor on random- and time-sliced biomedical graphs of real-world sizes (∼ 6 million edges) containing information relevant to DTI, PPI and LBD. We compared the performance of the neural link predictor to those of established baselines and report performance across five metrics. In random- and time-sliced experiments when the neural network methods were able to learn good node representations and there was a negligible amount of disconnected nodes, those approaches outperformed the baselines. In the smallest graph (∼ 15,000 edges) and in larger graphs with approximately 14% disconnected nodes, baselines such as Common Neighbours proved a justifiable choice for link prediction. At low recall levels (∼ 0.3) the approaches were mostly equal, but at higher recall levels across all nodes and average performance at individual nodes, neural network approaches were superior. Analysis showed that neural network methods performed well on links between nodes with no previous common neighbours; potentially the most interesting links. Additionally, while neural network methods benefit from large amounts of data, they require considerable amounts of computational resources to utilise them. Our results indicate that when there is enough data for the neural network methods to use and there are a negligible amount of disconnected nodes, those approaches outperform the baselines. At low recall levels the approaches are mostly equal but at higher recall levels and average performance at individual nodes, neural network approaches are superior. Performance at nodes without common neighbours which indicate more unexpected and perhaps more useful links account for this.

Assessing the effect of quantitative and qualitative predictors on gastric cancer individuals survival using hierarchical artificial neural network models.

PubMed

Amiri, Zohreh; Mohammad, Kazem; Mahmoudi, Mahmood; Parsaeian, Mahbubeh; Zeraati, Hojjat

2013-01-01

There are numerous unanswered questions in the application of artificial neural network models for analysis of survival data. In most studies, independent variables have been studied as qualitative dichotomous variables, and results of using discrete and continuous quantitative, ordinal, or multinomial categorical predictive variables in these models are not well understood in comparison to conventional models. This study was designed and conducted to examine the application of these models in order to determine the survival of gastric cancer patients, in comparison to the Cox proportional hazards model. We studied the postoperative survival of 330 gastric cancer patients who suffered surgery at a surgical unit of the Iran Cancer Institute over a five-year period. Covariates of age, gender, history of substance abuse, cancer site, type of pathology, presence of metastasis, stage, and number of complementary treatments were entered in the models, and survival probabilities were calculated at 6, 12, 18, 24, 36, 48, and 60 months using the Cox proportional hazards and neural network models. We estimated coefficients of the Cox model and the weights in the neural network (with 3, 5, and 7 nodes in the hidden layer) in the training group, and used them to derive predictions in the study group. Predictions with these two methods were compared with those of the Kaplan-Meier product limit estimator as the gold standard. Comparisons were performed with the Friedman and Kruskal-Wallis tests. Survival probabilities at different times were determined using the Cox proportional hazards and a neural network with three nodes in the hidden layer; the ratios of standard errors with these two methods to the Kaplan-Meier method were 1.1593 and 1.0071, respectively, revealed a significant difference between Cox and Kaplan-Meier (P < 0.05) and no significant difference between Cox and the neural network, and the neural network and the standard (Kaplan-Meier), as well as better accuracy for the neural network (with 3 nodes in the hidden layer). Probabilities of survival were calculated using three neural network models with 3, 5, and 7 nodes in the hidden layer, and it has been observed that none of the predictions was significantly different from results with the Kaplan-Meier method and they appeared more comparable towards the last months (fifth year). However, we observed better accuracy using the neural network with 5 nodes in the hidden layer. Using the Cox proportional hazards and a neural network with 3 nodes in the hidden layer, we found enhanced accuracy with the neural network model. Neural networks can provide more accurate predictions for survival probabilities compared to the Cox proportional hazards mode, especially now that advances in computer sciences have eliminated limitations associated with complex computations. It is not recommended in order to adding too many hidden layer nodes because sample size related effects can reduce the accuracy. We recommend increasing the number of nodes to a point that increased accuracy continues (decrease in mean standard error), however increasing nodes should cease when a change in this trend is observed.

Brains--Computers--Machines: Neural Engineering in Science Classrooms

ERIC Educational Resources Information Center

Chudler, Eric H.; Bergsman, Kristen Clapper

2016-01-01

Neural engineering is an emerging field of high relevance to students, teachers, and the general public. This feature presents online resources that educators and scientists can use to introduce students to neural engineering and to integrate core ideas from the life sciences, physical sciences, social sciences, computer science, and engineering…

Implantable brain computer interface: challenges to neurotechnology translation.

PubMed

Konrad, Peter; Shanks, Todd

2010-06-01

This article reviews three concepts related to implantable brain computer interface (BCI) devices being designed for human use: neural signal extraction primarily for motor commands, signal insertion to restore sensation, and technological challenges that remain. A significant body of literature has occurred over the past four decades regarding motor cortex signal extraction for upper extremity movement or computer interface. However, little is discussed regarding postural or ambulation command signaling. Auditory prosthesis research continues to represent the majority of literature on BCI signal insertion. Significant hurdles continue in the technological translation of BCI implants. These include developing a stable neural interface, significantly increasing signal processing capabilities, and methods of data transfer throughout the human body. The past few years, however, have provided extraordinary human examples of BCI implant potential. Despite technological hurdles, proof-of-concept animal and human studies provide significant encouragement that BCI implants may well find their way into mainstream medical practice in the foreseeable future.

Planning chemical syntheses with deep neural networks and symbolic AI

NASA Astrophysics Data System (ADS)

Segler, Marwin H. S.; Preuss, Mike; Waller, Mark P.

2018-03-01

To plan the syntheses of small organic molecules, chemists use retrosynthesis, a problem-solving technique in which target molecules are recursively transformed into increasingly simpler precursors. Computer-aided retrosynthesis would be a valuable tool but at present it is slow and provides results of unsatisfactory quality. Here we use Monte Carlo tree search and symbolic artificial intelligence (AI) to discover retrosynthetic routes. We combined Monte Carlo tree search with an expansion policy network that guides the search, and a filter network to pre-select the most promising retrosynthetic steps. These deep neural networks were trained on essentially all reactions ever published in organic chemistry. Our system solves for almost twice as many molecules, thirty times faster than the traditional computer-aided search method, which is based on extracted rules and hand-designed heuristics. In a double-blind AB test, chemists on average considered our computer-generated routes to be equivalent to reported literature routes.

Computer vision system for egg volume prediction using backpropagation neural network

NASA Astrophysics Data System (ADS)

Siswantoro, J.; Hilman, M. Y.; Widiasri, M.

2017-11-01

Volume is one of considered aspects in egg sorting process. A rapid and accurate volume measurement method is needed to develop an egg sorting system. Computer vision system (CVS) provides a promising solution for volume measurement problem. Artificial neural network (ANN) has been used to predict the volume of egg in several CVSs. However, volume prediction from ANN could have less accuracy due to inappropriate input features or inappropriate ANN structure. This paper proposes a CVS for predicting the volume of egg using ANN. The CVS acquired an image of egg from top view and then processed the image to extract its 1D and 2 D size features. The features were used as input for ANN in predicting the volume of egg. The experiment results show that the proposed CSV can predict the volume of egg with a good accuracy and less computation time.

Machine learning action parameters in lattice quantum chromodynamics

NASA Astrophysics Data System (ADS)

Shanahan, Phiala E.; Trewartha, Daniel; Detmold, William

2018-05-01

Numerical lattice quantum chromodynamics studies of the strong interaction are important in many aspects of particle and nuclear physics. Such studies require significant computing resources to undertake. A number of proposed methods promise improved efficiency of lattice calculations, and access to regions of parameter space that are currently computationally intractable, via multi-scale action-matching approaches that necessitate parametric regression of generated lattice datasets. The applicability of machine learning to this regression task is investigated, with deep neural networks found to provide an efficient solution even in cases where approaches such as principal component analysis fail. The high information content and complex symmetries inherent in lattice QCD datasets require custom neural network layers to be introduced and present opportunities for further development.

Decision theory, reinforcement learning, and the brain.

PubMed

Dayan, Peter; Daw, Nathaniel D

2008-12-01

Decision making is a core competence for animals and humans acting and surviving in environments they only partially comprehend, gaining rewards and punishments for their troubles. Decision-theoretic concepts permeate experiments and computational models in ethology, psychology, and neuroscience. Here, we review a well-known, coherent Bayesian approach to decision making, showing how it unifies issues in Markovian decision problems, signal detection psychophysics, sequential sampling, and optimal exploration and discuss paradigmatic psychological and neural examples of each problem. We discuss computational issues concerning what subjects know about their task and how ambitious they are in seeking optimal solutions; we address algorithmic topics concerning model-based and model-free methods for making choices; and we highlight key aspects of the neural implementation of decision making.

Polar cloud and surface classification using AVHRR imagery - An intercomparison of methods

NASA Technical Reports Server (NTRS)

Welch, R. M.; Sengupta, S. K.; Goroch, A. K.; Rabindra, P.; Rangaraj, N.; Navar, M. S.

1992-01-01

Six Advanced Very High-Resolution Radiometer local area coverage (AVHRR LAC) arctic scenes are classified into ten classes. Three different classifiers are examined: (1) the traditional stepwise discriminant analysis (SDA) method; (2) the feed-forward back-propagation (FFBP) neural network; and (3) the probabilistic neural network (PNN). More than 200 spectral and textural measures are computed. These are reduced to 20 features using sequential forward selection. Theoretical accuracy of the classifiers is determined using the bootstrap approach. Overall accuracy is 85.6 percent, 87.6 percent, and 87.0 percent for the SDA, FFBP, and PNN classifiers, respectively, with standard deviations of approximately 1 percent.

A Decade of Neural Networks: Practical Applications and Prospects

NASA Technical Reports Server (NTRS)

Kemeny, Sabrina E.

1994-01-01

The Jet Propulsion Laboratory Neural Network Workshop, sponsored by NASA and DOD, brings together sponsoring agencies, active researchers, and the user community to formulate a vision for the next decade of neural network research and application prospects. While the speed and computing power of microprocessors continue to grow at an ever-increasing pace, the demand to intelligently and adaptively deal with the complex, fuzzy, and often ill-defined world around us remains to a large extent unaddressed. Powerful, highly parallel computing paradigms such as neural networks promise to have a major impact in addressing these needs. Papers in the workshop proceedings highlight benefits of neural networks in real-world applications compared to conventional computing techniques. Topics include fault diagnosis, pattern recognition, and multiparameter optimization.

Neural computation of arithmetic functions

NASA Technical Reports Server (NTRS)

Siu, Kai-Yeung; Bruck, Jehoshua

1990-01-01

An area of application of neural networks is considered. A neuron is modeled as a linear threshold gate, and the network architecture considered is the layered feedforward network. It is shown how common arithmetic functions such as multiplication and sorting can be efficiently computed in a shallow neural network. Some known results are improved by showing that the product of two n-bit numbers and sorting of n n-bit numbers can be computed by a polynomial-size neural network using only four and five unit delays, respectively. Moreover, the weights of each threshold element in the neural networks require O(log n)-bit (instead of n-bit) accuracy. These results can be extended to more complicated functions such as multiple products, division, rational functions, and approximation of analytic functions.

Massively Parallel Signal Processing using the Graphics Processing Unit for Real-Time Brain-Computer Interface Feature Extraction.

PubMed

Wilson, J Adam; Williams, Justin C

2009-01-01

The clock speeds of modern computer processors have nearly plateaued in the past 5 years. Consequently, neural prosthetic systems that rely on processing large quantities of data in a short period of time face a bottleneck, in that it may not be possible to process all of the data recorded from an electrode array with high channel counts and bandwidth, such as electrocorticographic grids or other implantable systems. Therefore, in this study a method of using the processing capabilities of a graphics card [graphics processing unit (GPU)] was developed for real-time neural signal processing of a brain-computer interface (BCI). The NVIDIA CUDA system was used to offload processing to the GPU, which is capable of running many operations in parallel, potentially greatly increasing the speed of existing algorithms. The BCI system records many channels of data, which are processed and translated into a control signal, such as the movement of a computer cursor. This signal processing chain involves computing a matrix-matrix multiplication (i.e., a spatial filter), followed by calculating the power spectral density on every channel using an auto-regressive method, and finally classifying appropriate features for control. In this study, the first two computationally intensive steps were implemented on the GPU, and the speed was compared to both the current implementation and a central processing unit-based implementation that uses multi-threading. Significant performance gains were obtained with GPU processing: the current implementation processed 1000 channels of 250 ms in 933 ms, while the new GPU method took only 27 ms, an improvement of nearly 35 times.

Raingauge-Based Rainfall Nowcasting with Artificial Neural Network

NASA Astrophysics Data System (ADS)

Liong, Shie-Yui; He, Shan

2010-05-01

Rainfall forecasting and nowcasting are of great importance, for instance, in real-time flood early warning systems. Long term rainfall forecasting demands global climate, land, and sea data, thus, large computing power and storage capacity are required. Rainfall nowcasting's computing requirement, on the other hand, is much less. Rainfall nowcasting may use data captured by radar and/or weather stations. This paper presents the application of Artificial Neural Network (ANN) on rainfall nowcasting using data observed at weather and/or rainfall stations. The study focuses on the North-East monsoon period (December, January and February) in Singapore. Rainfall and weather data from ten stations, between 2000 and 2006, were selected and divided into three groups for training, over-fitting test and validation of the ANN. Several neural network architectures were tried in the study. Two architectures, Backpropagation ANN and Group Method of Data Handling ANN, yielded better rainfall nowcasting, up to two hours, than the other architectures. The obtained rainfall nowcasts were then used by a catchment model to forecast catchment runoff. The results of runoff forecast are encouraging and promising.With ANN's high computational speed, the proposed approach may be deliverable for creating the real-time flood early warning system.

Computational exploration of neuron and neural network models in neurobiology.

PubMed

Prinz, Astrid A

2007-01-01

The electrical activity of individual neurons and neuronal networks is shaped by the complex interplay of a large number of non-linear processes, including the voltage-dependent gating of ion channels and the activation of synaptic receptors. These complex dynamics make it difficult to understand how individual neuron or network parameters-such as the number of ion channels of a given type in a neuron's membrane or the strength of a particular synapse-influence neural system function. Systematic exploration of cellular or network model parameter spaces by computational brute force can overcome this difficulty and generate comprehensive data sets that contain information about neuron or network behavior for many different combinations of parameters. Searching such data sets for parameter combinations that produce functional neuron or network output provides insights into how narrowly different neural system parameters have to be tuned to produce a desired behavior. This chapter describes the construction and analysis of databases of neuron or neuronal network models and describes some of the advantages and downsides of such exploration methods.

Efficient Simulation of Wing Modal Response: Application of 2nd Order Shape Sensitivities and Neural Networks

NASA Technical Reports Server (NTRS)

Kapania, Rakesh K.; Liu, Youhua

2000-01-01

At the preliminary design stage of a wing structure, an efficient simulation, one needing little computation but yielding adequately accurate results for various response quantities, is essential in the search of optimal design in a vast design space. In the present paper, methods of using sensitivities up to 2nd order, and direct application of neural networks are explored. The example problem is how to decide the natural frequencies of a wing given the shape variables of the structure. It is shown that when sensitivities cannot be obtained analytically, the finite difference approach is usually more reliable than a semi-analytical approach provided an appropriate step size is used. The use of second order sensitivities is proved of being able to yield much better results than the case where only the first order sensitivities are used. When neural networks are trained to relate the wing natural frequencies to the shape variables, a negligible computation effort is needed to accurately determine the natural frequencies of a new design.

Automated detection of videotaped neonatal seizures based on motion segmentation methods.

PubMed

Karayiannis, Nicolaos B; Tao, Guozhi; Frost, James D; Wise, Merrill S; Hrachovy, Richard A; Mizrahi, Eli M

2006-07-01

This study was aimed at the development of a seizure detection system by training neural networks using quantitative motion information extracted by motion segmentation methods from short video recordings of infants monitored for seizures. The motion of the infants' body parts was quantified by temporal motion strength signals extracted from video recordings by motion segmentation methods based on optical flow computation. The area of each frame occupied by the infants' moving body parts was segmented by direct thresholding, by clustering of the pixel velocities, and by clustering the motion parameters obtained by fitting an affine model to the pixel velocities. The computational tools and procedures developed for automated seizure detection were tested and evaluated on 240 short video segments selected and labeled by physicians from a set of video recordings of 54 patients exhibiting myoclonic seizures (80 segments), focal clonic seizures (80 segments), and random infant movements (80 segments). The experimental study described in this paper provided the basis for selecting the most effective strategy for training neural networks to detect neonatal seizures as well as the decision scheme used for interpreting the responses of the trained neural networks. Depending on the decision scheme used for interpreting the responses of the trained neural networks, the best neural networks exhibited sensitivity above 90% or specificity above 90%. The best among the motion segmentation methods developed in this study produced quantitative features that constitute a reliable basis for detecting myoclonic and focal clonic neonatal seizures. The performance targets of this phase of the project may be achieved by combining the quantitative features described in this paper with those obtained by analyzing motion trajectory signals produced by motion tracking methods. A video system based upon automated analysis potentially offers a number of advantages. Infants who are at risk for seizures could be monitored continuously using relatively inexpensive and non-invasive video techniques that supplement direct observation by nursery personnel. This would represent a major advance in seizure surveillance and offers the possibility for earlier identification of potential neurological problems and subsequent intervention.

Predicting CYP2C19 Catalytic Parameters for Enantioselective Oxidations Using Artificial Neural Networks and a Chirality Code

PubMed Central

Hartman, Jessica H.; Cothren, Steven D.; Park, Sun-Ha; Yun, Chul-Ho; Darsey, Jerry A.; Miller, Grover P.

2013-01-01

Cytochromes P450 (CYP for isoforms) play a central role in biological processes especially metabolism of chiral molecules; thus, development of computational methods to predict parameters for chiral reactions is important for advancing this field. In this study, we identified the most optimal artificial neural networks using conformation-independent chirality codes to predict CYP2C19 catalytic parameters for enantioselective reactions. Optimization of the neural networks required identifying the most suitable representation of structure among a diverse array of training substrates, normalizing distribution of the corresponding catalytic parameters (kcat, Km, and kcat/Km), and determining the best topology for networks to make predictions. Among different structural descriptors, the use of partial atomic charges according to the CHelpG scheme and inclusion of hydrogens yielded the most optimal artificial neural networks. Their training also required resolution of poorly distributed output catalytic parameters using a Box-Cox transformation. End point leave-one-out cross correlations of the best neural networks revealed that predictions for individual catalytic parameters (kcat and Km) were more consistent with experimental values than those for catalytic efficiency (kcat/Km). Lastly, neural networks predicted correctly enantioselectivity and comparable catalytic parameters measured in this study for previously uncharacterized CYP2C19 substrates, R- and S-propranolol. Taken together, these seminal computational studies for CYP2C19 are the first to predict all catalytic parameters for enantioselective reactions using artificial neural networks and thus provide a foundation for expanding the prediction of cytochrome P450 reactions to chiral drugs, pollutants, and other biologically active compounds. PMID:23673224

Breast tumor malignancy modelling using evolutionary neural logic networks.

PubMed

Tsakonas, Athanasios; Dounias, Georgios; Panagi, Georgia; Panourgias, Evangelia

2006-01-01

The present work proposes a computer assisted methodology for the effective modelling of the diagnostic decision for breast tumor malignancy. The suggested approach is based on innovative hybrid computational intelligence algorithms properly applied in related cytological data contained in past medical records. The experimental data used in this study were gathered in the early 1990s in the University of Wisconsin, based in post diagnostic cytological observations performed by expert medical staff. Data were properly encoded in a computer database and accordingly, various alternative modelling techniques were applied on them, in an attempt to form diagnostic models. Previous methods included standard optimisation techniques, as well as artificial intelligence approaches, in a way that a variety of related publications exists in modern literature on the subject. In this report, a hybrid computational intelligence approach is suggested, which effectively combines modern mathematical logic principles, neural computation and genetic programming in an effective manner. The approach proves promising either in terms of diagnostic accuracy and generalization capabilities, or in terms of comprehensibility and practical importance for the related medical staff.

Using deep learning in image hyper spectral segmentation, classification, and detection

NASA Astrophysics Data System (ADS)

Zhao, Xiuying; Su, Zhenyu

2018-02-01

Recent years have shown that deep learning neural networks are a valuable tool in the field of computer vision. Deep learning method can be used in applications like remote sensing such as Land cover Classification, Detection of Vehicle in Satellite Images, Hyper spectral Image classification. This paper addresses the use of the deep learning artificial neural network in Satellite image segmentation. Image segmentation plays an important role in image processing. The hue of the remote sensing image often has a large hue difference, which will result in the poor display of the images in the VR environment. Image segmentation is a pre processing technique applied to the original images and splits the image into many parts which have different hue to unify the color. Several computational models based on supervised, unsupervised, parametric, probabilistic region based image segmentation techniques have been proposed. Recently, one of the machine learning technique known as, deep learning with convolution neural network has been widely used for development of efficient and automatic image segmentation models. In this paper, we focus on study of deep neural convolution network and its variants for automatic image segmentation rather than traditional image segmentation strategies.

The Population Tracking Model: A Simple, Scalable Statistical Model for Neural Population Data

PubMed Central

O'Donnell, Cian; alves, J. Tiago Gonç; Whiteley, Nick; Portera-Cailliau, Carlos; Sejnowski, Terrence J.

2017-01-01

Our understanding of neural population coding has been limited by a lack of analysis methods to characterize spiking data from large populations. The biggest challenge comes from the fact that the number of possible network activity patterns scales exponentially with the number of neurons recorded (∼2Neurons). Here we introduce a new statistical method for characterizing neural population activity that requires semi-independent fitting of only as many parameters as the square of the number of neurons, requiring drastically smaller data sets and minimal computation time. The model works by matching the population rate (the number of neurons synchronously active) and the probability that each individual neuron fires given the population rate. We found that this model can accurately fit synthetic data from up to 1000 neurons. We also found that the model could rapidly decode visual stimuli from neural population data from macaque primary visual cortex about 65 ms after stimulus onset. Finally, we used the model to estimate the entropy of neural population activity in developing mouse somatosensory cortex and, surprisingly, found that it first increases, and then decreases during development. This statistical model opens new options for interrogating neural population data and can bolster the use of modern large-scale in vivo Ca2+ and voltage imaging tools. PMID:27870612

Using an Extended Kalman Filter Learning Algorithm for Feed-Forward Neural Networks to Describe Tracer Correlations

NASA Technical Reports Server (NTRS)

Lary, David J.; Mussa, Yussuf

2004-01-01

In this study a new extended Kalman filter (EKF) learning algorithm for feed-forward neural networks (FFN) is used. With the EKF approach, the training of the FFN can be seen as state estimation for a non-linear stationary process. The EKF method gives excellent convergence performances provided that there is enough computer core memory and that the machine precision is high. Neural networks are ideally suited to describe the spatial and temporal dependence of tracer-tracer correlations. The neural network performs well even in regions where the correlations are less compact and normally a family of correlation curves would be required. For example, the CH4-N2O correlation can be well described using a neural network trained with the latitude, pressure, time of year, and CH4 volume mixing ratio (v.m.r.). The neural network was able to reproduce the CH4-N2O correlation with a correlation coefficient between simulated and training values of 0.9997. The neural network Fortran code used is available for download.

Analysis of Power Laws, Shape Collapses, and Neural Complexity: New Techniques and MATLAB Support via the NCC Toolbox.

PubMed

Marshall, Najja; Timme, Nicholas M; Bennett, Nicholas; Ripp, Monica; Lautzenhiser, Edward; Beggs, John M

2016-01-01

Neural systems include interactions that occur across many scales. Two divergent methods for characterizing such interactions have drawn on the physical analysis of critical phenomena and the mathematical study of information. Inferring criticality in neural systems has traditionally rested on fitting power laws to the property distributions of "neural avalanches" (contiguous bursts of activity), but the fractal nature of avalanche shapes has recently emerged as another signature of criticality. On the other hand, neural complexity, an information theoretic measure, has been used to capture the interplay between the functional localization of brain regions and their integration for higher cognitive functions. Unfortunately, treatments of all three methods-power-law fitting, avalanche shape collapse, and neural complexity-have suffered from shortcomings. Empirical data often contain biases that introduce deviations from true power law in the tail and head of the distribution, but deviations in the tail have often been unconsidered; avalanche shape collapse has required manual parameter tuning; and the estimation of neural complexity has relied on small data sets or statistical assumptions for the sake of computational efficiency. In this paper we present technical advancements in the analysis of criticality and complexity in neural systems. We use maximum-likelihood estimation to automatically fit power laws with left and right cutoffs, present the first automated shape collapse algorithm, and describe new techniques to account for large numbers of neural variables and small data sets in the calculation of neural complexity. In order to facilitate future research in criticality and complexity, we have made the software utilized in this analysis freely available online in the MATLAB NCC (Neural Complexity and Criticality) Toolbox.

Exploration of computational methods for classification of movement intention during human voluntary movement from single trial EEG.

PubMed

Bai, Ou; Lin, Peter; Vorbach, Sherry; Li, Jiang; Furlani, Steve; Hallett, Mark

2007-12-01

To explore effective combinations of computational methods for the prediction of movement intention preceding the production of self-paced right and left hand movements from single trial scalp electroencephalogram (EEG). Twelve naïve subjects performed self-paced movements consisting of three key strokes with either hand. EEG was recorded from 128 channels. The exploration was performed offline on single trial EEG data. We proposed that a successful computational procedure for classification would consist of spatial filtering, temporal filtering, feature selection, and pattern classification. A systematic investigation was performed with combinations of spatial filtering using principal component analysis (PCA), independent component analysis (ICA), common spatial patterns analysis (CSP), and surface Laplacian derivation (SLD); temporal filtering using power spectral density estimation (PSD) and discrete wavelet transform (DWT); pattern classification using linear Mahalanobis distance classifier (LMD), quadratic Mahalanobis distance classifier (QMD), Bayesian classifier (BSC), multi-layer perceptron neural network (MLP), probabilistic neural network (PNN), and support vector machine (SVM). A robust multivariate feature selection strategy using a genetic algorithm was employed. The combinations of spatial filtering using ICA and SLD, temporal filtering using PSD and DWT, and classification methods using LMD, QMD, BSC and SVM provided higher performance than those of other combinations. Utilizing one of the better combinations of ICA, PSD and SVM, the discrimination accuracy was as high as 75%. Further feature analysis showed that beta band EEG activity of the channels over right sensorimotor cortex was most appropriate for discrimination of right and left hand movement intention. Effective combinations of computational methods provide possible classification of human movement intention from single trial EEG. Such a method could be the basis for a potential brain-computer interface based on human natural movement, which might reduce the requirement of long-term training. Effective combinations of computational methods can classify human movement intention from single trial EEG with reasonable accuracy.

Multiple neural network approaches to clinical expert systems

NASA Astrophysics Data System (ADS)

Stubbs, Derek F.

1990-08-01

We briefly review the concept of computer aided medical diagnosis and more extensively review the the existing literature on neural network applications in the field. Neural networks can function as simple expert systems for diagnosis or prognosis. Using a public database we develop a neural network for the diagnosis of a major presenting symptom while discussing the development process and possible approaches. MEDICAL EXPERTS SYSTEMS COMPUTER AIDED DIAGNOSIS Biomedicine is an incredibly diverse and multidisciplinary field and it is not surprising that neural networks with their many applications are finding more and more applications in the highly non-linear field of biomedicine. I want to concentrate on neural networks as medical expert systems for clinical diagnosis or prognosis. Expert Systems started out as a set of computerized " ifthen" rules. Everything was reduced to boolean logic and the promised land of computer experts was said to be in sight. It never came. Why? First the computer code explodes as the number of " ifs" increases. All the " ifs" have to interact. Second experts are not very good at reducing expertise to language. It turns out that experts recognize patterns and have non-verbal left-brain intuition decision processes. Third learning by example rather than learning by rule is the way natural brains works and making computers work by rule-learning is hideously labor intensive. Neural networks can learn from example. They learn the results

Real-time simulation of large-scale neural architectures for visual features computation based on GPU.

PubMed

Chessa, Manuela; Bianchi, Valentina; Zampetti, Massimo; Sabatini, Silvio P; Solari, Fabio

2012-01-01

The intrinsic parallelism of visual neural architectures based on distributed hierarchical layers is well suited to be implemented on the multi-core architectures of modern graphics cards. The design strategies that allow us to optimally take advantage of such parallelism, in order to efficiently map on GPU the hierarchy of layers and the canonical neural computations, are proposed. Specifically, the advantages of a cortical map-like representation of the data are exploited. Moreover, a GPU implementation of a novel neural architecture for the computation of binocular disparity from stereo image pairs, based on populations of binocular energy neurons, is presented. The implemented neural model achieves good performances in terms of reliability of the disparity estimates and a near real-time execution speed, thus demonstrating the effectiveness of the devised design strategies. The proposed approach is valid in general, since the neural building blocks we implemented are a common basis for the modeling of visual neural functionalities.

An Attractor-Based Complexity Measurement for Boolean Recurrent Neural Networks

PubMed Central

Cabessa, Jérémie; Villa, Alessandro E. P.

2014-01-01

We provide a novel refined attractor-based complexity measurement for Boolean recurrent neural networks that represents an assessment of their computational power in terms of the significance of their attractor dynamics. This complexity measurement is achieved by first proving a computational equivalence between Boolean recurrent neural networks and some specific class of -automata, and then translating the most refined classification of -automata to the Boolean neural network context. As a result, a hierarchical classification of Boolean neural networks based on their attractive dynamics is obtained, thus providing a novel refined attractor-based complexity measurement for Boolean recurrent neural networks. These results provide new theoretical insights to the computational and dynamical capabilities of neural networks according to their attractive potentialities. An application of our findings is illustrated by the analysis of the dynamics of a simplified model of the basal ganglia-thalamocortical network simulated by a Boolean recurrent neural network. This example shows the significance of measuring network complexity, and how our results bear new founding elements for the understanding of the complexity of real brain circuits. PMID:24727866

Combining neural networks and signed particles to simulate quantum systems more efficiently

NASA Astrophysics Data System (ADS)

Sellier, Jean Michel

2018-04-01

Recently a new formulation of quantum mechanics has been suggested which describes systems by means of ensembles of classical particles provided with a sign. This novel approach mainly consists of two steps: the computation of the Wigner kernel, a multi-dimensional function describing the effects of the potential over the system, and the field-less evolution of the particles which eventually create new signed particles in the process. Although this method has proved to be extremely advantageous in terms of computational resources - as a matter of fact it is able to simulate in a time-dependent fashion many-body systems on relatively small machines - the Wigner kernel can represent the bottleneck of simulations of certain systems. Moreover, storing the kernel can be another issue as the amount of memory needed is cursed by the dimensionality of the system. In this work, we introduce a new technique which drastically reduces the computation time and memory requirement to simulate time-dependent quantum systems which is based on the use of an appropriately tailored neural network combined with the signed particle formalism. In particular, the suggested neural network is able to compute efficiently and reliably the Wigner kernel without any training as its entire set of weights and biases is specified by analytical formulas. As a consequence, the amount of memory for quantum simulations radically drops since the kernel does not need to be stored anymore as it is now computed by the neural network itself, only on the cells of the (discretized) phase-space which are occupied by particles. As its is clearly shown in the final part of this paper, not only this novel approach drastically reduces the computational time, it also remains accurate. The author believes this work opens the way towards effective design of quantum devices, with incredible practical implications.

Nonlinear dynamics based digital logic and circuits.

PubMed

Kia, Behnam; Lindner, John F; Ditto, William L

2015-01-01

We discuss the role and importance of dynamics in the brain and biological neural networks and argue that dynamics is one of the main missing elements in conventional Boolean logic and circuits. We summarize a simple dynamics based computing method, and categorize different techniques that we have introduced to realize logic, functionality, and programmability. We discuss the role and importance of coupled dynamics in networks of biological excitable cells, and then review our simple coupled dynamics based method for computing. In this paper, for the first time, we show how dynamics can be used and programmed to implement computation in any given base, including but not limited to base two.

Taming Many-Parameter BSM Models with Bayesian Neural Networks

NASA Astrophysics Data System (ADS)

Kuchera, M. P.; Karbo, A.; Prosper, H. B.; Sanchez, A.; Taylor, J. Z.

2017-09-01

The search for physics Beyond the Standard Model (BSM) is a major focus of large-scale high energy physics experiments. One method is to look for specific deviations from the Standard Model that are predicted by BSM models. In cases where the model has a large number of free parameters, standard search methods become intractable due to computation time. This talk presents results using Bayesian Neural Networks, a supervised machine learning method, to enable the study of higher-dimensional models. The popular phenomenological Minimal Supersymmetric Standard Model was studied as an example of the feasibility and usefulness of this method. Graphics Processing Units (GPUs) are used to expedite the calculations. Cross-section predictions for 13 TeV proton collisions will be presented. My participation in the Conference Experience for Undergraduates (CEU) in 2004-2006 exposed me to the national and global significance of cutting-edge research. At the 2005 CEU, I presented work from the previous summer's SULI internship at Lawrence Berkeley Laboratory, where I learned to program while working on the Majorana Project. That work inspired me to follow a similar research path, which led me to my current work on computational methods applied to BSM physics.

A Drone Remote Sensing for Virtual Reality Simulation System for Forest Fires: Semantic Neural Network Approach

NASA Astrophysics Data System (ADS)

Narasimha Rao, Gudikandhula; Jagadeeswara Rao, Peddada; Duvvuru, Rajesh

2016-09-01

Wild fires have significant impact on atmosphere and lives. The demand of predicting exact fire area in forest may help fire management team by using drone as a robot. These are flexible, inexpensive and elevated-motion remote sensing systems that use drones as platforms are important for substantial data gaps and supplementing the capabilities of manned aircraft and satellite remote sensing systems. In addition, powerful computational tools are essential for predicting certain burned area in the duration of a forest fire. The reason of this study is to built up a smart system based on semantic neural networking for the forecast of burned areas. The usage of virtual reality simulator is used to support the instruction process of fire fighters and all users for saving of surrounded wild lives by using a naive method Semantic Neural Network System (SNNS). Semantics are valuable initially to have a enhanced representation of the burned area prediction and better alteration of simulation situation to the users. In meticulous, consequences obtained with geometric semantic neural networking is extensively superior to other methods. This learning suggests that deeper investigation of neural networking in the field of forest fires prediction could be productive.

Application of an artificial neural network and morphing techniques in the redesign of dysplastic trochlea.

PubMed

Cho, Kyung Jin; Müller, Jacobus H; Erasmus, Pieter J; DeJour, David; Scheffer, Cornie

2014-01-01

Segmentation and computer assisted design tools have the potential to test the validity of simulated surgical procedures, e.g., trochleoplasty. A repeatable measurement method for three dimensional femur models that enables quantification of knee parameters of the distal femur is presented. Fifteen healthy knees are analysed using the method to provide a training set for an artificial neural network. The aim is to use this artificial neural network for the prediction of parameter values that describe the shape of a normal trochlear groove geometry. This is achieved by feeding the artificial neural network with the unaffected parameters of a dysplastic knee. Four dysplastic knees (Type A through D) are virtually redesigned by way of morphing the groove geometries based on the suggested shape from the artificial neural network. Each of the four resulting shapes is analysed and compared to its initial dysplastic shape in terms of three anteroposterior dimensions: lateral, central and medial. For the four knees the trochlear depth is increased, the ventral trochlear prominence reduced and the sulcus angle corrected to within published normal ranges. The results show a lateral facet elevation inadequate, with a sulcus deepening or a depression trochleoplasty more beneficial to correct trochlear dysplasia.

A solution for two-dimensional mazes with use of chaotic dynamics in a recurrent neural network model.

PubMed

Suemitsu, Yoshikazu; Nara, Shigetoshi

2004-09-01

Chaotic dynamics introduced into a neural network model is applied to solving two-dimensional mazes, which are ill-posed problems. A moving object moves from the position at t to t + 1 by simply defined motion function calculated from firing patterns of the neural network model at each time step t. We have embedded several prototype attractors that correspond to the simple motion of the object orienting toward several directions in two-dimensional space in our neural network model. Introducing chaotic dynamics into the network gives outputs sampled from intermediate state points between embedded attractors in a state space, and these dynamics enable the object to move in various directions. System parameter switching between a chaotic and an attractor regime in the state space of the neural network enables the object to move to a set target in a two-dimensional maze. Results of computer simulations show that the success rate for this method over 300 trials is higher than that of random walk. To investigate why the proposed method gives better performance, we calculate and discuss statistical data with respect to dynamical structure.

Neural networks and fault probability evaluation for diagnosis issues.

PubMed

Kourd, Yahia; Lefebvre, Dimitri; Guersi, Noureddine

2014-01-01

This paper presents a new FDI technique for fault detection and isolation in unknown nonlinear systems. The objective of the research is to construct and analyze residuals by means of artificial intelligence and probabilistic methods. Artificial neural networks are first used for modeling issues. Neural networks models are designed for learning the fault-free and the faulty behaviors of the considered systems. Once the residuals generated, an evaluation using probabilistic criteria is applied to them to determine what is the most likely fault among a set of candidate faults. The study also includes a comparison between the contributions of these tools and their limitations, particularly through the establishment of quantitative indicators to assess their performance. According to the computation of a confidence factor, the proposed method is suitable to evaluate the reliability of the FDI decision. The approach is applied to detect and isolate 19 fault candidates in the DAMADICS benchmark. The results obtained with the proposed scheme are compared with the results obtained according to a usual thresholding method.

Regional application of multi-layer artificial neural networks in 3-D ionosphere tomography

NASA Astrophysics Data System (ADS)

Ghaffari Razin, Mir Reza; Voosoghi, Behzad

2016-08-01

Tomography is a very cost-effective method to study physical properties of the ionosphere. In this paper, residual minimization training neural network (RMTNN) is used in voxel-based tomography to reconstruct of 3-D ionosphere electron density with high spatial resolution. For numerical experiments, observations collected at 37 GPS stations from Iranian permanent GPS network (IPGN) are used. A smoothed TEC approach was used for absolute STEC recovery. To improve the vertical resolution, empirical orthogonal functions (EOFs) obtained from international reference ionosphere 2012 (IRI-2012) used as object function in training neural network. Ionosonde observations is used for validate reliability of the proposed method. Minimum relative error for RMTNN is 1.64% and maximum relative error is 15.61%. Also root mean square error (RMSE) of 0.17 × 1011 (electrons/m3) is computed for RMTNN which is less than RMSE of IRI2012. The results show that RMTNN has higher accuracy and compiles speed than other ionosphere reconstruction methods.

Automated detection of videotaped neonatal seizures of epileptic origin.

PubMed

Karayiannis, Nicolaos B; Xiong, Yaohua; Tao, Guozhi; Frost, James D; Wise, Merrill S; Hrachovy, Richard A; Mizrahi, Eli M

2006-06-01

This study aimed at the development of a seizure-detection system by training neural networks with quantitative motion information extracted from short video segments of neonatal seizures of the myoclonic and focal clonic types and random infant movements. The motion of the infants' body parts was quantified by temporal motion-strength signals extracted from video segments by motion-segmentation methods based on optical flow computation. The area of each frame occupied by the infants' moving body parts was segmented by clustering the motion parameters obtained by fitting an affine model to the pixel velocities. The motion of the infants' body parts also was quantified by temporal motion-trajectory signals extracted from video recordings by robust motion trackers based on block-motion models. These motion trackers were developed to adjust autonomously to illumination and contrast changes that may occur during the video-frame sequence. Video segments were represented by quantitative features obtained by analyzing motion-strength and motion-trajectory signals in both the time and frequency domains. Seizure recognition was performed by conventional feed-forward neural networks, quantum neural networks, and cosine radial basis function neural networks, which were trained to detect neonatal seizures of the myoclonic and focal clonic types and to distinguish them from random infant movements. The computational tools and procedures developed for automated seizure detection were evaluated on a set of 240 video segments of 54 patients exhibiting myoclonic seizures (80 segments), focal clonic seizures (80 segments), and random infant movements (80 segments). Regardless of the decision scheme used for interpreting the responses of the trained neural networks, all the neural network models exhibited sensitivity and specificity>90%. For one of the decision schemes proposed for interpreting the responses of the trained neural networks, the majority of the trained neural-network models exhibited sensitivity>90% and specificity>95%. In particular, cosine radial basis function neural networks achieved the performance targets of this phase of the project (i.e., sensitivity>95% and specificity>95%). The best among the motion segmentation and tracking methods developed in this study produced quantitative features that constitute a reliable basis for detecting neonatal seizures. The performance targets of this phase of the project were achieved by combining the quantitative features obtained by analyzing motion-strength signals with those produced by analyzing motion-trajectory signals. The computational procedures and tools developed in this study to perform off-line analysis of short video segments will be used in the next phase of this project, which involves the integration of these procedures and tools into a system that can process and analyze long video recordings of infants monitored for seizures in real time.

Water demand forecasting: review of soft computing methods.

PubMed

Ghalehkhondabi, Iman; Ardjmand, Ehsan; Young, William A; Weckman, Gary R

2017-07-01

Demand forecasting plays a vital role in resource management for governments and private companies. Considering the scarcity of water and its inherent constraints, demand management and forecasting in this domain are critically important. Several soft computing techniques have been developed over the last few decades for water demand forecasting. This study focuses on soft computing methods of water consumption forecasting published between 2005 and 2015. These methods include artificial neural networks (ANNs), fuzzy and neuro-fuzzy models, support vector machines, metaheuristics, and system dynamics. Furthermore, it was discussed that while in short-term forecasting, ANNs have been superior in many cases, but it is still very difficult to pick a single method as the overall best. According to the literature, various methods and their hybrids are applied to water demand forecasting. However, it seems soft computing has a lot more to contribute to water demand forecasting. These contribution areas include, but are not limited, to various ANN architectures, unsupervised methods, deep learning, various metaheuristics, and ensemble methods. Moreover, it is found that soft computing methods are mainly used for short-term demand forecasting.

Nuevas tecnicas basadas en redes neuronales para el diseno de filtros de microondas multicapa apantallados

NASA Astrophysics Data System (ADS)

Pascual Garcia, Juan

In this PhD thesis one method of shielded multilayer circuit neural network based analysis has been developed. One of the most successful analysis procedures of these kind of structures is the Integral Equation technique (IE) solved by the Method of Moments (MoM). In order to solve the IE, in the version which uses the media relevant potentials, it is necessary to have a formulation of the Green's functions associated to the mentioned potentials. The main computational burden in the IE resolution lies on the numerical evaluation of the Green's functions. In this work, the circuit analysis has been drastically accelerated thanks to the approximation of the Green's functions by means of neural networks. Once trained, the neural networks substitute the Green's functions in the IE. Two different types of neural networks have been used: the Radial basis function neural networks (RBFNN) and the Chebyshev neural networks. Thanks mainly to two distinct operations the correct approximation of the Green's functions has been possible. On the one hand, a very effective input space division has been developed. On the other hand, the elimination of the singularity makes feasible the approximation of slow variation functions. Two different singularity elimination strategies have been developed. The first one is based on the multiplication by the source-observation points distance (rho). The second one outperforms the first one. It consists of the extraction of two layers of spatial images from the whole summation of images. With regard to the Chebyshev neural networks, the OLS training algorithm has been applied in a novel fashion. This method allows the optimum design in this kind of neural networks. In this way, the performance of these neural networks outperforms greatly the RBFNNs one. In both networks, the time gain reached makes the neural method profitable. The time invested in the input space division and in the neural training is negligible with only few circuit analysis. To show, in a practical way, the ability of the neural based analysis method, two new design procedures have been developed. The first method uses the Genetic Algorithms to optimize an initial filter which does not fulfill the established specifications. A new fitness function, specially well suited to design filters, has been defined in order to assure the correct convergence of the optimization process. This new function measures the fulfillment of the specifications and it also prevents the appearance of the premature convergence problem. The second method is found on the approximation, by means of neural networks, of the relations between the electrical parameters, which defined the circuit response, and the physical dimensions that synthesize the aforementioned parameters. The neural networks trained with these data can be used in the design of many circuits in a given structure. Both methods had been show their ability in the design of practical filters.

Seismic activity prediction using computational intelligence techniques in northern Pakistan

NASA Astrophysics Data System (ADS)

Asim, Khawaja M.; Awais, Muhammad; Martínez-Álvarez, F.; Iqbal, Talat

2017-10-01

Earthquake prediction study is carried out for the region of northern Pakistan. The prediction methodology includes interdisciplinary interaction of seismology and computational intelligence. Eight seismic parameters are computed based upon the past earthquakes. Predictive ability of these eight seismic parameters is evaluated in terms of information gain, which leads to the selection of six parameters to be used in prediction. Multiple computationally intelligent models have been developed for earthquake prediction using selected seismic parameters. These models include feed-forward neural network, recurrent neural network, random forest, multi layer perceptron, radial basis neural network, and support vector machine. The performance of every prediction model is evaluated and McNemar's statistical test is applied to observe the statistical significance of computational methodologies. Feed-forward neural network shows statistically significant predictions along with accuracy of 75% and positive predictive value of 78% in context of northern Pakistan.

Deep learning with coherent nanophotonic circuits

NASA Astrophysics Data System (ADS)

Shen, Yichen; Harris, Nicholas C.; Skirlo, Scott; Prabhu, Mihika; Baehr-Jones, Tom; Hochberg, Michael; Sun, Xin; Zhao, Shijie; Larochelle, Hugo; Englund, Dirk; Soljačić, Marin

2017-07-01

Artificial neural networks are computational network models inspired by signal processing in the brain. These models have dramatically improved performance for many machine-learning tasks, including speech and image recognition. However, today's computing hardware is inefficient at implementing neural networks, in large part because much of it was designed for von Neumann computing schemes. Significant effort has been made towards developing electronic architectures tuned to implement artificial neural networks that exhibit improved computational speed and accuracy. Here, we propose a new architecture for a fully optical neural network that, in principle, could offer an enhancement in computational speed and power efficiency over state-of-the-art electronics for conventional inference tasks. We experimentally demonstrate the essential part of the concept using a programmable nanophotonic processor featuring a cascaded array of 56 programmable Mach-Zehnder interferometers in a silicon photonic integrated circuit and show its utility for vowel recognition.

Model-based decoding, information estimation, and change-point detection techniques for multineuron spike trains.

PubMed

Pillow, Jonathan W; Ahmadian, Yashar; Paninski, Liam

2011-01-01

One of the central problems in systems neuroscience is to understand how neural spike trains convey sensory information. Decoding methods, which provide an explicit means for reading out the information contained in neural spike responses, offer a powerful set of tools for studying the neural coding problem. Here we develop several decoding methods based on point-process neural encoding models, or forward models that predict spike responses to stimuli. These models have concave log-likelihood functions, which allow efficient maximum-likelihood model fitting and stimulus decoding. We present several applications of the encoding model framework to the problem of decoding stimulus information from population spike responses: (1) a tractable algorithm for computing the maximum a posteriori (MAP) estimate of the stimulus, the most probable stimulus to have generated an observed single- or multiple-neuron spike train response, given some prior distribution over the stimulus; (2) a gaussian approximation to the posterior stimulus distribution that can be used to quantify the fidelity with which various stimulus features are encoded; (3) an efficient method for estimating the mutual information between the stimulus and the spike trains emitted by a neural population; and (4) a framework for the detection of change-point times (the time at which the stimulus undergoes a change in mean or variance) by marginalizing over the posterior stimulus distribution. We provide several examples illustrating the performance of these estimators with simulated and real neural data.

Recurrent neural network based virtual detection line

NASA Astrophysics Data System (ADS)

Kadikis, Roberts

2018-04-01

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

eLoom and Flatland: specification, simulation and visualization engines for the study of arbitrary hierarchical neural architectures.

PubMed

Caudell, Thomas P; Xiao, Yunhai; Healy, Michael J

2003-01-01

eLoom is an open source graph simulation software tool, developed at the University of New Mexico (UNM), that enables users to specify and simulate neural network models. Its specification language and libraries enables users to construct and simulate arbitrary, potentially hierarchical network structures on serial and parallel processing systems. In addition, eLoom is integrated with UNM's Flatland, an open source virtual environments development tool to provide real-time visualizations of the network structure and activity. Visualization is a useful method for understanding both learning and computation in artificial neural networks. Through 3D animated pictorially representations of the state and flow of information in the network, a better understanding of network functionality is achieved. ART-1, LAPART-II, MLP, and SOM neural networks are presented to illustrate eLoom and Flatland's capabilities.

Equivalent Skin Analysis of Wing Structures Using Neural Networks

NASA Technical Reports Server (NTRS)

Liu, Youhua; Kapania, Rakesh K.

2000-01-01

An efficient method of modeling trapezoidal built-up wing structures is developed by coupling. in an indirect way, an Equivalent Plate Analysis (EPA) with Neural Networks (NN). Being assumed to behave like a Mindlin-plate, the wing is solved using the Ritz method with Legendre polynomials employed as the trial functions. This analysis method can be made more efficient by avoiding most of the computational effort spent on calculating contributions to the stiffness and mass matrices from each spar and rib. This is accomplished by replacing the wing inner-structure with an "equivalent" material that combines to the skin and whose properties are simulated by neural networks. The constitutive matrix, which relates the stress vector to the strain vector, and the density of the equivalent material are obtained by enforcing mass and stiffness matrix equities with rec,ard to the EPA in a least-square sense. Neural networks for the material properties are trained in terms of the design variables of the wing structure. Examples show that the present method, which can be called an Equivalent Skin Analysis (ESA) of the wing structure, is more efficient than the EPA and still fairly good results can be obtained. The present ESA is very promising to be used at the early stages of wing structure design.

Thermalnet: a Deep Convolutional Network for Synthetic Thermal Image Generation

NASA Astrophysics Data System (ADS)

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

2017-05-01

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

Neural Network Design on the SRC-6 Reconfigurable Computer

DTIC Science & Technology

2006-12-01

fingerprint identification. In this field, automatic identification methods are used to save time, especially for the purpose of fingerprint matching in...grid widths and lengths and therefore was useful in producing an accurate canvas with which to create sample training images. The added benefit of...tools available free of charge and readily accessible on the computer, it was simple to design bitmap data files visually on a canvas and then

Neural Information Processing in Cognition: We Start to Understand the Orchestra, but Where is the Conductor?

PubMed Central

Palm, Günther

2016-01-01

Research in neural information processing has been successful in the past, providing useful approaches both to practical problems in computer science and to computational models in neuroscience. Recent developments in the area of cognitive neuroscience present new challenges for a computational or theoretical understanding asking for neural information processing models that fulfill criteria or constraints from cognitive psychology, neuroscience and computational efficiency. The most important of these criteria for the evaluation of present and future contributions to this new emerging field are listed at the end of this article. PMID:26858632

Synthesizing cognition in neuromorphic electronic systems

PubMed Central

Neftci, Emre; Binas, Jonathan; Rutishauser, Ueli; Chicca, Elisabetta; Indiveri, Giacomo; Douglas, Rodney J.

2013-01-01

The quest to implement intelligent processing in electronic neuromorphic systems lacks methods for achieving reliable behavioral dynamics on substrates of inherently imprecise and noisy neurons. Here we report a solution to this problem that involves first mapping an unreliable hardware layer of spiking silicon neurons into an abstract computational layer composed of generic reliable subnetworks of model neurons and then composing the target behavioral dynamics as a “soft state machine” running on these reliable subnets. In the first step, the neural networks of the abstract layer are realized on the hardware substrate by mapping the neuron circuit bias voltages to the model parameters. This mapping is obtained by an automatic method in which the electronic circuit biases are calibrated against the model parameters by a series of population activity measurements. The abstract computational layer is formed by configuring neural networks as generic soft winner-take-all subnetworks that provide reliable processing by virtue of their active gain, signal restoration, and multistability. The necessary states and transitions of the desired high-level behavior are then easily embedded in the computational layer by introducing only sparse connections between some neurons of the various subnets. We demonstrate this synthesis method for a neuromorphic sensory agent that performs real-time context-dependent classification of motion patterns observed by a silicon retina. PMID:23878215

Neural-Network Computer Transforms Coordinates

NASA Technical Reports Server (NTRS)

Josin, Gary M.

1990-01-01

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

Discrimination of Mixed Taste Solutions using Ultrasonic Wave and Soft Computing

NASA Astrophysics Data System (ADS)

Kojima, Yohichiro; Kimura, Futoshi; Mikami, Tsuyoshi; Kitama, Masataka

In this study, ultrasonic wave acoustic properties of mixed taste solutions were investigated, and the possibility of taste sensing based on the acoustical properties obtained was examined. In previous studies, properties of solutions were discriminated based on sound velocity, amplitude and frequency characteristics of ultrasonic waves propagating through the five basic taste solutions and marketed beverages. However, to make this method applicable to beverages that contain many taste substances, further studies are required. In this paper, the waveform of an ultrasonic wave with frequency of approximately 5 MHz propagating through mixed solutions composed of sweet and salty substance was measured. As a result, differences among solutions were clearly observed as differences in their properties. Furthermore, these mixed solutions were discriminated by a self-organizing neural network. The ratio of volume in their mixed solutions was estimated by a distance-type fuzzy reasoning method. Therefore, the possibility of taste sensing was shown by using ultrasonic wave acoustic properties and the soft computing, such as the self-organizing neural network and the distance-type fuzzy reasoning method.

Single neuron computation: from dynamical system to feature detector.

PubMed

Hong, Sungho; Agüera y Arcas, Blaise; Fairhall, Adrienne L

2007-12-01

White noise methods are a powerful tool for characterizing the computation performed by neural systems. These methods allow one to identify the feature or features that a neural system extracts from a complex input and to determine how these features are combined to drive the system's spiking response. These methods have also been applied to characterize the input-output relations of single neurons driven by synaptic inputs, simulated by direct current injection. To interpret the results of white noise analysis of single neurons, we would like to understand how the obtained feature space of a single neuron maps onto the biophysical properties of the membrane, in particular, the dynamics of ion channels. Here, through analysis of a simple dynamical model neuron, we draw explicit connections between the output of a white noise analysis and the underlying dynamical system. We find that under certain assumptions, the form of the relevant features is well defined by the parameters of the dynamical system. Further, we show that under some conditions, the feature space is spanned by the spike-triggered average and its successive order time derivatives.

Machine learning action parameters in lattice quantum chromodynamics

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

Shanahan, Phiala; Trewartha, Daneil; Detmold, William

Numerical lattice quantum chromodynamics studies of the strong interaction underpin theoretical understanding of many aspects of particle and nuclear physics. Such studies require significant computing resources to undertake. A number of proposed methods promise improved efficiency of lattice calculations, and access to regions of parameter space that are currently computationally intractable, via multi-scale action-matching approaches that necessitate parametric regression of generated lattice datasets. The applicability of machine learning to this regression task is investigated, with deep neural networks found to provide an efficient solution even in cases where approaches such as principal component analysis fail. Finally, the high information contentmore » and complex symmetries inherent in lattice QCD datasets require custom neural network layers to be introduced and present opportunities for further development.« less

Machine learning action parameters in lattice quantum chromodynamics

DOE PAGES

Shanahan, Phiala; Trewartha, Daneil; Detmold, William

2018-05-16

Numerical lattice quantum chromodynamics studies of the strong interaction underpin theoretical understanding of many aspects of particle and nuclear physics. Such studies require significant computing resources to undertake. A number of proposed methods promise improved efficiency of lattice calculations, and access to regions of parameter space that are currently computationally intractable, via multi-scale action-matching approaches that necessitate parametric regression of generated lattice datasets. The applicability of machine learning to this regression task is investigated, with deep neural networks found to provide an efficient solution even in cases where approaches such as principal component analysis fail. Finally, the high information contentmore » and complex symmetries inherent in lattice QCD datasets require custom neural network layers to be introduced and present opportunities for further development.« less

Computational optical tomography using 3-D deep convolutional neural networks

NASA Astrophysics Data System (ADS)

Nguyen, Thanh; Bui, Vy; Nehmetallah, George

2018-04-01

Deep convolutional neural networks (DCNNs) offer a promising performance for many image processing areas, such as super-resolution, deconvolution, image classification, denoising, and segmentation, with outstanding results. Here, we develop for the first time, to our knowledge, a method to perform 3-D computational optical tomography using 3-D DCNN. A simulated 3-D phantom dataset was first constructed and converted to a dataset of phase objects imaged on a spatial light modulator. For each phase image in the dataset, the corresponding diffracted intensity image was experimentally recorded on a CCD. We then experimentally demonstrate the ability of the developed 3-D DCNN algorithm to solve the inverse problem by reconstructing the 3-D index of refraction distributions of test phantoms from the dataset from their corresponding diffraction patterns.

High-Density Liquid-State Machine Circuitry for Time-Series Forecasting.

PubMed

Rosselló, Josep L; Alomar, Miquel L; Morro, Antoni; Oliver, Antoni; Canals, Vincent

2016-08-01

Spiking neural networks (SNN) are the last neural network generation that try to mimic the real behavior of biological neurons. Although most research in this area is done through software applications, it is in hardware implementations in which the intrinsic parallelism of these computing systems are more efficiently exploited. Liquid state machines (LSM) have arisen as a strategic technique to implement recurrent designs of SNN with a simple learning methodology. In this work, we show a new low-cost methodology to implement high-density LSM by using Boolean gates. The proposed method is based on the use of probabilistic computing concepts to reduce hardware requirements, thus considerably increasing the neuron count per chip. The result is a highly functional system that is applied to high-speed time series forecasting.

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

Comparison of RF spectrum prediction methods for dynamic spectrum access

NASA Astrophysics Data System (ADS)

Kovarskiy, Jacob A.; Martone, Anthony F.; Gallagher, Kyle A.; Sherbondy, Kelly D.; Narayanan, Ram M.

2017-05-01

Dynamic spectrum access (DSA) refers to the adaptive utilization of today's busy electromagnetic spectrum. Cognitive radio/radar technologies require DSA to intelligently transmit and receive information in changing environments. Predicting radio frequency (RF) activity reduces sensing time and energy consumption for identifying usable spectrum. Typical spectrum prediction methods involve modeling spectral statistics with Hidden Markov Models (HMM) or various neural network structures. HMMs describe the time-varying state probabilities of Markov processes as a dynamic Bayesian network. Neural Networks model biological brain neuron connections to perform a wide range of complex and often non-linear computations. This work compares HMM, Multilayer Perceptron (MLP), and Recurrent Neural Network (RNN) algorithms and their ability to perform RF channel state prediction. Monte Carlo simulations on both measured and simulated spectrum data evaluate the performance of these algorithms. Generalizing spectrum occupancy as an alternating renewal process allows Poisson random variables to generate simulated data while energy detection determines the occupancy state of measured RF spectrum data for testing. The results suggest that neural networks achieve better prediction accuracy and prove more adaptable to changing spectral statistics than HMMs given sufficient training data.

Predicate calculus for an architecture of multiple neural networks

NASA Astrophysics Data System (ADS)

Consoli, Robert H.

1990-08-01

Future projects with neural networks will require multiple individual network components. Current efforts along these lines are ad hoc. This paper relates the neural network to a classical device and derives a multi-part architecture from that model. Further it provides a Predicate Calculus variant for describing the location and nature of the trainings and suggests Resolution Refutation as a method for determining the performance of the system as well as the location of needed trainings for specific proofs. 2. THE NEURAL NETWORK AND A CLASSICAL DEVICE Recently investigators have been making reports about architectures of multiple neural networksL234. These efforts are appearing at an early stage in neural network investigations they are characterized by architectures suggested directly by the problem space. Touretzky and Hinton suggest an architecture for processing logical statements1 the design of this architecture arises from the syntax of a restricted class of logical expressions and exhibits syntactic limitations. In similar fashion a multiple neural netword arises out of a control problem2 from the sequence learning problem3 and from the domain of machine learning. 4 But a general theory of multiple neural devices is missing. More general attempts to relate single or multiple neural networks to classical computing devices are not common although an attempt is made to relate single neural devices to a Turing machines and Sun et a!. develop a multiple neural architecture that performs pattern classification.

Designing in vivo concentration gradients with discrete controlled release: a computational model

NASA Astrophysics Data System (ADS)

Walker, Edgar Y.; Barbour, Dennis L.

2010-08-01

One promising neurorehabilitation therapy involves presenting neurotrophins directly into the brain to induce growth of new neural connections. The precise control of neurotrophin concentration gradients deep within neural tissue that would be necessary for such a therapy is not currently possible, however. Here we evaluate the theoretical potential of a novel method of drug delivery, discrete controlled release (DCR), to control effective neurotrophin concentration gradients in an isotropic region of neocortex. We do so by constructing computational models of neurotrophin concentration profiles resulting from discrete release locations into the cortex and then optimizing their design for uniform concentration gradients. The resulting model indicates that by rationally selecting initial neurotrophin concentrations for drug-releasing electrode coatings in a square 16-electrode array, nearly uniform concentration gradients (i.e. planar concentration profiles) from one edge of the electrode array to the other should be obtainable. DCR therefore represents a promising new method of precisely directing neuronal growth in vivo over a wider spatial profile than would be possible with single release points.

A convolutional neural network approach to calibrating the rotation axis for X-ray computed tomography

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

Yang, Xiaogang; De Carlo, Francesco; Phatak, Charudatta

This paper presents an algorithm to calibrate the center-of-rotation for X-ray tomography by using a machine learning approach, the Convolutional Neural Network (CNN). The algorithm shows excellent accuracy from the evaluation of synthetic data with various noise ratios. It is further validated with experimental data of four different shale samples measured at the Advanced Photon Source and at the Swiss Light Source. The results are as good as those determined by visual inspection and show better robustness than conventional methods. CNN has also great potential forreducing or removingother artifacts caused by instrument instability, detector non-linearity,etc. An open-source toolbox, which integratesmore » the CNN methods described in this paper, is freely available through GitHub at tomography/xlearn and can be easily integrated into existing computational pipelines available at various synchrotron facilities. Source code, documentation and information on how to contribute are also provided.« less

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.

EEG-fMRI Bayesian framework for neural activity estimation: a simulation study

NASA Astrophysics Data System (ADS)

Croce, Pierpaolo; Basti, Alessio; Marzetti, Laura; Zappasodi, Filippo; Del Gratta, Cosimo

2016-12-01

Objective. Due to the complementary nature of electroencephalography (EEG) and functional magnetic resonance imaging (fMRI), and given the possibility of simultaneous acquisition, the joint data analysis can afford a better understanding of the underlying neural activity estimation. In this simulation study we want to show the benefit of the joint EEG-fMRI neural activity estimation in a Bayesian framework. Approach. We built a dynamic Bayesian framework in order to perform joint EEG-fMRI neural activity time course estimation. The neural activity is originated by a given brain area and detected by means of both measurement techniques. We have chosen a resting state neural activity situation to address the worst case in terms of the signal-to-noise ratio. To infer information by EEG and fMRI concurrently we used a tool belonging to the sequential Monte Carlo (SMC) methods: the particle filter (PF). Main results. First, despite a high computational cost, we showed the feasibility of such an approach. Second, we obtained an improvement in neural activity reconstruction when using both EEG and fMRI measurements. Significance. The proposed simulation shows the improvements in neural activity reconstruction with EEG-fMRI simultaneous data. The application of such an approach to real data allows a better comprehension of the neural dynamics.

EEG-fMRI Bayesian framework for neural activity estimation: a simulation study.

PubMed

Croce, Pierpaolo; Basti, Alessio; Marzetti, Laura; Zappasodi, Filippo; Gratta, Cosimo Del

2016-12-01

Due to the complementary nature of electroencephalography (EEG) and functional magnetic resonance imaging (fMRI), and given the possibility of simultaneous acquisition, the joint data analysis can afford a better understanding of the underlying neural activity estimation. In this simulation study we want to show the benefit of the joint EEG-fMRI neural activity estimation in a Bayesian framework. We built a dynamic Bayesian framework in order to perform joint EEG-fMRI neural activity time course estimation. The neural activity is originated by a given brain area and detected by means of both measurement techniques. We have chosen a resting state neural activity situation to address the worst case in terms of the signal-to-noise ratio. To infer information by EEG and fMRI concurrently we used a tool belonging to the sequential Monte Carlo (SMC) methods: the particle filter (PF). First, despite a high computational cost, we showed the feasibility of such an approach. Second, we obtained an improvement in neural activity reconstruction when using both EEG and fMRI measurements. The proposed simulation shows the improvements in neural activity reconstruction with EEG-fMRI simultaneous data. The application of such an approach to real data allows a better comprehension of the neural dynamics.

Automated selection of computed tomography display parameters using neural networks

NASA Astrophysics Data System (ADS)

Zhang, Di; Neu, Scott; Valentino, Daniel J.

2001-07-01

A collection of artificial neural networks (ANN's) was trained to identify simple anatomical structures in a set of x-ray computed tomography (CT) images. These neural networks learned to associate a point in an image with the anatomical structure containing the point by using the image pixels located on the horizontal and vertical lines that ran through the point. The neural networks were integrated into a computer software tool whose function is to select an index into a list of CT window/level values from the location of the user's mouse cursor. Based upon the anatomical structure selected by the user, the software tool automatically adjusts the image display to optimally view the structure.

Normalization as a canonical neural computation

PubMed Central

Carandini, Matteo; Heeger, David J.

2012-01-01

There is increasing evidence that the brain relies on a set of canonical neural computations, repeating them across brain regions and modalities to apply similar operations to different problems. A promising candidate for such a computation is normalization, in which the responses of neurons are divided by a common factor that typically includes the summed activity of a pool of neurons. Normalization was developed to explain responses in the primary visual cortex and is now thought to operate throughout the visual system, and in many other sensory modalities and brain regions. Normalization may underlie operations such as the representation of odours, the modulatory effects of visual attention, the encoding of value and the integration of multisensory information. Its presence in such a diversity of neural systems in multiple species, from invertebrates to mammals, suggests that it serves as a canonical neural computation. PMID:22108672

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…

Lumen-based detection of prostate cancer via convolutional neural networks

NASA Astrophysics Data System (ADS)

Kwak, Jin Tae; Hewitt, Stephen M.

2017-03-01

We present a deep learning approach for detecting prostate cancers. The approach consists of two steps. In the first step, we perform tissue segmentation that identifies lumens within digitized prostate tissue specimen images. Intensity- and texture-based image features are computed at five different scales, and a multiview boosting method is adopted to cooperatively combine the image features from differing scales and to identify lumens. In the second step, we utilize convolutional neural networks (CNN) to automatically extract high-level image features of lumens and to predict cancers. The segmented lumens are rescaled to reduce computational complexity and data augmentation by scaling, rotating, and flipping the rescaled image is applied to avoid overfitting. We evaluate the proposed method using two tissue microarrays (TMA) - TMA1 includes 162 tissue specimens (73 Benign and 89 Cancer) and TMA2 comprises 185 tissue specimens (70 Benign and 115 Cancer). In cross-validation on TMA1, the proposed method achieved an AUC of 0.95 (CI: 0.93-0.98). Trained on TMA1 and tested on TMA2, CNN obtained an AUC of 0.95 (CI: 0.92-0.98). This demonstrates that the proposed method can potentially improve prostate cancer pathology.

A study on using texture analysis methods for identifying lobar fissure regions in isotropic CT images.

PubMed

Wei, Q; Hu, Y

2009-01-01

The major hurdle for segmenting lung lobes in computed tomographic (CT) images is to identify fissure regions, which encase lobar fissures. Accurate identification of these regions is difficult due to the variable shape and appearance of the fissures, along with the low contrast and high noise associated with CT images. This paper studies the effectiveness of two texture analysis methods - the gray level co-occurrence matrix (GLCM) and the gray level run length matrix (GLRLM) - in identifying fissure regions from isotropic CT image stacks. To classify GLCM and GLRLM texture features, we applied a feed-forward back-propagation neural network and achieved the best classification accuracy utilizing 16 quantized levels for computing the GLCM and GLRLM texture features and 64 neurons in the input/hidden layers of the neural network. Tested on isotropic CT image stacks of 24 patients with the pathologic lungs, we obtained accuracies of 86% and 87% for identifying fissure regions using the GLCM and GLRLM methods, respectively. These accuracies compare favorably with surgeons/radiologists' accuracy of 80% for identifying fissure regions in clinical settings. This shows promising potential for segmenting lung lobes using the GLCM and GLRLM methods.

Random noise effects in pulse-mode digital multilayer neural networks.

PubMed

Kim, Y C; Shanblatt, M A

1995-01-01

A pulse-mode digital multilayer neural network (DMNN) based on stochastic computing techniques is implemented with simple logic gates as basic computing elements. The pulse-mode signal representation and the use of simple logic gates for neural operations lead to a massively parallel yet compact and flexible network architecture, well suited for VLSI implementation. Algebraic neural operations are replaced by stochastic processes using pseudorandom pulse sequences. The distributions of the results from the stochastic processes are approximated using the hypergeometric distribution. Synaptic weights and neuron states are represented as probabilities and estimated as average pulse occurrence rates in corresponding pulse sequences. A statistical model of the noise (error) is developed to estimate the relative accuracy associated with stochastic computing in terms of mean and variance. Computational differences are then explained by comparison to deterministic neural computations. DMNN feedforward architectures are modeled in VHDL using character recognition problems as testbeds. Computational accuracy is analyzed, and the results of the statistical model are compared with the actual simulation results. Experiments show that the calculations performed in the DMNN are more accurate than those anticipated when Bernoulli sequences are assumed, as is common in the literature. Furthermore, the statistical model successfully predicts the accuracy of the operations performed in the DMNN.

Large Deviations for Nonlocal Stochastic Neural Fields

PubMed Central

2014-01-01

We study the effect of additive noise on integro-differential neural field equations. In particular, we analyze an Amari-type model driven by a Q-Wiener process, and focus on noise-induced transitions and escape. We argue that proving a sharp Kramers’ law for neural fields poses substantial difficulties, but that one may transfer techniques from stochastic partial differential equations to establish a large deviation principle (LDP). Then we demonstrate that an efficient finite-dimensional approximation of the stochastic neural field equation can be achieved using a Galerkin method and that the resulting finite-dimensional rate function for the LDP can have a multiscale structure in certain cases. These results form the starting point for an efficient practical computation of the LDP. Our approach also provides the technical basis for further rigorous study of noise-induced transitions in neural fields based on Galerkin approximations. Mathematics Subject Classification (2000): 60F10, 60H15, 65M60, 92C20. PMID:24742297

Forecasting PM10 in metropolitan areas: Efficacy of neural networks.

PubMed

Fernando, H J S; Mammarella, M C; Grandoni, G; Fedele, P; Di Marco, R; Dimitrova, R; Hyde, P

2012-04-01

Deterministic photochemical air quality models are commonly used for regulatory management and planning of urban airsheds. These models are complex, computer intensive, and hence are prohibitively expensive for routine air quality predictions. Stochastic methods are becoming increasingly popular as an alternative, which relegate decision making to artificial intelligence based on Neural Networks that are made of artificial neurons or 'nodes' capable of 'learning through training' via historic data. A Neural Network was used to predict particulate matter concentration at a regulatory monitoring site in Phoenix, Arizona; its development, efficacy as a predictive tool and performance vis-à-vis a commonly used regulatory photochemical model are described in this paper. It is concluded that Neural Networks are much easier, quicker and economical to implement without compromising the accuracy of predictions. Neural Networks can be used to develop rapid air quality warning systems based on a network of automated monitoring stations. Copyright © 2011 Elsevier Ltd. All rights reserved.

Face recognition: a convolutional neural-network approach.

PubMed

Lawrence, S; Giles, C L; Tsoi, A C; Back, A D

1997-01-01

We present a hybrid neural-network for human face recognition which compares favourably with other methods. The system combines local image sampling, a self-organizing map (SOM) neural network, and a convolutional neural network. The SOM provides a quantization of the image samples into a topological space where inputs that are nearby in the original space are also nearby in the output space, thereby providing dimensionality reduction and invariance to minor changes in the image sample, and the convolutional neural network provides partial invariance to translation, rotation, scale, and deformation. The convolutional network extracts successively larger features in a hierarchical set of layers. We present results using the Karhunen-Loeve transform in place of the SOM, and a multilayer perceptron (MLP) in place of the convolutional network for comparison. We use a database of 400 images of 40 individuals which contains quite a high degree of variability in expression, pose, and facial details. We analyze the computational complexity and discuss how new classes could be added to the trained recognizer.

The super-Turing computational power of plastic recurrent neural networks.

PubMed

Cabessa, Jérémie; Siegelmann, Hava T

2014-12-01

We study the computational capabilities of a biologically inspired neural model where the synaptic weights, the connectivity pattern, and the number of neurons can evolve over time rather than stay static. Our study focuses on the mere concept of plasticity of the model so that the nature of the updates is assumed to be not constrained. In this context, we show that the so-called plastic recurrent neural networks (RNNs) are capable of the precise super-Turing computational power--as the static analog neural networks--irrespective of whether their synaptic weights are modeled by rational or real numbers, and moreover, irrespective of whether their patterns of plasticity are restricted to bi-valued updates or expressed by any other more general form of updating. Consequently, the incorporation of only bi-valued plastic capabilities in a basic model of RNNs suffices to break the Turing barrier and achieve the super-Turing level of computation. The consideration of more general mechanisms of architectural plasticity or of real synaptic weights does not further increase the capabilities of the networks. These results support the claim that the general mechanism of plasticity is crucially involved in the computational and dynamical capabilities of biological neural networks. They further show that the super-Turing level of computation reflects in a suitable way the capabilities of brain-like models of computation.

Linking structure and activity in nonlinear spiking networks

PubMed Central

Josić, Krešimir; Shea-Brown, Eric

2017-01-01

Recent experimental advances are producing an avalanche of data on both neural connectivity and neural activity. To take full advantage of these two emerging datasets we need a framework that links them, revealing how collective neural activity arises from the structure of neural connectivity and intrinsic neural dynamics. This problem of structure-driven activity has drawn major interest in computational neuroscience. Existing methods for relating activity and architecture in spiking networks rely on linearizing activity around a central operating point and thus fail to capture the nonlinear responses of individual neurons that are the hallmark of neural information processing. Here, we overcome this limitation and present a new relationship between connectivity and activity in networks of nonlinear spiking neurons by developing a diagrammatic fluctuation expansion based on statistical field theory. We explicitly show how recurrent network structure produces pairwise and higher-order correlated activity, and how nonlinearities impact the networks’ spiking activity. Our findings open new avenues to investigating how single-neuron nonlinearities—including those of different cell types—combine with connectivity to shape population activity and function. PMID:28644840

A dual estimate method for aeromagnetic compensation

NASA Astrophysics Data System (ADS)

Ma, Ming; Zhou, Zhijian; Cheng, Defu

2017-11-01

Scalar aeromagnetic surveys have played a vital role in prospecting. However, before analysis of the surveys’ aeromagnetic data is possible, the aircraft’s magnetic interference should be removed. The extensively adopted linear model for aeromagnetic compensation is computationally efficient but faces an underfitting problem. On the other hand, the neural model proposed by Williams is more powerful at fitting but always suffers from an overfitting problem. This paper starts off with an analysis of these two models and then proposes a dual estimate method to combine them together to improve accuracy. This method is based on an unscented Kalman filter, but a gradient descent method is implemented over the iteration so that the parameters of the linear model are adjustable during flight. The noise caused by the neural model’s overfitting problem is suppressed by introducing an observation noise.

An Energy Model of Place Cell Network in Three Dimensional Space.

PubMed

Wang, Yihong; Xu, Xuying; Wang, Rubin

2018-01-01

Place cells are important elements in the spatial representation system of the brain. A considerable amount of experimental data and classical models are achieved in this area. However, an important question has not been addressed, which is how the three dimensional space is represented by the place cells. This question is preliminarily surveyed by energy coding method in this research. Energy coding method argues that neural information can be expressed by neural energy and it is convenient to model and compute for neural systems due to the global and linearly addable properties of neural energy. Nevertheless, the models of functional neural networks based on energy coding method have not been established. In this work, we construct a place cell network model to represent three dimensional space on an energy level. Then we define the place field and place field center and test the locating performance in three dimensional space. The results imply that the model successfully simulates the basic properties of place cells. The individual place cell obtains unique spatial selectivity. The place fields in three dimensional space vary in size and energy consumption. Furthermore, the locating error is limited to a certain level and the simulated place field agrees to the experimental results. In conclusion, this is an effective model to represent three dimensional space by energy method. The research verifies the energy efficiency principle of the brain during the neural coding for three dimensional spatial information. It is the first step to complete the three dimensional spatial representing system of the brain, and helps us further understand how the energy efficiency principle directs the locating, navigating, and path planning function of the brain.

Non-causal spike filtering improves decoding of movement intention for intracortical BCIs

PubMed Central

Masse, Nicolas Y.; Jarosiewicz, Beata; Simeral, John D.; Bacher, Daniel; Stavisky, Sergey D.; Cash, Sydney S.; Oakley, Erin M.; Berhanu, Etsub; Eskandar, Emad; Friehs, Gerhard; Hochberg, Leigh R.; Donoghue, John P.

2014-01-01

Background Multiple types of neural signals are available for controlling assistive devices through brain-computer interfaces (BCIs). Intracortically-recorded spiking neural signals are attractive for BCIs because they can in principle provide greater fidelity of encoded information compared to electrocorticographic (ECoG) signals and electroencephalograms (EEGs). Recent reports show that the information content of these spiking neural signals can be reliably extracted simply by causally band-pass filtering the recorded extracellular voltage signals and then applying a spike detection threshold, without relying on “sorting” action potentials. New method We show that replacing the causal filter with an equivalent non-causal filter increases the information content extracted from the extracellular spiking signal and improves decoding of intended movement direction. This method can be used for real-time BCI applications by using a 4 ms lag between recording and filtering neural signals. Results Across 18 sessions from two people with tetraplegia enrolled in the BrainGate2 pilot clinical trial, we found that threshold crossing events extracted using this non-causal filtering method were significantly more informative of each participant’s intended cursor kinematics compared to threshold crossing events derived from causally filtered signals. This new method decreased the mean angular error between the intended and decoded cursor direction by 9.7° for participant S3, who was implanted 5.4 years prior to this study, and by 3.5° for participant T2, who was implanted 3 months prior to this study. Conclusions Non-causally filtering neural signals prior to extracting threshold crossing events may be a simple yet effective way to condition intracortically recorded neural activity for direct control of external devices through BCIs. PMID:25128256

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

PubMed

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

2017-07-18

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

Neurally and Ocularly Informed Graph-Based Models for Searching 3D Environments

DTIC Science & Technology

2014-06-03

hBCI = hybrid brain–computer interface, TAG = transductive annotation by graph, CV = computer vision, TSP = traveling salesman problem . are navigated...environment that are most likely to contain objects that the subject would like to visit. 2.9. Route planning A traveling salesman problem (TSP) solver...fixations in a visual search task using fixation-related potentials J. Vis. 13 Croes G 1958 A method for solving traveling - salesman problems Oper. Res

Improved neural network based scene-adaptive nonuniformity correction method for infrared focal plane arrays.

PubMed

Lai, Rui; Yang, Yin-tang; Zhou, Duan; Li, Yue-jin

2008-08-20

An improved scene-adaptive nonuniformity correction (NUC) algorithm for infrared focal plane arrays (IRFPAs) is proposed. This method simultaneously estimates the infrared detectors' parameters and eliminates the nonuniformity causing fixed pattern noise (FPN) by using a neural network (NN) approach. In the learning process of neuron parameter estimation, the traditional LMS algorithm is substituted with the newly presented variable step size (VSS) normalized least-mean square (NLMS) based adaptive filtering algorithm, which yields faster convergence, smaller misadjustment, and lower computational cost. In addition, a new NN structure is designed to estimate the desired target value, which promotes the calibration precision considerably. The proposed NUC method reaches high correction performance, which is validated by the experimental results quantitatively tested with a simulative testing sequence and a real infrared image sequence.

Modeling fMRI signals can provide insights into neural processing in the cerebral cortex

PubMed Central

Sharifian, Fariba; Heikkinen, Hanna; Vigário, Ricardo

2015-01-01

Every stimulus or task activates multiple areas in the mammalian cortex. These distributed activations can be measured with functional magnetic resonance imaging (fMRI), which has the best spatial resolution among the noninvasive brain imaging methods. Unfortunately, the relationship between the fMRI activations and distributed cortical processing has remained unclear, both because the coupling between neural and fMRI activations has remained poorly understood and because fMRI voxels are too large to directly sense the local neural events. To get an idea of the local processing given the macroscopic data, we need models to simulate the neural activity and to provide output that can be compared with fMRI data. Such models can describe neural mechanisms as mathematical functions between input and output in a specific system, with little correspondence to physiological mechanisms. Alternatively, models can be biomimetic, including biological details with straightforward correspondence to experimental data. After careful balancing between complexity, computational efficiency, and realism, a biomimetic simulation should be able to provide insight into how biological structures or functions contribute to actual data processing as well as to promote theory-driven neuroscience experiments. This review analyzes the requirements for validating system-level computational models with fMRI. In particular, we study mesoscopic biomimetic models, which include a limited set of details from real-life networks and enable system-level simulations of neural mass action. In addition, we discuss how recent developments in neurophysiology and biophysics may significantly advance the modelling of fMRI signals. PMID:25972586

Modeling fMRI signals can provide insights into neural processing in the cerebral cortex.

PubMed

Vanni, Simo; Sharifian, Fariba; Heikkinen, Hanna; Vigário, Ricardo

2015-08-01

Every stimulus or task activates multiple areas in the mammalian cortex. These distributed activations can be measured with functional magnetic resonance imaging (fMRI), which has the best spatial resolution among the noninvasive brain imaging methods. Unfortunately, the relationship between the fMRI activations and distributed cortical processing has remained unclear, both because the coupling between neural and fMRI activations has remained poorly understood and because fMRI voxels are too large to directly sense the local neural events. To get an idea of the local processing given the macroscopic data, we need models to simulate the neural activity and to provide output that can be compared with fMRI data. Such models can describe neural mechanisms as mathematical functions between input and output in a specific system, with little correspondence to physiological mechanisms. Alternatively, models can be biomimetic, including biological details with straightforward correspondence to experimental data. After careful balancing between complexity, computational efficiency, and realism, a biomimetic simulation should be able to provide insight into how biological structures or functions contribute to actual data processing as well as to promote theory-driven neuroscience experiments. This review analyzes the requirements for validating system-level computational models with fMRI. In particular, we study mesoscopic biomimetic models, which include a limited set of details from real-life networks and enable system-level simulations of neural mass action. In addition, we discuss how recent developments in neurophysiology and biophysics may significantly advance the modelling of fMRI signals. Copyright © 2015 the American Physiological Society.

Databases, data integration, and expert systems: new directions in mineral resource assessment and mineral exploration

USGS Publications Warehouse

McCammon, Richard B.; Ramani, Raja V.; Mozumdar, Bijoy K.; Samaddar, Arun B.

1994-01-01

Overcoming future difficulties in searching for ore deposits deeper in the earth's crust will require closer attention to the collection and analysis of more diverse types of data and to more efficient use of current computer technologies. Computer technologies of greatest interest include methods of storage and retrieval of resource information, methods for integrating geologic, geochemical, and geophysical data, and the introduction of advanced computer technologies such as expert systems, multivariate techniques, and neural networks. Much experience has been gained in the past few years in applying these technologies. More experience is needed if they are to be implemented for everyday use in future assessments and exploration.

Language Networks as Complex Systems

ERIC Educational Resources Information Center

Lee, Max Kueiming; Ou, Sheue-Jen

2008-01-01

Starting in the late eighties, with a growing discontent with analytical methods in science and the growing power of computers, researchers began to study complex systems such as living organisms, evolution of genes, biological systems, brain neural networks, epidemics, ecology, economy, social networks, etc. In the early nineties, the research…

Denoising by coupled partial differential equations and extracting phase by backpropagation neural networks for electronic speckle pattern interferometry.

PubMed

Tang, Chen; Lu, Wenjing; Chen, Song; Zhang, Zhen; Li, Botao; Wang, Wenping; Han, Lin

2007-10-20

We extend and refine previous work [Appl. Opt. 46, 2907 (2007)]. Combining the coupled nonlinear partial differential equations (PDEs) denoising model with the ordinary differential equations enhancement method, we propose the new denoising and enhancing model for electronic speckle pattern interferometry (ESPI) fringe patterns. Meanwhile, we propose the backpropagation neural networks (BPNN) method to obtain unwrapped phase values based on a skeleton map instead of traditional interpolations. We test the introduced methods on the computer-simulated speckle ESPI fringe patterns and experimentally obtained fringe pattern, respectively. The experimental results show that the coupled nonlinear PDEs denoising model is capable of effectively removing noise, and the unwrapped phase values obtained by the BPNN method are much more accurate than those obtained by the well-known traditional interpolation. In addition, the accuracy of the BPNN method is adjustable by changing the parameters of networks such as the number of neurons.

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.

New exponential synchronization criteria for time-varying delayed neural networks with discontinuous activations.

PubMed

Cai, Zuowei; Huang, Lihong; Zhang, Lingling

2015-05-01

This paper investigates the problem of exponential synchronization of time-varying delayed neural networks with discontinuous neuron activations. Under the extended Filippov differential inclusion framework, by designing discontinuous state-feedback controller and using some analytic techniques, new testable algebraic criteria are obtained to realize two different kinds of global exponential synchronization of the drive-response system. Moreover, we give the estimated rate of exponential synchronization which depends on the delays and system parameters. The obtained results extend some previous works on synchronization of delayed neural networks not only with continuous activations but also with discontinuous activations. Finally, numerical examples are provided to show the correctness of our analysis via computer simulations. Our method and theoretical results have a leading significance in the design of synchronized neural network circuits involving discontinuous factors and time-varying delays. Copyright © 2015 Elsevier Ltd. All rights reserved.

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.

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

Neural-genetic synthesis for state-space controllers based on linear quadratic regulator design for eigenstructure assignment.

PubMed

da Fonseca Neto, João Viana; Abreu, Ivanildo Silva; da Silva, Fábio Nogueira

2010-04-01

Toward the synthesis of state-space controllers, a neural-genetic model based on the linear quadratic regulator design for the eigenstructure assignment of multivariable dynamic systems is presented. The neural-genetic model represents a fusion of a genetic algorithm and a recurrent neural network (RNN) to perform the selection of the weighting matrices and the algebraic Riccati equation solution, respectively. A fourth-order electric circuit model is used to evaluate the convergence of the computational intelligence paradigms and the control design method performance. The genetic search convergence evaluation is performed in terms of the fitness function statistics and the RNN convergence, which is evaluated by landscapes of the energy and norm, as a function of the parameter deviations. The control problem solution is evaluated in the time and frequency domains by the impulse response, singular values, and modal analysis.

Within- and across-trial dynamics of human EEG reveal cooperative interplay between reinforcement learning and working memory.

PubMed

Collins, Anne G E; Frank, Michael J

2018-03-06

Learning from rewards and punishments is essential to survival and facilitates flexible human behavior. It is widely appreciated that multiple cognitive and reinforcement learning systems contribute to decision-making, but the nature of their interactions is elusive. Here, we leverage methods for extracting trial-by-trial indices of reinforcement learning (RL) and working memory (WM) in human electro-encephalography to reveal single-trial computations beyond that afforded by behavior alone. Neural dynamics confirmed that increases in neural expectation were predictive of reduced neural surprise in the following feedback period, supporting central tenets of RL models. Within- and cross-trial dynamics revealed a cooperative interplay between systems for learning, in which WM contributes expectations to guide RL, despite competition between systems during choice. Together, these results provide a deeper understanding of how multiple neural systems interact for learning and decision-making and facilitate analysis of their disruption in clinical populations.

Global Neural Pattern Similarity as a Common Basis for Categorization and Recognition Memory

PubMed Central

Xue, Gui; Love, Bradley C.; Preston, Alison R.; Poldrack, Russell A.

2014-01-01

Familiarity, or memory strength, is a central construct in models of cognition. In previous categorization and long-term memory research, correlations have been found between psychological measures of memory strength and activation in the medial temporal lobes (MTLs), which suggests a common neural locus for memory strength. However, activation alone is insufficient for determining whether the same mechanisms underlie neural function across domains. Guided by mathematical models of categorization and long-term memory, we develop a theory and a method to test whether memory strength arises from the global similarity among neural representations. In human subjects, we find significant correlations between global similarity among activation patterns in the MTLs and both subsequent memory confidence in a recognition memory task and model-based measures of memory strength in a category learning task. Our work bridges formal cognitive theories and neuroscientific models by illustrating that the same global similarity computations underlie processing in multiple cognitive domains. Moreover, by establishing a link between neural similarity and psychological memory strength, our findings suggest that there may be an isomorphism between psychological and neural representational spaces that can be exploited to test cognitive theories at both the neural and behavioral levels. PMID:24872552

Tomographic methods in flow diagnostics

NASA Technical Reports Server (NTRS)

Decker, Arthur J.

1993-01-01

This report presents a viewpoint of tomography that should be well adapted to currently available optical measurement technology as well as the needs of computational and experimental fluid dynamists. The goals in mind are to record data with the fastest optical array sensors; process the data with the fastest parallel processing technology available for small computers; and generate results for both experimental and theoretical data. An in-depth example treats interferometric data as it might be recorded in an aeronautics test facility, but the results are applicable whenever fluid properties are to be measured or applied from projections of those properties. The paper discusses both computed and neural net calibration tomography. The report also contains an overview of key definitions and computational methods, key references, computational problems such as ill-posedness, artifacts, missing data, and some possible and current research topics.

Identification of the connections in biologically inspired neural networks

NASA Technical Reports Server (NTRS)

Demuth, H.; Leung, K.; Beale, M.; Hicklin, J.

1990-01-01

We developed an identification method to find the strength of the connections between neurons from their behavior in small biologically-inspired artificial neural networks. That is, given the network external inputs and the temporal firing pattern of the neurons, we can calculate a solution for the strengths of the connections between neurons and the initial neuron activations if a solution exists. The method determines directly if there is a solution to a particular neural network problem. No training of the network is required. It should be noted that this is a first pass at the solution of a difficult problem. The neuron and network models chosen are related to biology but do not contain all of its complexities, some of which we hope to add to the model in future work. A variety of new results have been obtained. First, the method has been tailored to produce connection weight matrix solutions for networks with important features of biological neural (bioneural) networks. Second, a computationally efficient method of finding a robust central solution has been developed. This later method also enables us to find the most consistent solution in the presence of noisy data. Prospects of applying our method to identify bioneural network connections are exciting because such connections are almost impossible to measure in the laboratory. Knowledge of such connections would facilitate an understanding of bioneural networks and would allow the construction of the electronic counterparts of bioneural networks on very large scale integrated (VLSI) circuits.

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

NASA Astrophysics Data System (ADS)

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

2018-03-01

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

Accelerating global optimization of aerodynamic shapes using a new surrogate-assisted parallel genetic algorithm

NASA Astrophysics Data System (ADS)

Ebrahimi, Mehdi; Jahangirian, Alireza

2017-12-01

An efficient strategy is presented for global shape optimization of wing sections with a parallel genetic algorithm. Several computational techniques are applied to increase the convergence rate and the efficiency of the method. A variable fidelity computational evaluation method is applied in which the expensive Navier-Stokes flow solver is complemented by an inexpensive multi-layer perceptron neural network for the objective function evaluations. A population dispersion method that consists of two phases, of exploration and refinement, is developed to improve the convergence rate and the robustness of the genetic algorithm. Owing to the nature of the optimization problem, a parallel framework based on the master/slave approach is used. The outcomes indicate that the method is able to find the global optimum with significantly lower computational time in comparison to the conventional genetic algorithm.

High-performance reconfigurable hardware architecture for restricted Boltzmann machines.

PubMed

Ly, Daniel Le; Chow, Paul

2010-11-01

Despite the popularity and success of neural networks in research, the number of resulting commercial or industrial applications has been limited. A primary cause for this lack of adoption is that neural networks are usually implemented as software running on general-purpose processors. Hence, a hardware implementation that can exploit the inherent parallelism in neural networks is desired. This paper investigates how the restricted Boltzmann machine (RBM), which is a popular type of neural network, can be mapped to a high-performance hardware architecture on field-programmable gate array (FPGA) platforms. The proposed modular framework is designed to reduce the time complexity of the computations through heavily customized hardware engines. A method to partition large RBMs into smaller congruent components is also presented, allowing the distribution of one RBM across multiple FPGA resources. The framework is tested on a platform of four Xilinx Virtex II-Pro XC2VP70 FPGAs running at 100 MHz through a variety of different configurations. The maximum performance was obtained by instantiating an RBM of 256 × 256 nodes distributed across four FPGAs, which resulted in a computational speed of 3.13 billion connection-updates-per-second and a speedup of 145-fold over an optimized C program running on a 2.8-GHz Intel processor.

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.

CNN-BLPred: a Convolutional neural network based predictor for β-Lactamases (BL) and their classes.

PubMed

White, Clarence; Ismail, Hamid D; Saigo, Hiroto; Kc, Dukka B

2017-12-28

The β-Lactamase (BL) enzyme family is an important class of enzymes that plays a key role in bacterial resistance to antibiotics. As the newly identified number of BL enzymes is increasing daily, it is imperative to develop a computational tool to classify the newly identified BL enzymes into one of its classes. There are two types of classification of BL enzymes: Molecular Classification and Functional Classification. Existing computational methods only address Molecular Classification and the performance of these existing methods is unsatisfactory. We addressed the unsatisfactory performance of the existing methods by implementing a Deep Learning approach called Convolutional Neural Network (CNN). We developed CNN-BLPred, an approach for the classification of BL proteins. The CNN-BLPred uses Gradient Boosted Feature Selection (GBFS) in order to select the ideal feature set for each BL classification. Based on the rigorous benchmarking of CCN-BLPred using both leave-one-out cross-validation and independent test sets, CCN-BLPred performed better than the other existing algorithms. Compared with other architectures of CNN, Recurrent Neural Network, and Random Forest, the simple CNN architecture with only one convolutional layer performs the best. After feature extraction, we were able to remove ~95% of the 10,912 features using Gradient Boosted Trees. During 10-fold cross validation, we increased the accuracy of the classic BL predictions by 7%. We also increased the accuracy of Class A, Class B, Class C, and Class D performance by an average of 25.64%. The independent test results followed a similar trend. We implemented a deep learning algorithm known as Convolutional Neural Network (CNN) to develop a classifier for BL classification. Combined with feature selection on an exhaustive feature set and using balancing method such as Random Oversampling (ROS), Random Undersampling (RUS) and Synthetic Minority Oversampling Technique (SMOTE), CNN-BLPred performs significantly better than existing algorithms for BL classification.

A signal-flow-graph approach to on-line gradient calculation.

PubMed

Campolucci, P; Uncini, A; Piazza, F

2000-08-01

A large class of nonlinear dynamic adaptive systems such as dynamic recurrent neural networks can be effectively represented by signal flow graphs (SFGs). By this method, complex systems are described as a general connection of many simple components, each of them implementing a simple one-input, one-output transformation, as in an electrical circuit. Even if graph representations are popular in the neural network community, they are often used for qualitative description rather than for rigorous representation and computational purposes. In this article, a method for both on-line and batch-backward gradient computation of a system output or cost function with respect to system parameters is derived by the SFG representation theory and its known properties. The system can be any causal, in general nonlinear and time-variant, dynamic system represented by an SFG, in particular any feedforward, time-delay, or recurrent neural network. In this work, we use discrete-time notation, but the same theory holds for the continuous-time case. The gradient is obtained in a straightforward way by the analysis of two SFGs, the original one and its adjoint (obtained from the first by simple transformations), without the complex chain rule expansions of derivatives usually employed. This method can be used for sensitivity analysis and for learning both off-line and on-line. On-line learning is particularly important since it is required by many real applications, such as digital signal processing, system identification and control, channel equalization, and predistortion.

Reinforced dynamics for enhanced sampling in large atomic and molecular systems

NASA Astrophysics Data System (ADS)

Zhang, Linfeng; Wang, Han; E, Weinan

2018-03-01

A new approach for efficiently exploring the configuration space and computing the free energy of large atomic and molecular systems is proposed, motivated by an analogy with reinforcement learning. There are two major components in this new approach. Like metadynamics, it allows for an efficient exploration of the configuration space by adding an adaptively computed biasing potential to the original dynamics. Like deep reinforcement learning, this biasing potential is trained on the fly using deep neural networks, with data collected judiciously from the exploration and an uncertainty indicator from the neural network model playing the role of the reward function. Parameterization using neural networks makes it feasible to handle cases with a large set of collective variables. This has the potential advantage that selecting precisely the right set of collective variables has now become less critical for capturing the structural transformations of the system. The method is illustrated by studying the full-atom explicit solvent models of alanine dipeptide and tripeptide, as well as the system of a polyalanine-10 molecule with 20 collective variables.

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

DOT National Transportation Integrated Search

2008-09-01

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

Artificial intelligence in medicine.

PubMed Central

Ramesh, A. N.; Kambhampati, C.; Monson, J. R. T.; Drew, P. J.

2004-01-01

INTRODUCTION: Artificial intelligence is a branch of computer science capable of analysing complex medical data. Their potential to exploit meaningful relationship with in a data set can be used in the diagnosis, treatment and predicting outcome in many clinical scenarios. METHODS: Medline and internet searches were carried out using the keywords 'artificial intelligence' and 'neural networks (computer)'. Further references were obtained by cross-referencing from key articles. An overview of different artificial intelligent techniques is presented in this paper along with the review of important clinical applications. RESULTS: The proficiency of artificial intelligent techniques has been explored in almost every field of medicine. Artificial neural network was the most commonly used analytical tool whilst other artificial intelligent techniques such as fuzzy expert systems, evolutionary computation and hybrid intelligent systems have all been used in different clinical settings. DISCUSSION: Artificial intelligence techniques have the potential to be applied in almost every field of medicine. There is need for further clinical trials which are appropriately designed before these emergent techniques find application in the real clinical setting. PMID:15333167

Neural network approach to time-dependent dividing surfaces in classical reaction dynamics.

PubMed

Schraft, Philippe; Junginger, Andrej; Feldmaier, Matthias; Bardakcioglu, Robin; Main, Jörg; Wunner, Günter; Hernandez, Rigoberto

2018-04-01

In a dynamical system, the transition between reactants and products is typically mediated by an energy barrier whose properties determine the corresponding pathways and rates. The latter is the flux through a dividing surface (DS) between the two corresponding regions, and it is exact only if it is free of recrossings. For time-independent barriers, the DS can be attached to the top of the corresponding saddle point of the potential energy surface, and in time-dependent systems, the DS is a moving object. The precise determination of these direct reaction rates, e.g., using transition state theory, requires the actual construction of a DS for a given saddle geometry, which is in general a demanding methodical and computational task, especially in high-dimensional systems. In this paper, we demonstrate how such time-dependent, global, and recrossing-free DSs can be constructed using neural networks. In our approach, the neural network uses the bath coordinates and time as input, and it is trained in a way that its output provides the position of the DS along the reaction coordinate. An advantage of this procedure is that, once the neural network is trained, the complete information about the dynamical phase space separation is stored in the network's parameters, and a precise distinction between reactants and products can be made for all possible system configurations, all times, and with little computational effort. We demonstrate this general method for two- and three-dimensional systems and explain its straightforward extension to even more degrees of freedom.

Neural network approach to time-dependent dividing surfaces in classical reaction dynamics

NASA Astrophysics Data System (ADS)

Schraft, Philippe; Junginger, Andrej; Feldmaier, Matthias; Bardakcioglu, Robin; Main, Jörg; Wunner, Günter; Hernandez, Rigoberto

2018-04-01

In a dynamical system, the transition between reactants and products is typically mediated by an energy barrier whose properties determine the corresponding pathways and rates. The latter is the flux through a dividing surface (DS) between the two corresponding regions, and it is exact only if it is free of recrossings. For time-independent barriers, the DS can be attached to the top of the corresponding saddle point of the potential energy surface, and in time-dependent systems, the DS is a moving object. The precise determination of these direct reaction rates, e.g., using transition state theory, requires the actual construction of a DS for a given saddle geometry, which is in general a demanding methodical and computational task, especially in high-dimensional systems. In this paper, we demonstrate how such time-dependent, global, and recrossing-free DSs can be constructed using neural networks. In our approach, the neural network uses the bath coordinates and time as input, and it is trained in a way that its output provides the position of the DS along the reaction coordinate. An advantage of this procedure is that, once the neural network is trained, the complete information about the dynamical phase space separation is stored in the network's parameters, and a precise distinction between reactants and products can be made for all possible system configurations, all times, and with little computational effort. We demonstrate this general method for two- and three-dimensional systems and explain its straightforward extension to even more degrees of freedom.

Linking normative models of natural tasks to descriptive models of neural response.

PubMed

Jaini, Priyank; Burge, Johannes

2017-10-01

Understanding how nervous systems exploit task-relevant properties of sensory stimuli to perform natural tasks is fundamental to the study of perceptual systems. However, there are few formal methods for determining which stimulus properties are most useful for a given natural task. As a consequence, it is difficult to develop principled models for how to compute task-relevant latent variables from natural signals, and it is difficult to evaluate descriptive models fit to neural response. Accuracy maximization analysis (AMA) is a recently developed Bayesian method for finding the optimal task-specific filters (receptive fields). Here, we introduce AMA-Gauss, a new faster form of AMA that incorporates the assumption that the class-conditional filter responses are Gaussian distributed. Then, we use AMA-Gauss to show that its assumptions are justified for two fundamental visual tasks: retinal speed estimation and binocular disparity estimation. Next, we show that AMA-Gauss has striking formal similarities to popular quadratic models of neural response: the energy model and the generalized quadratic model (GQM). Together, these developments deepen our understanding of why the energy model of neural response have proven useful, improve our ability to evaluate results from subunit model fits to neural data, and should help accelerate psychophysics and neuroscience research with natural stimuli.

Recurrent Neural Network for Computing the Drazin Inverse.

PubMed

Stanimirović, Predrag S; Zivković, Ivan S; Wei, Yimin

2015-11-01

This paper presents a recurrent neural network (RNN) for computing the Drazin inverse of a real matrix in real time. This recurrent neural network (RNN) is composed of n independent parts (subnetworks), where n is the order of the input matrix. These subnetworks can operate concurrently, so parallel and distributed processing can be achieved. In this way, the computational advantages over the existing sequential algorithms can be attained in real-time applications. The RNN defined in this paper is convenient for an implementation in an electronic circuit. The number of neurons in the neural network is the same as the number of elements in the output matrix, which represents the Drazin inverse. The difference between the proposed RNN and the existing ones for the Drazin inverse computation lies in their network architecture and dynamics. The conditions that ensure the stability of the defined RNN as well as its convergence toward the Drazin inverse are considered. In addition, illustrative examples and examples of application to the practical engineering problems are discussed to show the efficacy of the proposed neural network.

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

NASA Astrophysics Data System (ADS)

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

2018-02-01

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

Efficient organ localization using multi-label convolutional neural networks in thorax-abdomen CT scans

NASA Astrophysics Data System (ADS)

Efrain Humpire-Mamani, Gabriel; Arindra Adiyoso Setio, Arnaud; van Ginneken, Bram; Jacobs, Colin

2018-04-01

Automatic localization of organs and other structures in medical images is an important preprocessing step that can improve and speed up other algorithms such as organ segmentation, lesion detection, and registration. This work presents an efficient method for simultaneous localization of multiple structures in 3D thorax-abdomen CT scans. Our approach predicts the location of multiple structures using a single multi-label convolutional neural network for each orthogonal view. Each network takes extra slices around the current slice as input to provide extra context. A sigmoid layer is used to perform multi-label classification. The output of the three networks is subsequently combined to compute a 3D bounding box for each structure. We used our approach to locate 11 structures of interest. The neural network was trained and evaluated on a large set of 1884 thorax-abdomen CT scans from patients undergoing oncological workup. Reference bounding boxes were annotated by human observers. The performance of our method was evaluated by computing the wall distance to the reference bounding boxes. The bounding boxes annotated by the first human observer were used as the reference standard for the test set. Using the best configuration, we obtained an average wall distance of 3.20~+/-~7.33 mm in the test set. The second human observer achieved 1.23~+/-~3.39 mm. For all structures, the results were better than those reported in previously published studies. In conclusion, we proposed an efficient method for the accurate localization of multiple organs. Our method uses multiple slices as input to provide more context around the slice under analysis, and we have shown that this improves performance. This method can easily be adapted to handle more organs.

APPLICATION OF NEURAL COMPUTING METHODS FOR INTERPRETING PHOSPHOLIPID FATTY ACID PROFILES OF NATURAL MICROBIAL COMMUNITIES. (R826944)

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...

Hierarchical Recurrent Neural Hashing for Image Retrieval With Hierarchical Convolutional Features.

PubMed

Lu, Xiaoqiang; Chen, Yaxiong; Li, Xuelong

Hashing has been an important and effective technology in image retrieval due to its computational efficiency and fast search speed. The traditional hashing methods usually learn hash functions to obtain binary codes by exploiting hand-crafted features, which cannot optimally represent the information of the sample. Recently, deep learning methods can achieve better performance, since deep learning architectures can learn more effective image representation features. However, these methods only use semantic features to generate hash codes by shallow projection but ignore texture details. In this paper, we proposed a novel hashing method, namely hierarchical recurrent neural hashing (HRNH), to exploit hierarchical recurrent neural network to generate effective hash codes. There are three contributions of this paper. First, a deep hashing method is proposed to extensively exploit both spatial details and semantic information, in which, we leverage hierarchical convolutional features to construct image pyramid representation. Second, our proposed deep network can exploit directly convolutional feature maps as input to preserve the spatial structure of convolutional feature maps. Finally, we propose a new loss function that considers the quantization error of binarizing the continuous embeddings into the discrete binary codes, and simultaneously maintains the semantic similarity and balanceable property of hash codes. Experimental results on four widely used data sets demonstrate that the proposed HRNH can achieve superior performance over other state-of-the-art hashing methods.Hashing has been an important and effective technology in image retrieval due to its computational efficiency and fast search speed. The traditional hashing methods usually learn hash functions to obtain binary codes by exploiting hand-crafted features, which cannot optimally represent the information of the sample. Recently, deep learning methods can achieve better performance, since deep learning architectures can learn more effective image representation features. However, these methods only use semantic features to generate hash codes by shallow projection but ignore texture details. In this paper, we proposed a novel hashing method, namely hierarchical recurrent neural hashing (HRNH), to exploit hierarchical recurrent neural network to generate effective hash codes. There are three contributions of this paper. First, a deep hashing method is proposed to extensively exploit both spatial details and semantic information, in which, we leverage hierarchical convolutional features to construct image pyramid representation. Second, our proposed deep network can exploit directly convolutional feature maps as input to preserve the spatial structure of convolutional feature maps. Finally, we propose a new loss function that considers the quantization error of binarizing the continuous embeddings into the discrete binary codes, and simultaneously maintains the semantic similarity and balanceable property of hash codes. Experimental results on four widely used data sets demonstrate that the proposed HRNH can achieve superior performance over other state-of-the-art hashing methods.

Adaptive regularization network based neural modeling paradigm for nonlinear adaptive estimation of cerebral evoked potentials.

PubMed

Zhang, Jian-Hua; Böhme, Johann F

2007-11-01

In this paper we report an adaptive regularization network (ARN) approach to realizing fast blind separation of cerebral evoked potentials (EPs) from background electroencephalogram (EEG) activity with no need to make any explicit assumption on the statistical (or deterministic) signal model. The ARNs are proposed to construct nonlinear EEG and EP signal models. A novel adaptive regularization training (ART) algorithm is proposed to improve the generalization performance of the ARN. Two adaptive neural modeling methods based on the ARN are developed and their implementation and performance analysis are also presented. The computer experiments using simulated and measured visual evoked potential (VEP) data have shown that the proposed ARN modeling paradigm yields computationally efficient and more accurate VEP signal estimation owing to its intrinsic model-free and nonlinear processing characteristics.

Neural Cognition and Affective Computing on Cyber Language.

PubMed

Huang, Shuang; Zhou, Xuan; Xue, Ke; Wan, Xiqiong; Yang, Zhenyi; Xu, Duo; Ivanović, Mirjana; Yu, Xueer

2015-01-01

Characterized by its customary symbol system and simple and vivid expression patterns, cyber language acts as not only a tool for convenient communication but also a carrier of abundant emotions and causes high attention in public opinion analysis, internet marketing, service feedback monitoring, and social emergency management. Based on our multidisciplinary research, this paper presents a classification of the emotional symbols in cyber language, analyzes the cognitive characteristics of different symbols, and puts forward a mechanism model to show the dominant neural activities in that process. Through the comparative study of Chinese, English, and Spanish, which are used by the largest population in the world, this paper discusses the expressive patterns of emotions in international cyber languages and proposes an intelligent method for affective computing on cyber language in a unified PAD (Pleasure-Arousal-Dominance) emotional space.

Neural Cognition and Affective Computing on Cyber Language

PubMed Central

Huang, Shuang; Zhou, Xuan; Xue, Ke; Wan, Xiqiong; Yang, Zhenyi; Xu, Duo; Ivanović, Mirjana

2015-01-01

Characterized by its customary symbol system and simple and vivid expression patterns, cyber language acts as not only a tool for convenient communication but also a carrier of abundant emotions and causes high attention in public opinion analysis, internet marketing, service feedback monitoring, and social emergency management. Based on our multidisciplinary research, this paper presents a classification of the emotional symbols in cyber language, analyzes the cognitive characteristics of different symbols, and puts forward a mechanism model to show the dominant neural activities in that process. Through the comparative study of Chinese, English, and Spanish, which are used by the largest population in the world, this paper discusses the expressive patterns of emotions in international cyber languages and proposes an intelligent method for affective computing on cyber language in a unified PAD (Pleasure-Arousal-Dominance) emotional space. PMID:26491431

Antenna analysis using neural networks

NASA Technical Reports Server (NTRS)

Smith, William T.

1992-01-01

Conventional computing schemes have long been used to analyze problems in electromagnetics (EM). The vast majority of EM applications require computationally intensive algorithms involving numerical integration and solutions to large systems of equations. The feasibility of using neural network computing algorithms for antenna analysis is investigated. The ultimate goal is to use a trained neural network algorithm to reduce the computational demands of existing reflector surface error compensation techniques. Neural networks are computational algorithms based on neurobiological systems. Neural nets consist of massively parallel interconnected nonlinear computational elements. They are often employed in pattern recognition and image processing problems. Recently, neural network analysis has been applied in the electromagnetics area for the design of frequency selective surfaces and beam forming networks. The backpropagation training algorithm was employed to simulate classical antenna array synthesis techniques. The Woodward-Lawson (W-L) and Dolph-Chebyshev (D-C) array pattern synthesis techniques were used to train the neural network. The inputs to the network were samples of the desired synthesis pattern. The outputs are the array element excitations required to synthesize the desired pattern. Once trained, the network is used to simulate the W-L or D-C techniques. Various sector patterns and cosecant-type patterns (27 total) generated using W-L synthesis were used to train the network. Desired pattern samples were then fed to the neural network. The outputs of the network were the simulated W-L excitations. A 20 element linear array was used. There were 41 input pattern samples with 40 output excitations (20 real parts, 20 imaginary). A comparison between the simulated and actual W-L techniques is shown for a triangular-shaped pattern. Dolph-Chebyshev is a different class of synthesis technique in that D-C is used for side lobe control as opposed to pattern shaping. The interesting thing about D-C synthesis is that the side lobes have the same amplitude. Five-element arrays were used. Again, 41 pattern samples were used for the input. Nine actual D-C patterns ranging from -10 dB to -30 dB side lobe levels were used to train the network. A comparison between simulated and actual D-C techniques for a pattern with -22 dB side lobe level is shown. The goal for this research was to evaluate the performance of neural network computing with antennas. Future applications will employ the backpropagation training algorithm to drastically reduce the computational complexity involved in performing EM compensation for surface errors in large space reflector antennas.

Antenna analysis using neural networks

NASA Astrophysics Data System (ADS)

Smith, William T.

1992-09-01

Conventional computing schemes have long been used to analyze problems in electromagnetics (EM). The vast majority of EM applications require computationally intensive algorithms involving numerical integration and solutions to large systems of equations. The feasibility of using neural network computing algorithms for antenna analysis is investigated. The ultimate goal is to use a trained neural network algorithm to reduce the computational demands of existing reflector surface error compensation techniques. Neural networks are computational algorithms based on neurobiological systems. Neural nets consist of massively parallel interconnected nonlinear computational elements. They are often employed in pattern recognition and image processing problems. Recently, neural network analysis has been applied in the electromagnetics area for the design of frequency selective surfaces and beam forming networks. The backpropagation training algorithm was employed to simulate classical antenna array synthesis techniques. The Woodward-Lawson (W-L) and Dolph-Chebyshev (D-C) array pattern synthesis techniques were used to train the neural network. The inputs to the network were samples of the desired synthesis pattern. The outputs are the array element excitations required to synthesize the desired pattern. Once trained, the network is used to simulate the W-L or D-C techniques. Various sector patterns and cosecant-type patterns (27 total) generated using W-L synthesis were used to train the network. Desired pattern samples were then fed to the neural network. The outputs of the network were the simulated W-L excitations. A 20 element linear array was used. There were 41 input pattern samples with 40 output excitations (20 real parts, 20 imaginary).

Spatiotemporal Dynamics and Reliable Computations in Recurrent Spiking Neural Networks

NASA Astrophysics Data System (ADS)

Pyle, Ryan; Rosenbaum, Robert

2017-01-01

Randomly connected networks of excitatory and inhibitory spiking neurons provide a parsimonious model of neural variability, but are notoriously unreliable for performing computations. We show that this difficulty is overcome by incorporating the well-documented dependence of connection probability on distance. Spatially extended spiking networks exhibit symmetry-breaking bifurcations and generate spatiotemporal patterns that can be trained to perform dynamical computations under a reservoir computing framework.

Performance/price estimates for cortex-scale hardware: a design space exploration.

PubMed

Zaveri, Mazad S; Hammerstrom, Dan

2011-04-01

In this paper, we revisit the concept of virtualization. Virtualization is useful for understanding and investigating the performance/price and other trade-offs related to the hardware design space. Moreover, it is perhaps the most important aspect of a hardware design space exploration. Such a design space exploration is a necessary part of the study of hardware architectures for large-scale computational models for intelligent computing, including AI, Bayesian, bio-inspired and neural models. A methodical exploration is needed to identify potentially interesting regions in the design space, and to assess the relative performance/price points of these implementations. As an example, in this paper we investigate the performance/price of (digital and mixed-signal) CMOS and hypothetical CMOL (nanogrid) technology based hardware implementations of human cortex-scale spiking neural systems. Through this analysis, and the resulting performance/price points, we demonstrate, in general, the importance of virtualization, and of doing these kinds of design space explorations. The specific results suggest that hybrid nanotechnology such as CMOL is a promising candidate to implement very large-scale spiking neural systems, providing a more efficient utilization of the density and storage benefits of emerging nano-scale technologies. In general, we believe that the study of such hypothetical designs/architectures will guide the neuromorphic hardware community towards building large-scale systems, and help guide research trends in intelligent computing, and computer engineering. Copyright © 2010 Elsevier Ltd. All rights reserved.

Computer aided decision making for heart disease detection using hybrid neural network-Genetic algorithm.

PubMed

Arabasadi, Zeinab; Alizadehsani, Roohallah; Roshanzamir, Mohamad; Moosaei, Hossein; Yarifard, Ali Asghar

2017-04-01

Cardiovascular disease is one of the most rampant causes of death around the world and was deemed as a major illness in Middle and Old ages. Coronary artery disease, in particular, is a widespread cardiovascular malady entailing high mortality rates. Angiography is, more often than not, regarded as the best method for the diagnosis of coronary artery disease; on the other hand, it is associated with high costs and major side effects. Much research has, therefore, been conducted using machine learning and data mining so as to seek alternative modalities. Accordingly, we herein propose a highly accurate hybrid method for the diagnosis of coronary artery disease. As a matter of fact, the proposed method is able to increase the performance of neural network by approximately 10% through enhancing its initial weights using genetic algorithm which suggests better weights for neural network. Making use of such methodology, we achieved accuracy, sensitivity and specificity rates of 93.85%, 97% and 92% respectively, on Z-Alizadeh Sani dataset. Copyright © 2017 Elsevier B.V. All rights reserved.

GaAs Optoelectronic Integrated-Circuit Neurons

NASA Technical Reports Server (NTRS)

Lin, Steven H.; Kim, Jae H.; Psaltis, Demetri

1992-01-01

Monolithic GaAs optoelectronic integrated circuits developed for use as artificial neurons. Neural-network computer contains planar arrays of optoelectronic neurons, and variable synaptic connections between neurons effected by diffraction of light from volume hologram in photorefractive material. Basic principles of neural-network computers explained more fully in "Optoelectronic Integrated Circuits For Neural Networks" (NPO-17652). In present circuits, devices replaced by metal/semiconductor field effect transistors (MESFET's), which consume less power.

Nature-Inspired Cognitive Evolution to Play MS. Pac-Man

NASA Astrophysics Data System (ADS)

Tan, Tse Guan; Teo, Jason; Anthony, Patricia

Recent developments in nature-inspired computation have heightened the need for research into the three main areas of scientific, engineering and industrial applications. Some approaches have reported that it is able to solve dynamic problems and very useful for improving the performance of various complex systems. So far however, there has been little discussion about the effectiveness of the application of these models to computer and video games in particular. The focus of this research is to explore the hybridization of nature-inspired computation methods for optimization of neural network-based cognition in video games, in this case the combination of a neural network with an evolutionary algorithm. In essence, a neural network is an attempt to mimic the extremely complex human brain system, which is building an artificial brain that is able to self-learn intelligently. On the other hand, an evolutionary algorithm is to simulate the biological evolutionary processes that evolve potential solutions in order to solve the problems or tasks by applying the genetic operators such as crossover, mutation and selection into the solutions. This paper investigates the abilities of Evolution Strategies (ES) to evolve feed-forward artificial neural network's internal parameters (i.e. weight and bias values) for automatically generating Ms. Pac-man controllers. The main objective of this game is to clear a maze of dots while avoiding the ghosts and to achieve the highest possible score. The experimental results show that an ES-based system can be successfully applied to automatically generate artificial intelligence for a complex, dynamic and highly stochastic video game environment.

Neuroscience-inspired computational systems for speech recognition under noisy conditions

NASA Astrophysics Data System (ADS)

Schafer, Phillip B.

Humans routinely recognize speech in challenging acoustic environments with background music, engine sounds, competing talkers, and other acoustic noise. However, today's automatic speech recognition (ASR) systems perform poorly in such environments. In this dissertation, I present novel methods for ASR designed to approach human-level performance by emulating the brain's processing of sounds. I exploit recent advances in auditory neuroscience to compute neuron-based representations of speech, and design novel methods for decoding these representations to produce word transcriptions. I begin by considering speech representations modeled on the spectrotemporal receptive fields of auditory neurons. These representations can be tuned to optimize a variety of objective functions, which characterize the response properties of a neural population. I propose an objective function that explicitly optimizes the noise invariance of the neural responses, and find that it gives improved performance on an ASR task in noise compared to other objectives. The method as a whole, however, fails to significantly close the performance gap with humans. I next consider speech representations that make use of spiking model neurons. The neurons in this method are feature detectors that selectively respond to spectrotemporal patterns within short time windows in speech. I consider a number of methods for training the response properties of the neurons. In particular, I present a method using linear support vector machines (SVMs) and show that this method produces spikes that are robust to additive noise. I compute the spectrotemporal receptive fields of the neurons for comparison with previous physiological results. To decode the spike-based speech representations, I propose two methods designed to work on isolated word recordings. The first method uses a classical ASR technique based on the hidden Markov model. The second method is a novel template-based recognition scheme that takes advantage of the neural representation's invariance in noise. The scheme centers on a speech similarity measure based on the longest common subsequence between spike sequences. The combined encoding and decoding scheme outperforms a benchmark system in extremely noisy acoustic conditions. Finally, I consider methods for decoding spike representations of continuous speech. To help guide the alignment of templates to words, I design a syllable detection scheme that robustly marks the locations of syllabic nuclei. The scheme combines SVM-based training with a peak selection algorithm designed to improve noise tolerance. By incorporating syllable information into the ASR system, I obtain strong recognition results in noisy conditions, although the performance in noiseless conditions is below the state of the art. The work presented here constitutes a novel approach to the problem of ASR that can be applied in the many challenging acoustic environments in which we use computer technologies today. The proposed spike-based processing methods can potentially be exploited in effcient hardware implementations and could significantly reduce the computational costs of ASR. The work also provides a framework for understanding the advantages of spike-based acoustic coding in the human brain.

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

PubMed

Somers, M J

1999-04-01

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

Neural simulations on multi-core architectures.

PubMed

Eichner, Hubert; Klug, Tobias; Borst, Alexander

2009-01-01

Neuroscience is witnessing increasing knowledge about the anatomy and electrophysiological properties of neurons and their connectivity, leading to an ever increasing computational complexity of neural simulations. At the same time, a rather radical change in personal computer technology emerges with the establishment of multi-cores: high-density, explicitly parallel processor architectures for both high performance as well as standard desktop computers. This work introduces strategies for the parallelization of biophysically realistic neural simulations based on the compartmental modeling technique and results of such an implementation, with a strong focus on multi-core architectures and automation, i.e. user-transparent load balancing.

Neural Simulations on Multi-Core Architectures

PubMed Central

Eichner, Hubert; Klug, Tobias; Borst, Alexander

2009-01-01

Neuroscience is witnessing increasing knowledge about the anatomy and electrophysiological properties of neurons and their connectivity, leading to an ever increasing computational complexity of neural simulations. At the same time, a rather radical change in personal computer technology emerges with the establishment of multi-cores: high-density, explicitly parallel processor architectures for both high performance as well as standard desktop computers. This work introduces strategies for the parallelization of biophysically realistic neural simulations based on the compartmental modeling technique and results of such an implementation, with a strong focus on multi-core architectures and automation, i.e. user-transparent load balancing. PMID:19636393

Neural Computations in a Dynamical System with Multiple Time Scales.

PubMed

Mi, Yuanyuan; Lin, Xiaohan; Wu, Si

2016-01-01

Neural systems display rich short-term dynamics at various levels, e.g., spike-frequency adaptation (SFA) at the single-neuron level, and short-term facilitation (STF) and depression (STD) at the synapse level. These dynamical features typically cover a broad range of time scales and exhibit large diversity in different brain regions. It remains unclear what is the computational benefit for the brain to have such variability in short-term dynamics. In this study, we propose that the brain can exploit such dynamical features to implement multiple seemingly contradictory computations in a single neural circuit. To demonstrate this idea, we use continuous attractor neural network (CANN) as a working model and include STF, SFA and STD with increasing time constants in its dynamics. Three computational tasks are considered, which are persistent activity, adaptation, and anticipative tracking. These tasks require conflicting neural mechanisms, and hence cannot be implemented by a single dynamical feature or any combination with similar time constants. However, with properly coordinated STF, SFA and STD, we show that the network is able to implement the three computational tasks concurrently. We hope this study will shed light on the understanding of how the brain orchestrates its rich dynamics at various levels to realize diverse cognitive functions.

How Neural Networks Learn from Experience.

ERIC Educational Resources Information Center

Hinton, Geoffrey E.

1992-01-01

Discusses computational studies of learning in artificial neural networks and findings that may provide insights into the learning abilities of the human brain. Describes efforts to test theories about brain information processing, using artificial neural networks. Vignettes include information concerning how a neural network represents…

Metamodels for Computer-Based Engineering Design: Survey and Recommendations

NASA Technical Reports Server (NTRS)

Simpson, Timothy W.; Peplinski, Jesse; Koch, Patrick N.; Allen, Janet K.

1997-01-01

The use of statistical techniques to build approximations of expensive computer analysis codes pervades much of todays engineering design. These statistical approximations, or metamodels, are used to replace the actual expensive computer analyses, facilitating multidisciplinary, multiobjective optimization and concept exploration. In this paper we review several of these techniques including design of experiments, response surface methodology, Taguchi methods, neural networks, inductive learning, and kriging. We survey their existing application in engineering design and then address the dangers of applying traditional statistical techniques to approximate deterministic computer analysis codes. We conclude with recommendations for the appropriate use of statistical approximation techniques in given situations and how common pitfalls can be avoided.

Neural network-based feature point descriptors for registration of optical and SAR images

NASA Astrophysics Data System (ADS)

Abulkhanov, Dmitry; Konovalenko, Ivan; Nikolaev, Dmitry; Savchik, Alexey; Shvets, Evgeny; Sidorchuk, Dmitry

2018-04-01

Registration of images of different nature is an important technique used in image fusion, change detection, efficient information representation and other problems of computer vision. Solving this task using feature-based approaches is usually more complex than registration of several optical images because traditional feature descriptors (SIFT, SURF, etc.) perform poorly when images have different nature. In this paper we consider the problem of registration of SAR and optical images. We train neural network to build feature point descriptors and use RANSAC algorithm to align found matches. Experimental results are presented that confirm the method's effectiveness.

Multiscale Rotation-Invariant Convolutional Neural Networks for Lung Texture Classification.

PubMed

Wang, Qiangchang; Zheng, Yuanjie; Yang, Gongping; Jin, Weidong; Chen, Xinjian; Yin, Yilong

2018-01-01

We propose a new multiscale rotation-invariant convolutional neural network (MRCNN) model for classifying various lung tissue types on high-resolution computed tomography. MRCNN employs Gabor-local binary pattern that introduces a good property in image analysis-invariance to image scales and rotations. In addition, we offer an approach to deal with the problems caused by imbalanced number of samples between different classes in most of the existing works, accomplished by changing the overlapping size between the adjacent patches. Experimental results on a public interstitial lung disease database show a superior performance of the proposed method to state of the art.

Deep convolutional neural network based antenna selection in multiple-input multiple-output system

NASA Astrophysics Data System (ADS)

Cai, Jiaxin; Li, Yan; Hu, Ying

2018-03-01

Antenna selection of wireless communication system has attracted increasing attention due to the challenge of keeping a balance between communication performance and computational complexity in large-scale Multiple-Input MultipleOutput antenna systems. Recently, deep learning based methods have achieved promising performance for large-scale data processing and analysis in many application fields. This paper is the first attempt to introduce the deep learning technique into the field of Multiple-Input Multiple-Output antenna selection in wireless communications. First, the label of attenuation coefficients channel matrix is generated by minimizing the key performance indicator of training antenna systems. Then, a deep convolutional neural network that explicitly exploits the massive latent cues of attenuation coefficients is learned on the training antenna systems. Finally, we use the adopted deep convolutional neural network to classify the channel matrix labels of test antennas and select the optimal antenna subset. Simulation experimental results demonstrate that our method can achieve better performance than the state-of-the-art baselines for data-driven based wireless antenna selection.

Quantitative structure-activity relationships by neural networks and inductive logic programming. I. The inhibition of dihydrofolate reductase by pyrimidines

NASA Astrophysics Data System (ADS)

Hirst, Jonathan D.; King, Ross D.; Sternberg, Michael J. E.

1994-08-01

Neural networks and inductive logic programming (ILP) have been compared to linear regression for modelling the QSAR of the inhibition of E. coli dihydrofolate reductase (DHFR) by 2,4-diamino-5-(substitured benzyl)pyrimidines, and, in the subsequent paper [Hirst, J.D., King, R.D. and Sternberg, M.J.E., J. Comput.-Aided Mol. Design, 8 (1994) 421], the inhibition of rodent DHFR by 2,4-diamino-6,6-dimethyl-5-phenyl-dihydrotriazines. Cross-validation trials provide a statistically rigorous assessment of the predictive capabilities of the methods, with training and testing data selected randomly and all the methods developed using identical training data. For the ILP analysis, molecules are represented by attributes other than Hansch parameters. Neural networks and ILP perform better than linear regression using the attribute representation, but the difference is not statistically significant. The major benefit from the ILP analysis is the formulation of understandable rules relating the activity of the inhibitors to their chemical structure.

Dense Matching Comparison Between Census and a Convolutional Neural Network Algorithm for Plant Reconstruction

NASA Astrophysics Data System (ADS)

Xia, Y.; Tian, J.; d'Angelo, P.; Reinartz, P.

2018-05-01

3D reconstruction of plants is hard to implement, as the complex leaf distribution highly increases the difficulty level in dense matching. Semi-Global Matching has been successfully applied to recover the depth information of a scene, but may perform variably when different matching cost algorithms are used. In this paper two matching cost computation algorithms, Census transform and an algorithm using a convolutional neural network, are tested for plant reconstruction based on Semi-Global Matching. High resolution close-range photogrammetric images from a handheld camera are used for the experiment. The disparity maps generated based on the two selected matching cost methods are comparable with acceptable quality, which shows the good performance of Census and the potential of neural networks to improve the dense matching.

Integrating probabilistic models of perception and interactive neural networks: a historical and tutorial review

PubMed Central

McClelland, James L.

2013-01-01

This article seeks to establish a rapprochement between explicitly Bayesian models of contextual effects in perception and neural network models of such effects, particularly the connectionist interactive activation (IA) model of perception. The article is in part an historical review and in part a tutorial, reviewing the probabilistic Bayesian approach to understanding perception and how it may be shaped by context, and also reviewing ideas about how such probabilistic computations may be carried out in neural networks, focusing on the role of context in interactive neural networks, in which both bottom-up and top-down signals affect the interpretation of sensory inputs. It is pointed out that connectionist units that use the logistic or softmax activation functions can exactly compute Bayesian posterior probabilities when the bias terms and connection weights affecting such units are set to the logarithms of appropriate probabilistic quantities. Bayesian concepts such the prior, likelihood, (joint and marginal) posterior, probability matching and maximizing, and calculating vs. sampling from the posterior are all reviewed and linked to neural network computations. Probabilistic and neural network models are explicitly linked to the concept of a probabilistic generative model that describes the relationship between the underlying target of perception (e.g., the word intended by a speaker or other source of sensory stimuli) and the sensory input that reaches the perceiver for use in inferring the underlying target. It is shown how a new version of the IA model called the multinomial interactive activation (MIA) model can sample correctly from the joint posterior of a proposed generative model for perception of letters in words, indicating that interactive processing is fully consistent with principled probabilistic computation. Ways in which these computations might be realized in real neural systems are also considered. PMID:23970868

Integrating probabilistic models of perception and interactive neural networks: a historical and tutorial review.

PubMed

McClelland, James L

2013-01-01

This article seeks to establish a rapprochement between explicitly Bayesian models of contextual effects in perception and neural network models of such effects, particularly the connectionist interactive activation (IA) model of perception. The article is in part an historical review and in part a tutorial, reviewing the probabilistic Bayesian approach to understanding perception and how it may be shaped by context, and also reviewing ideas about how such probabilistic computations may be carried out in neural networks, focusing on the role of context in interactive neural networks, in which both bottom-up and top-down signals affect the interpretation of sensory inputs. It is pointed out that connectionist units that use the logistic or softmax activation functions can exactly compute Bayesian posterior probabilities when the bias terms and connection weights affecting such units are set to the logarithms of appropriate probabilistic quantities. Bayesian concepts such the prior, likelihood, (joint and marginal) posterior, probability matching and maximizing, and calculating vs. sampling from the posterior are all reviewed and linked to neural network computations. Probabilistic and neural network models are explicitly linked to the concept of a probabilistic generative model that describes the relationship between the underlying target of perception (e.g., the word intended by a speaker or other source of sensory stimuli) and the sensory input that reaches the perceiver for use in inferring the underlying target. It is shown how a new version of the IA model called the multinomial interactive activation (MIA) model can sample correctly from the joint posterior of a proposed generative model for perception of letters in words, indicating that interactive processing is fully consistent with principled probabilistic computation. Ways in which these computations might be realized in real neural systems are also considered.

View-interpolation of sparsely sampled sinogram using convolutional neural network

NASA Astrophysics Data System (ADS)

Lee, Hoyeon; Lee, Jongha; Cho, Suengryong

2017-02-01

Spare-view sampling and its associated iterative image reconstruction in computed tomography have actively investigated. Sparse-view CT technique is a viable option to low-dose CT, particularly in cone-beam CT (CBCT) applications, with advanced iterative image reconstructions with varying degrees of image artifacts. One of the artifacts that may occur in sparse-view CT is the streak artifact in the reconstructed images. Another approach has been investigated for sparse-view CT imaging by use of the interpolation methods to fill in the missing view data and that reconstructs the image by an analytic reconstruction algorithm. In this study, we developed an interpolation method using convolutional neural network (CNN), which is one of the widely used deep-learning methods, to find missing projection data and compared its performances with the other interpolation techniques.

Data Structures in Natural Computing: Databases as Weak or Strong Anticipatory Systems

NASA Astrophysics Data System (ADS)

Rossiter, B. N.; Heather, M. A.

2004-08-01

Information systems anticipate the real world. Classical databases store, organise and search collections of data of that real world but only as weak anticipatory information systems. This is because of the reductionism and normalisation needed to map the structuralism of natural data on to idealised machines with von Neumann architectures consisting of fixed instructions. Category theory developed as a formalism to explore the theoretical concept of naturality shows that methods like sketches arising from graph theory as only non-natural models of naturality cannot capture real-world structures for strong anticipatory information systems. Databases need a schema of the natural world. Natural computing databases need the schema itself to be also natural. Natural computing methods including neural computers, evolutionary automata, molecular and nanocomputing and quantum computation have the potential to be strong. At present they are mainly at the stage of weak anticipatory systems.

Decoding of visual activity patterns from fMRI responses using multivariate pattern analyses and convolutional neural network.

PubMed

Zafar, Raheel; Kamel, Nidal; Naufal, Mohamad; Malik, Aamir Saeed; Dass, Sarat C; Ahmad, Rana Fayyaz; Abdullah, Jafri M; Reza, Faruque

2017-01-01

Decoding of human brain activity has always been a primary goal in neuroscience especially with functional magnetic resonance imaging (fMRI) data. In recent years, Convolutional neural network (CNN) has become a popular method for the extraction of features due to its higher accuracy, however it needs a lot of computation and training data. In this study, an algorithm is developed using Multivariate pattern analysis (MVPA) and modified CNN to decode the behavior of brain for different images with limited data set. Selection of significant features is an important part of fMRI data analysis, since it reduces the computational burden and improves the prediction performance; significant features are selected using t-test. MVPA uses machine learning algorithms to classify different brain states and helps in prediction during the task. General linear model (GLM) is used to find the unknown parameters of every individual voxel and the classification is done using multi-class support vector machine (SVM). MVPA-CNN based proposed algorithm is compared with region of interest (ROI) based method and MVPA based estimated values. The proposed method showed better overall accuracy (68.6%) compared to ROI (61.88%) and estimation values (64.17%).

Machine learning methods in chemoinformatics

PubMed Central

Mitchell, John B O

2014-01-01

Machine learning algorithms are generally developed in computer science or adjacent disciplines and find their way into chemical modeling by a process of diffusion. Though particular machine learning methods are popular in chemoinformatics and quantitative structure–activity relationships (QSAR), many others exist in the technical literature. This discussion is methods-based and focused on some algorithms that chemoinformatics researchers frequently use. It makes no claim to be exhaustive. We concentrate on methods for supervised learning, predicting the unknown property values of a test set of instances, usually molecules, based on the known values for a training set. Particularly relevant approaches include Artificial Neural Networks, Random Forest, Support Vector Machine, k-Nearest Neighbors and naïve Bayes classifiers. WIREs Comput Mol Sci 2014, 4:468–481. How to cite this article: WIREs Comput Mol Sci 2014, 4:468–481. doi:10.1002/wcms.1183 PMID:25285160

Computational intelligence approaches for pattern discovery in biological systems.

PubMed

Fogel, Gary B

2008-07-01

Biology, chemistry and medicine are faced by tremendous challenges caused by an overwhelming amount of data and the need for rapid interpretation. Computational intelligence (CI) approaches such as artificial neural networks, fuzzy systems and evolutionary computation are being used with increasing frequency to contend with this problem, in light of noise, non-linearity and temporal dynamics in the data. Such methods can be used to develop robust models of processes either on their own or in combination with standard statistical approaches. This is especially true for database mining, where modeling is a key component of scientific understanding. This review provides an introduction to current CI methods, their application to biological problems, and concludes with a commentary about the anticipated impact of these approaches in bioinformatics.

Application of artificial neural networks to gaming

NASA Astrophysics Data System (ADS)

Baba, Norio; Kita, Tomio; Oda, Kazuhiro

1995-04-01

Recently, neural network technology has been applied to various actual problems. It has succeeded in producing a large number of intelligent systems. In this article, we suggest that it could be applied to the field of gaming. In particular, we suggest that the neural network model could be used to mimic players' characters. Several computer simulation results using a computer gaming system which is a modified version of the COMMONS GAME confirm our idea.

Investigation of a Neural Network Implementation of a TCP Packet Anomaly Detection System

DTIC Science & Technology

2004-05-01

reconnatre les nouvelles variantes d’attaque. Les réseaux de neurones artificiels (ANN) ont les capacités d’apprendre à partir de schémas et de...Computational Intelligence Techniques in Intrusion Detection Systems. In IASTED International Conference on Neural Networks and Computational Intelligence , pp...Neural Network Training: Overfitting May be Harder than Expected. In Proceedings of the Fourteenth National Conference on Artificial Intelligence , AAAI-97

Program Helps Simulate Neural Networks

NASA Technical Reports Server (NTRS)

Villarreal, James; Mcintire, Gary

1993-01-01

Neural Network Environment on Transputer System (NNETS) computer program provides users high degree of flexibility in creating and manipulating wide variety of neural-network topologies at processing speeds not found in conventional computing environments. Supports back-propagation and back-propagation-related algorithms. Back-propagation algorithm used is implementation of Rumelhart's generalized delta rule. NNETS developed on INMOS Transputer(R). Predefines back-propagation network, Jordan network, and reinforcement network to assist users in learning and defining own networks. Also enables users to configure other neural-network paradigms from NNETS basic architecture. Small portion of software written in OCCAM(R) language.

Quantum neural networks: Current status and prospects for development

NASA Astrophysics Data System (ADS)

Altaisky, M. V.; Kaputkina, N. E.; Krylov, V. A.

2014-11-01

The idea of quantum artificial neural networks, first formulated in [34], unites the artificial neural network concept with the quantum computation paradigm. Quantum artificial neural networks were first systematically considered in the PhD thesis by T. Menneer (1998). Based on the works of Menneer and Narayanan [42, 43], Kouda, Matsui, and Nishimura [35, 36], Altaisky [2, 68], Zhou [67], and others, quantum-inspired learning algorithms for neural networks were developed, and are now used in various training programs and computer games [29, 30]. The first practically realizable scaled hardware-implemented model of the quantum artificial neural network is obtained by D-Wave Systems, Inc. [33]. It is a quantum Hopfield network implemented on the basis of superconducting quantum interference devices (SQUIDs). In this work we analyze possibilities and underlying principles of an alternative way to implement quantum neural networks on the basis of quantum dots. A possibility of using quantum neural network algorithms in automated control systems, associative memory devices, and in modeling biological and social networks is examined.

Benchmarking Spike-Based Visual Recognition: A Dataset and Evaluation

PubMed Central

Liu, Qian; Pineda-García, Garibaldi; Stromatias, Evangelos; Serrano-Gotarredona, Teresa; Furber, Steve B.

2016-01-01

Today, increasing attention is being paid to research into spike-based neural computation both to gain a better understanding of the brain and to explore biologically-inspired computation. Within this field, the primate visual pathway and its hierarchical organization have been extensively studied. Spiking Neural Networks (SNNs), inspired by the understanding of observed biological structure and function, have been successfully applied to visual recognition and classification tasks. In addition, implementations on neuromorphic hardware have enabled large-scale networks to run in (or even faster than) real time, making spike-based neural vision processing accessible on mobile robots. Neuromorphic sensors such as silicon retinas are able to feed such mobile systems with real-time visual stimuli. A new set of vision benchmarks for spike-based neural processing are now needed to measure progress quantitatively within this rapidly advancing field. We propose that a large dataset of spike-based visual stimuli is needed to provide meaningful comparisons between different systems, and a corresponding evaluation methodology is also required to measure the performance of SNN models and their hardware implementations. In this paper we first propose an initial NE (Neuromorphic Engineering) dataset based on standard computer vision benchmarksand that uses digits from the MNIST database. This dataset is compatible with the state of current research on spike-based image recognition. The corresponding spike trains are produced using a range of techniques: rate-based Poisson spike generation, rank order encoding, and recorded output from a silicon retina with both flashing and oscillating input stimuli. In addition, a complementary evaluation methodology is presented to assess both model-level and hardware-level performance. Finally, we demonstrate the use of the dataset and the evaluation methodology using two SNN models to validate the performance of the models and their hardware implementations. With this dataset we hope to (1) promote meaningful comparison between algorithms in the field of neural computation, (2) allow comparison with conventional image recognition methods, (3) provide an assessment of the state of the art in spike-based visual recognition, and (4) help researchers identify future directions and advance the field. PMID:27853419

Benchmarking Spike-Based Visual Recognition: A Dataset and Evaluation.

PubMed

Liu, Qian; Pineda-García, Garibaldi; Stromatias, Evangelos; Serrano-Gotarredona, Teresa; Furber, Steve B

2016-01-01

Today, increasing attention is being paid to research into spike-based neural computation both to gain a better understanding of the brain and to explore biologically-inspired computation. Within this field, the primate visual pathway and its hierarchical organization have been extensively studied. Spiking Neural Networks (SNNs), inspired by the understanding of observed biological structure and function, have been successfully applied to visual recognition and classification tasks. In addition, implementations on neuromorphic hardware have enabled large-scale networks to run in (or even faster than) real time, making spike-based neural vision processing accessible on mobile robots. Neuromorphic sensors such as silicon retinas are able to feed such mobile systems with real-time visual stimuli. A new set of vision benchmarks for spike-based neural processing are now needed to measure progress quantitatively within this rapidly advancing field. We propose that a large dataset of spike-based visual stimuli is needed to provide meaningful comparisons between different systems, and a corresponding evaluation methodology is also required to measure the performance of SNN models and their hardware implementations. In this paper we first propose an initial NE (Neuromorphic Engineering) dataset based on standard computer vision benchmarksand that uses digits from the MNIST database. This dataset is compatible with the state of current research on spike-based image recognition. The corresponding spike trains are produced using a range of techniques: rate-based Poisson spike generation, rank order encoding, and recorded output from a silicon retina with both flashing and oscillating input stimuli. In addition, a complementary evaluation methodology is presented to assess both model-level and hardware-level performance. Finally, we demonstrate the use of the dataset and the evaluation methodology using two SNN models to validate the performance of the models and their hardware implementations. With this dataset we hope to (1) promote meaningful comparison between algorithms in the field of neural computation, (2) allow comparison with conventional image recognition methods, (3) provide an assessment of the state of the art in spike-based visual recognition, and (4) help researchers identify future directions and advance the field.

Event-driven processing for hardware-efficient neural spike sorting

NASA Astrophysics Data System (ADS)

Liu, Yan; Pereira, João L.; Constandinou, Timothy G.

2018-02-01

Objective. The prospect of real-time and on-node spike sorting provides a genuine opportunity to push the envelope of large-scale integrated neural recording systems. In such systems the hardware resources, power requirements and data bandwidth increase linearly with channel count. Event-based (or data-driven) processing can provide here a new efficient means for hardware implementation that is completely activity dependant. In this work, we investigate using continuous-time level-crossing sampling for efficient data representation and subsequent spike processing. Approach. (1) We first compare signals (synthetic neural datasets) encoded with this technique against conventional sampling. (2) We then show how such a representation can be directly exploited by extracting simple time domain features from the bitstream to perform neural spike sorting. (3) The proposed method is implemented in a low power FPGA platform to demonstrate its hardware viability. Main results. It is observed that considerably lower data rates are achievable when using 7 bits or less to represent the signals, whilst maintaining the signal fidelity. Results obtained using both MATLAB and reconfigurable logic hardware (FPGA) indicate that feature extraction and spike sorting accuracies can be achieved with comparable or better accuracy than reference methods whilst also requiring relatively low hardware resources. Significance. By effectively exploiting continuous-time data representation, neural signal processing can be achieved in a completely event-driven manner, reducing both the required resources (memory, complexity) and computations (operations). This will see future large-scale neural systems integrating on-node processing in real-time hardware.

Neural Parallel Engine: A toolbox for massively parallel neural signal processing.

PubMed

Tam, Wing-Kin; Yang, Zhi

2018-05-01

Large-scale neural recordings provide detailed information on neuronal activities and can help elicit the underlying neural mechanisms of the brain. However, the computational burden is also formidable when we try to process the huge data stream generated by such recordings. In this study, we report the development of Neural Parallel Engine (NPE), a toolbox for massively parallel neural signal processing on graphical processing units (GPUs). It offers a selection of the most commonly used routines in neural signal processing such as spike detection and spike sorting, including advanced algorithms such as exponential-component-power-component (EC-PC) spike detection and binary pursuit spike sorting. We also propose a new method for detecting peaks in parallel through a parallel compact operation. Our toolbox is able to offer a 5× to 110× speedup compared with its CPU counterparts depending on the algorithms. A user-friendly MATLAB interface is provided to allow easy integration of the toolbox into existing workflows. Previous efforts on GPU neural signal processing only focus on a few rudimentary algorithms, are not well-optimized and often do not provide a user-friendly programming interface to fit into existing workflows. There is a strong need for a comprehensive toolbox for massively parallel neural signal processing. A new toolbox for massively parallel neural signal processing has been created. It can offer significant speedup in processing signals from large-scale recordings up to thousands of channels. Copyright © 2018 Elsevier B.V. All rights reserved.

Techniques for extracting single-trial activity patterns from large-scale neural recordings

PubMed Central

Churchland, Mark M; Yu, Byron M; Sahani, Maneesh; Shenoy, Krishna V

2008-01-01

Summary Large, chronically-implanted arrays of microelectrodes are an increasingly common tool for recording from primate cortex, and can provide extracellular recordings from many (order of 100) neurons. While the desire for cortically-based motor prostheses has helped drive their development, such arrays also offer great potential to advance basic neuroscience research. Here we discuss the utility of array recording for the study of neural dynamics. Neural activity often has dynamics beyond that driven directly by the stimulus. While governed by those dynamics, neural responses may nevertheless unfold differently for nominally identical trials, rendering many traditional analysis methods ineffective. We review recent studies – some employing simultaneous recording, some not – indicating that such variability is indeed present both during movement generation, and during the preceding premotor computations. In such cases, large-scale simultaneous recordings have the potential to provide an unprecedented view of neural dynamics at the level of single trials. However, this enterprise will depend not only on techniques for simultaneous recording, but also on the use and further development of analysis techniques that can appropriately reduce the dimensionality of the data, and allow visualization of single-trial neural behavior. PMID:18093826

Large-scale neural circuit mapping data analysis accelerated with the graphical processing unit (GPU).

PubMed

Shi, Yulin; Veidenbaum, Alexander V; Nicolau, Alex; Xu, Xiangmin

2015-01-15

Modern neuroscience research demands computing power. Neural circuit mapping studies such as those using laser scanning photostimulation (LSPS) produce large amounts of data and require intensive computation for post hoc processing and analysis. Here we report on the design and implementation of a cost-effective desktop computer system for accelerated experimental data processing with recent GPU computing technology. A new version of Matlab software with GPU enabled functions is used to develop programs that run on Nvidia GPUs to harness their parallel computing power. We evaluated both the central processing unit (CPU) and GPU-enabled computational performance of our system in benchmark testing and practical applications. The experimental results show that the GPU-CPU co-processing of simulated data and actual LSPS experimental data clearly outperformed the multi-core CPU with up to a 22× speedup, depending on computational tasks. Further, we present a comparison of numerical accuracy between GPU and CPU computation to verify the precision of GPU computation. In addition, we show how GPUs can be effectively adapted to improve the performance of commercial image processing software such as Adobe Photoshop. To our best knowledge, this is the first demonstration of GPU application in neural circuit mapping and electrophysiology-based data processing. Together, GPU enabled computation enhances our ability to process large-scale data sets derived from neural circuit mapping studies, allowing for increased processing speeds while retaining data precision. Copyright © 2014 Elsevier B.V. All rights reserved.

Inference in the brain: Statistics flowing in redundant population codes

PubMed Central

Pitkow, Xaq; Angelaki, Dora E

2017-01-01

It is widely believed that the brain performs approximate probabilistic inference to estimate causal variables in the world from ambiguous sensory data. To understand these computations, we need to analyze how information is represented and transformed by the actions of nonlinear recurrent neural networks. We propose that these probabilistic computations function by a message-passing algorithm operating at the level of redundant neural populations. To explain this framework, we review its underlying concepts, including graphical models, sufficient statistics, and message-passing, and then describe how these concepts could be implemented by recurrently connected probabilistic population codes. The relevant information flow in these networks will be most interpretable at the population level, particularly for redundant neural codes. We therefore outline a general approach to identify the essential features of a neural message-passing algorithm. Finally, we argue that to reveal the most important aspects of these neural computations, we must study large-scale activity patterns during moderately complex, naturalistic behaviors. PMID:28595050

Computing single step operators of logic programming in radial basis function neural networks

NASA Astrophysics Data System (ADS)

Hamadneh, Nawaf; Sathasivam, Saratha; Choon, Ong Hong

2014-07-01

Logic programming is the process that leads from an original formulation of a computing problem to executable programs. A normal logic program consists of a finite set of clauses. A valuation I of logic programming is a mapping from ground atoms to false or true. The single step operator of any logic programming is defined as a function (Tp:I→I). Logic programming is well-suited to building the artificial intelligence systems. In this study, we established a new technique to compute the single step operators of logic programming in the radial basis function neural networks. To do that, we proposed a new technique to generate the training data sets of single step operators. The training data sets are used to build the neural networks. We used the recurrent radial basis function neural networks to get to the steady state (the fixed point of the operators). To improve the performance of the neural networks, we used the particle swarm optimization algorithm to train the networks.

Retrieval of cloud properties from POLDER-3 data using the neural network approach

NASA Astrophysics Data System (ADS)

Di Noia, A.; Hasekamp, O. P.

2017-12-01

Satellite multi-angle spectroplarimetry is a useful technique for observing the microphysical properties of clouds and aerosols. Most of the algorithms for the retrieval of cloud and aerosol properties from satellite measurements require multiple calls to radiative transfer models, which make the retrieval computationally expensive. A traditional alternative to these schemes is represented by lookup-tables (LUTs), where the retrieval is performed by choosing, within a predefined database of combinations of clouds or aerosol properties, the combination that best fits the measurements. LUT retrievals are quicker than full-physics, iterative retrievals, but their accuracy is limited by the number of entries stored in the LUT. Another retrieval method capable of producing very quick retrievals without a big sacrifice in accuracy is the neural network method. Neural network methods are routinely applied to several types of satellite measurements, but their application to multi-angle spectropolarimetric data is still in its early stage, because of the difficulty of accounting for the angular variability of the measurements in the training process. We have recently developed a neural network scheme for the retrieval of cloud properties from POLDER-3 data. The neural network retrieval is trained using synthetic measurements performed for realistic combinations of cloud properties and measurement angles, and is able to process an entire orbit in about 20 seconds. Comparisons of the retrieved cloud properties with Moderate Resolution Imaging Spectroradiometer (MODIS) gridded products during one year show encouraging retrieval performance for cloud optical thickness and effective radius. A discussion of the setup of the neural network and of the validation results will be the main topic of our presentation.

Dimensionality-varied deep convolutional neural network for spectral-spatial classification of hyperspectral data

NASA Astrophysics Data System (ADS)

Qu, Haicheng; Liang, Xuejian; Liang, Shichao; Liu, Wanjun

2018-01-01

Many methods of hyperspectral image classification have been proposed recently, and the convolutional neural network (CNN) achieves outstanding performance. However, spectral-spatial classification of CNN requires an excessively large model, tremendous computations, and complex network, and CNN is generally unable to use the noisy bands caused by water-vapor absorption. A dimensionality-varied CNN (DV-CNN) is proposed to address these issues. There are four stages in DV-CNN and the dimensionalities of spectral-spatial feature maps vary with the stages. DV-CNN can reduce the computation and simplify the structure of the network. All feature maps are processed by more kernels in higher stages to extract more precise features. DV-CNN also improves the classification accuracy and enhances the robustness to water-vapor absorption bands. The experiments are performed on data sets of Indian Pines and Pavia University scene. The classification performance of DV-CNN is compared with state-of-the-art methods, which contain the variations of CNN, traditional, and other deep learning methods. The experiment of performance analysis about DV-CNN itself is also carried out. The experimental results demonstrate that DV-CNN outperforms state-of-the-art methods for spectral-spatial classification and it is also robust to water-vapor absorption bands. Moreover, reasonable parameters selection is effective to improve classification accuracy.

Artificial Neural Network for Probabilistic Feature Recognition in Liquid Chromatography Coupled to High-Resolution Mass Spectrometry.

PubMed

Woldegebriel, Michael; Derks, Eduard

2017-01-17

In this work, a novel probabilistic untargeted feature detection algorithm for liquid chromatography coupled to high-resolution mass spectrometry (LC-HRMS) using artificial neural network (ANN) is presented. The feature detection process is approached as a pattern recognition problem, and thus, ANN was utilized as an efficient feature recognition tool. Unlike most existing feature detection algorithms, with this approach, any suspected chromatographic profile (i.e., shape of a peak) can easily be incorporated by training the network, avoiding the need to perform computationally expensive regression methods with specific mathematical models. In addition, with this method, we have shown that the high-resolution raw data can be fully utilized without applying any arbitrary thresholds or data reduction, therefore improving the sensitivity of the method for compound identification purposes. Furthermore, opposed to existing deterministic (binary) approaches, this method rather estimates the probability of a feature being present/absent at a given point of interest, thus giving chance for all data points to be propagated down the data analysis pipeline, weighed with their probability. The algorithm was tested with data sets generated from spiked samples in forensic and food safety context and has shown promising results by detecting features for all compounds in a computationally reasonable time.

SuperSpike: Supervised Learning in Multilayer Spiking Neural Networks.

PubMed

Zenke, Friedemann; Ganguli, Surya

2018-06-01

A vast majority of computation in the brain is performed by spiking neural networks. Despite the ubiquity of such spiking, we currently lack an understanding of how biological spiking neural circuits learn and compute in vivo, as well as how we can instantiate such capabilities in artificial spiking circuits in silico. Here we revisit the problem of supervised learning in temporally coding multilayer spiking neural networks. First, by using a surrogate gradient approach, we derive SuperSpike, a nonlinear voltage-based three-factor learning rule capable of training multilayer networks of deterministic integrate-and-fire neurons to perform nonlinear computations on spatiotemporal spike patterns. Second, inspired by recent results on feedback alignment, we compare the performance of our learning rule under different credit assignment strategies for propagating output errors to hidden units. Specifically, we test uniform, symmetric, and random feedback, finding that simpler tasks can be solved with any type of feedback, while more complex tasks require symmetric feedback. In summary, our results open the door to obtaining a better scientific understanding of learning and computation in spiking neural networks by advancing our ability to train them to solve nonlinear problems involving transformations between different spatiotemporal spike time patterns.

A novel nonlinear adaptive filter using a pipelined second-order Volterra recurrent neural network.

PubMed

Zhao, Haiquan; Zhang, Jiashu

2009-12-01

To enhance the performance and overcome the heavy computational complexity of recurrent neural networks (RNN), a novel nonlinear adaptive filter based on a pipelined second-order Volterra recurrent neural network (PSOVRNN) is proposed in this paper. A modified real-time recurrent learning (RTRL) algorithm of the proposed filter is derived in much more detail. The PSOVRNN comprises of a number of simple small-scale second-order Volterra recurrent neural network (SOVRNN) modules. In contrast to the standard RNN, these modules of a PSOVRNN can be performed simultaneously in a pipelined parallelism fashion, which can lead to a significant improvement in its total computational efficiency. Moreover, since each module of the PSOVRNN is a SOVRNN in which nonlinearity is introduced by the recursive second-order Volterra (RSOV) expansion, its performance can be further improved. Computer simulations have demonstrated that the PSOVRNN performs better than the pipelined recurrent neural network (PRNN) and RNN for nonlinear colored signals prediction and nonlinear channel equalization. However, the superiority of the PSOVRNN over the PRNN is at the cost of increasing computational complexity due to the introduced nonlinear expansion of each module.

Novel adaptive neural control design for a constrained flexible air-breathing hypersonic vehicle based on actuator compensation

NASA Astrophysics Data System (ADS)

Bu, Xiangwei; Wu, Xiaoyan; He, Guangjun; Huang, Jiaqi

2016-03-01

This paper investigates the design of a novel adaptive neural controller for the longitudinal dynamics of a flexible air-breathing hypersonic vehicle with control input constraints. To reduce the complexity of controller design, the vehicle dynamics is decomposed into the velocity subsystem and the altitude subsystem, respectively. For each subsystem, only one neural network is utilized to approach the lumped unknown function. By employing a minimal-learning parameter method to estimate the norm of ideal weight vectors rather than their elements, there are only two adaptive parameters required for neural approximation. Thus, the computational burden is lower than the ones derived from neural back-stepping schemes. Specially, to deal with the control input constraints, additional systems are exploited to compensate the actuators. Lyapunov synthesis proves that all the closed-loop signals involved are uniformly ultimately bounded. Finally, simulation results show that the adopted compensation scheme can tackle actuator constraint effectively and moreover velocity and altitude can stably track their reference trajectories even when the physical limitations on control inputs are in effect.

Prediction of forced expiratory volume in pulmonary function test using radial basis neural networks and k-means clustering.

PubMed

Manoharan, Sujatha C; Ramakrishnan, Swaminathan

2009-10-01

In this work, prediction of forced expiratory volume in pulmonary function test, carried out using spirometry and neural networks is presented. The pulmonary function data were recorded from volunteers using commercial available flow volume spirometer in standard acquisition protocol. The Radial Basis Function neural networks were used to predict forced expiratory volume in 1 s (FEV1) from the recorded flow volume curves. The optimal centres of the hidden layer of radial basis function were determined by k-means clustering algorithm. The performance of the neural network model was evaluated by computing their prediction error statistics of average value, standard deviation, root mean square and their correlation with the true data for normal, restrictive and obstructive cases. Results show that the adopted neural networks are capable of predicting FEV1 in both normal and abnormal cases. Prediction accuracy was more in obstructive abnormality when compared to restrictive cases. It appears that this method of assessment is useful in diagnosing the pulmonary abnormalities with incomplete data and data with poor recording.

Neural Imaging Using Single-Photon Avalanche Diodes

PubMed Central

Karami, Mohammad Azim; Ansarian, Misagh

2017-01-01

Introduction: This paper analyses the ability of single-photon avalanche diodes (SPADs) for neural imaging. The current trend in the production of SPADs moves toward the minimum dark count rate (DCR) and maximum photon detection probability (PDP). Moreover, the jitter response which is the main measurement characteristic for the timing uncertainty is progressing. Methods: The neural imaging process using SPADs can be performed by means of florescence lifetime imaging (FLIM), time correlated single-photon counting (TCSPC), positron emission tomography (PET), and single-photon emission computed tomography (SPECT). Results: This trend will result in more precise neural imaging cameras. While achieving low DCR SPADs is difficult in deep submicron technologies because of using higher doping profiles, higher PDPs are reported in green and blue part of light. Furthermore, the number of pixels integrated in the same chip is increasing with the technology progress which can result in the higher resolution of imaging. Conclusion: This study proposes implemented SPADs in Deep-submicron technologies to be used in neural imaging cameras, due to the small size pixels and higher timing accuracies. PMID:28446946

Mamdani Fuzzy System for Indoor Autonomous Mobile Robot

NASA Astrophysics Data System (ADS)

Khan, M. K. A. Ahamed; Rashid, Razif; Elamvazuthi, I.

2011-06-01

Several control algorithms for autonomous mobile robot navigation have been proposed in the literature. Recently, the employment of non-analytical methods of computing such as fuzzy logic, evolutionary computation, and neural networks has demonstrated the utility and potential of these paradigms for intelligent control of mobile robot navigation. In this paper, Mamdani fuzzy system for an autonomous mobile robot is developed. The paper begins with the discussion on the conventional controller and then followed by the description of fuzzy logic controller in detail.

A Procedure for Measuring Latencies in Brain-Computer Interfaces

PubMed Central

Wilson, J. Adam; Mellinger, Jürgen; Schalk, Gerwin; Williams, Justin

2011-01-01

Brain-computer interface (BCI) systems must process neural signals with consistent timing in order to support adequate system performance. Thus, it is important to have the capability to determine whether a particular BCI configuration (i.e., hardware, software) provides adequate timing performance for a particular experiment. This report presents a method of measuring and quantifying different aspects of system timing in several typical BCI experiments across a range of settings, and presents comprehensive measures of expected overall system latency for each experimental configuration. PMID:20403781

Rapid Human-Computer Interactive Conceptual Design of Mobile and Manipulative Robot Systems

DTIC Science & Technology

2015-05-19

algorithm based on Age-Fitness Pareto Optimization (AFPO) ([9]) with an additional user prefer- ence objective and a neural network-based user model, we...greater than 40, which is about 5 times further than any robot traveled in our experiments. 6 3.3 Methods The algorithm uses a client -server computational...architecture. The client here is an interactive pro- gram which takes a pair of controllers as input, simulates4 two copies of the robot with

Global neural pattern similarity as a common basis for categorization and recognition memory.

PubMed

Davis, Tyler; Xue, Gui; Love, Bradley C; Preston, Alison R; Poldrack, Russell A

2014-05-28

Familiarity, or memory strength, is a central construct in models of cognition. In previous categorization and long-term memory research, correlations have been found between psychological measures of memory strength and activation in the medial temporal lobes (MTLs), which suggests a common neural locus for memory strength. However, activation alone is insufficient for determining whether the same mechanisms underlie neural function across domains. Guided by mathematical models of categorization and long-term memory, we develop a theory and a method to test whether memory strength arises from the global similarity among neural representations. In human subjects, we find significant correlations between global similarity among activation patterns in the MTLs and both subsequent memory confidence in a recognition memory task and model-based measures of memory strength in a category learning task. Our work bridges formal cognitive theories and neuroscientific models by illustrating that the same global similarity computations underlie processing in multiple cognitive domains. Moreover, by establishing a link between neural similarity and psychological memory strength, our findings suggest that there may be an isomorphism between psychological and neural representational spaces that can be exploited to test cognitive theories at both the neural and behavioral levels. Copyright © 2014 the authors 0270-6474/14/347472-13$15.00/0.

Medical image analysis with artificial neural networks.

PubMed

Jiang, J; Trundle, P; Ren, J

2010-12-01

Given that neural networks have been widely reported in the research community of medical imaging, we provide a focused literature survey on recent neural network developments in computer-aided diagnosis, medical image segmentation and edge detection towards visual content analysis, and medical image registration for its pre-processing and post-processing, with the aims of increasing awareness of how neural networks can be applied to these areas and to provide a foundation for further research and practical development. Representative techniques and algorithms are explained in detail to provide inspiring examples illustrating: (i) how a known neural network with fixed structure and training procedure could be applied to resolve a medical imaging problem; (ii) how medical images could be analysed, processed, and characterised by neural networks; and (iii) how neural networks could be expanded further to resolve problems relevant to medical imaging. In the concluding section, a highlight of comparisons among many neural network applications is included to provide a global view on computational intelligence with neural networks in medical imaging. Copyright © 2010 Elsevier Ltd. All rights reserved.

Application of a soft computing technique in predicting the percentage of shear force carried by walls in a rectangular channel with non-homogeneous roughness.

PubMed

Khozani, Zohreh Sheikh; Bonakdari, Hossein; Zaji, Amir Hossein

2016-01-01

Two new soft computing models, namely genetic programming (GP) and genetic artificial algorithm (GAA) neural network (a combination of modified genetic algorithm and artificial neural network methods) were developed in order to predict the percentage of shear force in a rectangular channel with non-homogeneous roughness. The ability of these methods to estimate the percentage of shear force was investigated. Moreover, the independent parameters' effectiveness in predicting the percentage of shear force was determined using sensitivity analysis. According to the results, the GP model demonstrated superior performance to the GAA model. A comparison was also made between the GP program determined as the best model and five equations obtained in prior research. The GP model with the lowest error values (root mean square error ((RMSE) of 0.0515) had the best function compared with the other equations presented for rough and smooth channels as well as smooth ducts. The equation proposed for rectangular channels with rough boundaries (RMSE of 0.0642) outperformed the prior equations for smooth boundaries.

An alternative respiratory sounds classification system utilizing artificial neural networks.

PubMed

Oweis, Rami J; Abdulhay, Enas W; Khayal, Amer; Awad, Areen

2015-01-01

Computerized lung sound analysis involves recording lung sound via an electronic device, followed by computer analysis and classification based on specific signal characteristics as non-linearity and nonstationarity caused by air turbulence. An automatic analysis is necessary to avoid dependence on expert skills. This work revolves around exploiting autocorrelation in the feature extraction stage. All process stages were implemented in MATLAB. The classification process was performed comparatively using both artificial neural networks (ANNs) and adaptive neuro-fuzzy inference systems (ANFIS) toolboxes. The methods have been applied to 10 different respiratory sounds for classification. The ANN was superior to the ANFIS system and returned superior performance parameters. Its accuracy, specificity, and sensitivity were 98.6%, 100%, and 97.8%, respectively. The obtained parameters showed superiority to many recent approaches. The promising proposed method is an efficient fast tool for the intended purpose as manifested in the performance parameters, specifically, accuracy, specificity, and sensitivity. Furthermore, it may be added that utilizing the autocorrelation function in the feature extraction in such applications results in enhanced performance and avoids undesired computation complexities compared to other techniques.

Real-time simulation of a spiking neural network model of the basal ganglia circuitry using general purpose computing on graphics processing units.

PubMed

Igarashi, Jun; Shouno, Osamu; Fukai, Tomoki; Tsujino, Hiroshi

2011-11-01

Real-time simulation of a biologically realistic spiking neural network is necessary for evaluation of its capacity to interact with real environments. However, the real-time simulation of such a neural network is difficult due to its high computational costs that arise from two factors: (1) vast network size and (2) the complicated dynamics of biologically realistic neurons. In order to address these problems, mainly the latter, we chose to use general purpose computing on graphics processing units (GPGPUs) for simulation of such a neural network, taking advantage of the powerful computational capability of a graphics processing unit (GPU). As a target for real-time simulation, we used a model of the basal ganglia that has been developed according to electrophysiological and anatomical knowledge. The model consists of heterogeneous populations of 370 spiking model neurons, including computationally heavy conductance-based models, connected by 11,002 synapses. Simulation of the model has not yet been performed in real-time using a general computing server. By parallelization of the model on the NVIDIA Geforce GTX 280 GPU in data-parallel and task-parallel fashion, faster-than-real-time simulation was robustly realized with only one-third of the GPU's total computational resources. Furthermore, we used the GPU's full computational resources to perform faster-than-real-time simulation of three instances of the basal ganglia model; these instances consisted of 1100 neurons and 33,006 synapses and were synchronized at each calculation step. Finally, we developed software for simultaneous visualization of faster-than-real-time simulation output. These results suggest the potential power of GPGPU techniques in real-time simulation of realistic neural networks. Copyright © 2011 Elsevier Ltd. All rights reserved.

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.

Short-time windowed covariance: A metric for identifying non-stationary, event-related covariant cortical sites

PubMed Central

Blakely, Timothy; Ojemann, Jeffrey G.; Rao, Rajesh P.N.

2014-01-01

Background Electrocorticography (ECoG) signals can provide high spatio-temporal resolution and high signal to noise ratio recordings of local neural activity from the surface of the brain. Previous studies have shown that broad-band, spatially focal, high-frequency increases in ECoG signals are highly correlated with movement and other cognitive tasks and can be volitionally modulated. However, significant additional information may be present in inter-electrode interactions, but adding additional higher order inter-electrode interactions can be impractical from a computational aspect, if not impossible. New method In this paper we present a new method of calculating high frequency interactions between electrodes called Short-Time Windowed Covariance (STWC) that builds on mathematical techniques currently used in neural signal analysis, along with an implementation that accelerates the algorithm by orders of magnitude by leveraging commodity, off-the-shelf graphics processing unit (GPU) hardware. Results Using the hardware-accelerated implementation of STWC, we identify many types of event-related inter-electrode interactions from human ECoG recordings on global and local scales that have not been identified by previous methods. Unique temporal patterns are observed for digit flexion in both low- (10 mm spacing) and high-resolution (3 mm spacing) electrode arrays. Comparison with existing methods Covariance is a commonly used metric for identifying correlated signals, but the standard covariance calculations do not allow for temporally varying covariance. In contrast STWC allows and identifies event-driven changes in covariance without identifying spurious noise correlations. Conclusions: STWC can be used to identify event-related neural interactions whose high computational load is well suited to GPU capabilities. PMID:24211499

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).

Neural constraints on learning.

PubMed

Sadtler, Patrick T; Quick, Kristin M; Golub, Matthew D; Chase, Steven M; Ryu, Stephen I; Tyler-Kabara, Elizabeth C; Yu, Byron M; Batista, Aaron P

2014-08-28

Learning, whether motor, sensory or cognitive, requires networks of neurons to generate new activity patterns. As some behaviours are easier to learn than others, we asked if some neural activity patterns are easier to generate than others. Here we investigate whether an existing network constrains the patterns that a subset of its neurons is capable of exhibiting, and if so, what principles define this constraint. We employed a closed-loop intracortical brain-computer interface learning paradigm in which Rhesus macaques (Macaca mulatta) controlled a computer cursor by modulating neural activity patterns in the primary motor cortex. Using the brain-computer interface paradigm, we could specify and alter how neural activity mapped to cursor velocity. At the start of each session, we observed the characteristic activity patterns of the recorded neural population. The activity of a neural population can be represented in a high-dimensional space (termed the neural space), wherein each dimension corresponds to the activity of one neuron. These characteristic activity patterns comprise a low-dimensional subspace (termed the intrinsic manifold) within the neural space. The intrinsic manifold presumably reflects constraints imposed by the underlying neural circuitry. Here we show that the animals could readily learn to proficiently control the cursor using neural activity patterns that were within the intrinsic manifold. However, animals were less able to learn to proficiently control the cursor using activity patterns that were outside of the intrinsic manifold. These results suggest that the existing structure of a network can shape learning. On a timescale of hours, it seems to be difficult to learn to generate neural activity patterns that are not consistent with the existing network structure. These findings offer a network-level explanation for the observation that we are more readily able to learn new skills when they are related to the skills that we already possess.

Spatial-Temporal Reasoning Applications of Computational Intelligence in the Game of Go and Computer Networks

DTIC Science & Technology

2012-01-01

dimensionality, Tesauro used a backpropagation- based , three-layer neural network and implemented the outcome from a self-play game as the reinforcement signal...a school of fish, flock of birds, and colony of ants. Our literature review reveals that no one has used PSO to train the neural network ...trained with a variant of PSO called cellular PSO (CPSO). CSRN is a supervised learning neural network (SLNN). The proposed algorithm for the

Hybrid computing using a neural network with dynamic external memory.

PubMed

Graves, Alex; Wayne, Greg; Reynolds, Malcolm; Harley, Tim; Danihelka, Ivo; Grabska-Barwińska, Agnieszka; Colmenarejo, Sergio Gómez; Grefenstette, Edward; Ramalho, Tiago; Agapiou, John; Badia, Adrià Puigdomènech; Hermann, Karl Moritz; Zwols, Yori; Ostrovski, Georg; Cain, Adam; King, Helen; Summerfield, Christopher; Blunsom, Phil; Kavukcuoglu, Koray; Hassabis, Demis

2016-10-27

Artificial neural networks are remarkably adept at sensory processing, sequence learning and reinforcement learning, but are limited in their ability to represent variables and data structures and to store data over long timescales, owing to the lack of an external memory. Here we introduce a machine learning model called a differentiable neural computer (DNC), which consists of a neural network that can read from and write to an external memory matrix, analogous to the random-access memory in a conventional computer. Like a conventional computer, it can use its memory to represent and manipulate complex data structures, but, like a neural network, it can learn to do so from data. When trained with supervised learning, we demonstrate that a DNC can successfully answer synthetic questions designed to emulate reasoning and inference problems in natural language. We show that it can learn tasks such as finding the shortest path between specified points and inferring the missing links in randomly generated graphs, and then generalize these tasks to specific graphs such as transport networks and family trees. When trained with reinforcement learning, a DNC can complete a moving blocks puzzle in which changing goals are specified by sequences of symbols. Taken together, our results demonstrate that DNCs have the capacity to solve complex, structured tasks that are inaccessible to neural networks without external read-write memory.

Science & Technology Review June 2012

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

Poyneer, L A

2012-04-20

This month's issue has the following articles: (1) A New Era in Climate System Analysis - Commentary by William H. Goldstein; (2) Seeking Clues to Climate Change - By comparing past climate records with results from computer simulations, Livermore scientists can better understand why Earth's climate has changed and how it might change in the future; (3) Finding and Fixing a Supercomputer's Faults - Livermore experts have developed innovative methods to detect hardware faults in supercomputers and help applications recover from errors that do occur; (4) Targeting Ignition - Enhancements to the cryogenic targets for National Ignition Facility experiments aremore » furthering work to achieve fusion ignition with energy gain; (5) Neural Implants Come of Age - A new generation of fully implantable, biocompatible neural prosthetics offers hope to patients with neurological impairment; and (6) Incubator Busy Growing Energy Technologies - Six collaborations with industrial partners are using the Laboratory's high-performance computing resources to find solutions to urgent energy-related problems.« less

Dynamic labelling of neural connections in multiple colours by trans-synaptic fluorescence complementation

PubMed Central

Macpherson, Lindsey J.; Zaharieva, Emanuela E.; Kearney, Patrick J.; Alpert, Michael H.; Lin, Tzu-Yang; Turan, Zeynep; Lee, Chi-Hon; Gallio, Marco

2015-01-01

Determining the pattern of activity of individual connections within a neural circuit could provide insights into the computational processes that underlie brain function. Here, we develop new strategies to label active synapses by trans-synaptic fluorescence complementation in Drosophila. First, we demonstrate that a synaptobrevin-GRASP chimera functions as a powerful activity-dependent marker for synapses in vivo. Next, we create cyan and yellow variants, achieving activity-dependent, multi-colour fluorescence reconstitution across synapses (X-RASP). Our system allows for the first time retrospective labelling of synapses (rather than whole neurons) based on their activity, in multiple colours, in the same animal. As individual synapses often act as computational units in the brain, our method will promote the design of experiments that are not possible using existing techniques. Moreover, our strategies are easily adaptable to circuit mapping in any genetic system. PMID:26635273

Rapid automated classification of anesthetic depth levels using GPU based parallelization of neural networks.

PubMed

Peker, Musa; Şen, Baha; Gürüler, Hüseyin

2015-02-01

The effect of anesthesia on the patient is referred to as depth of anesthesia. Rapid classification of appropriate depth level of anesthesia is a matter of great importance in surgical operations. Similarly, accelerating classification algorithms is important for the rapid solution of problems in the field of biomedical signal processing. However numerous, time-consuming mathematical operations are required when training and testing stages of the classification algorithms, especially in neural networks. In this study, to accelerate the process, parallel programming and computing platform (Nvidia CUDA) facilitates dramatic increases in computing performance by harnessing the power of the graphics processing unit (GPU) was utilized. The system was employed to detect anesthetic depth level on related electroencephalogram (EEG) data set. This dataset is rather complex and large. Moreover, the achieving more anesthetic levels with rapid response is critical in anesthesia. The proposed parallelization method yielded high accurate classification results in a faster time.

Neural system prediction and identification challenge.

PubMed

Vlachos, Ioannis; Zaytsev, Yury V; Spreizer, Sebastian; Aertsen, Ad; Kumar, Arvind

2013-01-01

Can we infer the function of a biological neural network (BNN) if we know the connectivity and activity of all its constituent neurons?This question is at the core of neuroscience and, accordingly, various methods have been developed to record the activity and connectivity of as many neurons as possible. Surprisingly, there is no theoretical or computational demonstration that neuronal activity and connectivity are indeed sufficient to infer the function of a BNN. Therefore, we pose the Neural Systems Identification and Prediction Challenge (nuSPIC). We provide the connectivity and activity of all neurons and invite participants (1) to infer the functions implemented (hard-wired) in spiking neural networks (SNNs) by stimulating and recording the activity of neurons and, (2) to implement predefined mathematical/biological functions using SNNs. The nuSPICs can be accessed via a web-interface to the NEST simulator and the user is not required to know any specific programming language. Furthermore, the nuSPICs can be used as a teaching tool. Finally, nuSPICs use the crowd-sourcing model to address scientific issues. With this computational approach we aim to identify which functions can be inferred by systematic recordings of neuronal activity and connectivity. In addition, nuSPICs will help the design and application of new experimental paradigms based on the structure of the SNN and the presumed function which is to be discovered.

Neural system prediction and identification challenge

PubMed Central

Vlachos, Ioannis; Zaytsev, Yury V.; Spreizer, Sebastian; Aertsen, Ad; Kumar, Arvind

2013-01-01

Can we infer the function of a biological neural network (BNN) if we know the connectivity and activity of all its constituent neurons?This question is at the core of neuroscience and, accordingly, various methods have been developed to record the activity and connectivity of as many neurons as possible. Surprisingly, there is no theoretical or computational demonstration that neuronal activity and connectivity are indeed sufficient to infer the function of a BNN. Therefore, we pose the Neural Systems Identification and Prediction Challenge (nuSPIC). We provide the connectivity and activity of all neurons and invite participants (1) to infer the functions implemented (hard-wired) in spiking neural networks (SNNs) by stimulating and recording the activity of neurons and, (2) to implement predefined mathematical/biological functions using SNNs. The nuSPICs can be accessed via a web-interface to the NEST simulator and the user is not required to know any specific programming language. Furthermore, the nuSPICs can be used as a teaching tool. Finally, nuSPICs use the crowd-sourcing model to address scientific issues. With this computational approach we aim to identify which functions can be inferred by systematic recordings of neuronal activity and connectivity. In addition, nuSPICs will help the design and application of new experimental paradigms based on the structure of the SNN and the presumed function which is to be discovered. PMID:24399966

FPGA implementation of a biological neural network based on the Hodgkin-Huxley neuron model.

PubMed

Yaghini Bonabi, Safa; Asgharian, Hassan; Safari, Saeed; Nili Ahmadabadi, Majid

2014-01-01

A set of techniques for efficient implementation of Hodgkin-Huxley-based (H-H) model of a neural network on FPGA (Field Programmable Gate Array) is presented. The central implementation challenge is H-H model complexity that puts limits on the network size and on the execution speed. However, basics of the original model cannot be compromised when effect of synaptic specifications on the network behavior is the subject of study. To solve the problem, we used computational techniques such as CORDIC (Coordinate Rotation Digital Computer) algorithm and step-by-step integration in the implementation of arithmetic circuits. In addition, we employed different techniques such as sharing resources to preserve the details of model as well as increasing the network size in addition to keeping the network execution speed close to real time while having high precision. Implementation of a two mini-columns network with 120/30 excitatory/inhibitory neurons is provided to investigate the characteristic of our method in practice. The implementation techniques provide an opportunity to construct large FPGA-based network models to investigate the effect of different neurophysiological mechanisms, like voltage-gated channels and synaptic activities, on the behavior of a neural network in an appropriate execution time. Additional to inherent properties of FPGA, like parallelism and re-configurability, our approach makes the FPGA-based system a proper candidate for study on neural control of cognitive robots and systems as well.

Formulation and Implementation of Nonlinear Integral Equations to Model Neural Dynamics Within the Vertebrate Retina.

PubMed

Eshraghian, Jason K; Baek, Seungbum; Kim, Jun-Ho; Iannella, Nicolangelo; Cho, Kyoungrok; Goo, Yong Sook; Iu, Herbert H C; Kang, Sung-Mo; Eshraghian, Kamran

2018-02-13

Existing computational models of the retina often compromise between the biophysical accuracy and a hardware-adaptable methodology of implementation. When compared to the current modes of vision restoration, algorithmic models often contain a greater correlation between stimuli and the affected neural network, but lack physical hardware practicality. Thus, if the present processing methods are adapted to complement very-large-scale circuit design techniques, it is anticipated that it will engender a more feasible approach to the physical construction of the artificial retina. The computational model presented in this research serves to provide a fast and accurate predictive model of the retina, a deeper understanding of neural responses to visual stimulation, and an architecture that can realistically be transformed into a hardware device. Traditionally, implicit (or semi-implicit) ordinary differential equations (OES) have been used for optimal speed and accuracy. We present a novel approach that requires the effective integration of different dynamical time scales within a unified framework of neural responses, where the rod, cone, amacrine, bipolar, and ganglion cells correspond to the implemented pathways. Furthermore, we show that adopting numerical integration can both accelerate retinal pathway simulations by more than 50% when compared with traditional ODE solvers in some cases, and prove to be a more realizable solution for the hardware implementation of predictive retinal models.

Forecasting sea cliff retreat in Southern California using process-based models and artificial neural networks

NASA Astrophysics Data System (ADS)

Limber, P. W.; Barnard, P.; Erikson, L. H.

2016-02-01

Modeling coastal geomorphic change over multi-decadal time and regional spatial scales (i.e. >20 km alongshore) is in high demand due to rising global sea levels and heavily populated coastal zones, but is challenging for several reasons: adequate geomorphic and oceanographic data often does not exist over the entire study area or time period; models can be too computationally expensive; and model uncertainty is high. In the absence of rich datasets and unlimited computer processing power, researchers are forced to leverage existing data, however sparse, and find analytical methods that minimize computation time without sacrificing (too much) model reliability. Machine learning techniques, such as artificial neural networks, can assimilate and efficiently extrapolate geomorphic model behavior over large areas. They can also facilitate ensemble model forecasts over a broad range of parameter space, which is useful when a paucity of observational data inhibits the constraint of model parameters. Here, we assimilate the behavior of two established process-based sea cliff erosion and retreat models into a neural network to forecast the impacts of sea level rise on sea cliff retreat in Southern California ( 400 km) through the 21st century. Using inputs such as historical cliff retreat rates, mean wave power, and whether or not a beach is present, the neural network independently reproduces modeled sea cliff retreat as a function of sea level rise with a high degree of confidence (R2 > 0.9, mean squared error < 0.1 m yr-1). Results will continuously improve as more model scenarios are assimilated into the neural network, and more field data (i.e., cliff composition and rock hardness) becomes available to tune the cliff retreat models. Preliminary results suggest that sea level rise rates of 2 to 20 mm yr-1 during the next century could accelerate historical cliff retreat rates in Southern California by an average of 0.10 - 0.56 m yr-1.

Encoder-Decoder Optimization for Brain-Computer Interfaces

PubMed Central

Merel, Josh; Pianto, Donald M.; Cunningham, John P.; Paninski, Liam

2015-01-01

Neuroprosthetic brain-computer interfaces are systems that decode neural activity into useful control signals for effectors, such as a cursor on a computer screen. It has long been recognized that both the user and decoding system can adapt to increase the accuracy of the end effector. Co-adaptation is the process whereby a user learns to control the system in conjunction with the decoder adapting to learn the user's neural patterns. We provide a mathematical framework for co-adaptation and relate co-adaptation to the joint optimization of the user's control scheme ("encoding model") and the decoding algorithm's parameters. When the assumptions of that framework are respected, co-adaptation cannot yield better performance than that obtainable by an optimal initial choice of fixed decoder, coupled with optimal user learning. For a specific case, we provide numerical methods to obtain such an optimized decoder. We demonstrate our approach in a model brain-computer interface system using an online prosthesis simulator, a simple human-in-the-loop pyschophysics setup which provides a non-invasive simulation of the BCI setting. These experiments support two claims: that users can learn encoders matched to fixed, optimal decoders and that, once learned, our approach yields expected performance advantages. PMID:26029919

Encoder-decoder optimization for brain-computer interfaces.

PubMed

Merel, Josh; Pianto, Donald M; Cunningham, John P; Paninski, Liam

2015-06-01

Neuroprosthetic brain-computer interfaces are systems that decode neural activity into useful control signals for effectors, such as a cursor on a computer screen. It has long been recognized that both the user and decoding system can adapt to increase the accuracy of the end effector. Co-adaptation is the process whereby a user learns to control the system in conjunction with the decoder adapting to learn the user's neural patterns. We provide a mathematical framework for co-adaptation and relate co-adaptation to the joint optimization of the user's control scheme ("encoding model") and the decoding algorithm's parameters. When the assumptions of that framework are respected, co-adaptation cannot yield better performance than that obtainable by an optimal initial choice of fixed decoder, coupled with optimal user learning. For a specific case, we provide numerical methods to obtain such an optimized decoder. We demonstrate our approach in a model brain-computer interface system using an online prosthesis simulator, a simple human-in-the-loop pyschophysics setup which provides a non-invasive simulation of the BCI setting. These experiments support two claims: that users can learn encoders matched to fixed, optimal decoders and that, once learned, our approach yields expected performance advantages.

Evaluation of MTANNs for eliminating false-positive with different computer aided pulmonary nodules detection software.

PubMed

Shi, Zhenghao; Ma, Jiejue; Feng, Yaning; He, Lifeng; Suzuki, Kenji

2015-11-01

MTANN (Massive Training Artificial Neural Network) is a promising tool, which applied to eliminate false-positive for thoracic CT in recent years. In order to evaluate whether this method is feasible to eliminate false-positive of different CAD schemes, especially, when it is applied to commercial CAD software, this paper evaluate the performance of the method for eliminating false-positives produced by three different versions of commercial CAD software for lung nodules detection in chest radiographs. Experimental results demonstrate that the approach is useful in reducing FPs for different computer aided lung nodules detection software in chest radiographs.

Reprint of “Non-causal spike filtering improves decoding of movement intention for intracortical BCIs”☆

PubMed Central

Masse, Nicolas Y.; Jarosiewicz, Beata; Simeral, John D.; Bacher, Daniel; Stavisky, Sergey D.; Cash, Sydney S.; Oakley, Erin M.; Berhanu, Etsub; Eskandar, Emad; Friehs, Gerhard; Hochberg, Leigh R.; Donoghue, John P.

2015-01-01

Background Multiple types of neural signals are available for controlling assistive devices through brain–computer interfaces (BCIs). Intracortically recorded spiking neural signals are attractive for BCIs because they can in principle provide greater fidelity of encoded information compared to electrocorticographic (ECoG) signals and electroencephalograms (EEGs). Recent reports show that the information content of these spiking neural signals can be reliably extracted simply by causally band-pass filtering the recorded extracellular voltage signals and then applying a spike detection threshold, without relying on “sorting” action potentials. New method We show that replacing the causal filter with an equivalent non-causal filter increases the information content extracted from the extracellular spiking signal and improves decoding of intended movement direction. This method can be used for real-time BCI applications by using a 4 ms lag between recording and filtering neural signals. Results Across 18 sessions from two people with tetraplegia enrolled in the BrainGate2 pilot clinical trial, we found that threshold crossing events extracted using this non-causal filtering method were significantly more informative of each participant’s intended cursor kinematics compared to threshold crossing events derived from causally filtered signals. This new method decreased the mean angular error between the intended and decoded cursor direction by 9.7° for participant S3, who was implanted 5.4 years prior to this study, and by 3.5° for participant T2, who was implanted 3 months prior to this study. PMID:25681017

A Pruning Neural Network Model in Credit Classification Analysis

PubMed Central

Tang, Yajiao; Ji, Junkai; Dai, Hongwei; Yu, Yang; Todo, Yuki

2018-01-01

Nowadays, credit classification models are widely applied because they can help financial decision-makers to handle credit classification issues. Among them, artificial neural networks (ANNs) have been widely accepted as the convincing methods in the credit industry. In this paper, we propose a pruning neural network (PNN) and apply it to solve credit classification problem by adopting the well-known Australian and Japanese credit datasets. The model is inspired by synaptic nonlinearity of a dendritic tree in a biological neural model. And it is trained by an error back-propagation algorithm. The model is capable of realizing a neuronal pruning function by removing the superfluous synapses and useless dendrites and forms a tidy dendritic morphology at the end of learning. Furthermore, we utilize logic circuits (LCs) to simulate the dendritic structures successfully which makes PNN be implemented on the hardware effectively. The statistical results of our experiments have verified that PNN obtains superior performance in comparison with other classical algorithms in terms of accuracy and computational efficiency. PMID:29606961

Community-based benchmarking improves spike rate inference from two-photon calcium imaging data.

PubMed

Berens, Philipp; Freeman, Jeremy; Deneux, Thomas; Chenkov, Nikolay; McColgan, Thomas; Speiser, Artur; Macke, Jakob H; Turaga, Srinivas C; Mineault, Patrick; Rupprecht, Peter; Gerhard, Stephan; Friedrich, Rainer W; Friedrich, Johannes; Paninski, Liam; Pachitariu, Marius; Harris, Kenneth D; Bolte, Ben; Machado, Timothy A; Ringach, Dario; Stone, Jasmine; Rogerson, Luke E; Sofroniew, Nicolas J; Reimer, Jacob; Froudarakis, Emmanouil; Euler, Thomas; Román Rosón, Miroslav; Theis, Lucas; Tolias, Andreas S; Bethge, Matthias

2018-05-01

In recent years, two-photon calcium imaging has become a standard tool to probe the function of neural circuits and to study computations in neuronal populations. However, the acquired signal is only an indirect measurement of neural activity due to the comparatively slow dynamics of fluorescent calcium indicators. Different algorithms for estimating spike rates from noisy calcium measurements have been proposed in the past, but it is an open question how far performance can be improved. Here, we report the results of the spikefinder challenge, launched to catalyze the development of new spike rate inference algorithms through crowd-sourcing. We present ten of the submitted algorithms which show improved performance compared to previously evaluated methods. Interestingly, the top-performing algorithms are based on a wide range of principles from deep neural networks to generative models, yet provide highly correlated estimates of the neural activity. The competition shows that benchmark challenges can drive algorithmic developments in neuroscience.

Biologically plausible learning in recurrent neural networks reproduces neural dynamics observed during cognitive tasks

PubMed Central

Miconi, Thomas

2017-01-01

Neural activity during cognitive tasks exhibits complex dynamics that flexibly encode task-relevant variables. Chaotic recurrent networks, which spontaneously generate rich dynamics, have been proposed as a model of cortical computation during cognitive tasks. However, existing methods for training these networks are either biologically implausible, and/or require a continuous, real-time error signal to guide learning. Here we show that a biologically plausible learning rule can train such recurrent networks, guided solely by delayed, phasic rewards at the end of each trial. Networks endowed with this learning rule can successfully learn nontrivial tasks requiring flexible (context-dependent) associations, memory maintenance, nonlinear mixed selectivities, and coordination among multiple outputs. The resulting networks replicate complex dynamics previously observed in animal cortex, such as dynamic encoding of task features and selective integration of sensory inputs. We conclude that recurrent neural networks offer a plausible model of cortical dynamics during both learning and performance of flexible behavior. DOI: http://dx.doi.org/10.7554/eLife.20899.001 PMID:28230528

Biologically plausible learning in recurrent neural networks reproduces neural dynamics observed during cognitive tasks.

PubMed

Miconi, Thomas

2017-02-23

Neural activity during cognitive tasks exhibits complex dynamics that flexibly encode task-relevant variables. Chaotic recurrent networks, which spontaneously generate rich dynamics, have been proposed as a model of cortical computation during cognitive tasks. However, existing methods for training these networks are either biologically implausible, and/or require a continuous, real-time error signal to guide learning. Here we show that a biologically plausible learning rule can train such recurrent networks, guided solely by delayed, phasic rewards at the end of each trial. Networks endowed with this learning rule can successfully learn nontrivial tasks requiring flexible (context-dependent) associations, memory maintenance, nonlinear mixed selectivities, and coordination among multiple outputs. The resulting networks replicate complex dynamics previously observed in animal cortex, such as dynamic encoding of task features and selective integration of sensory inputs. We conclude that recurrent neural networks offer a plausible model of cortical dynamics during both learning and performance of flexible behavior.

Volumetric multimodality neural network for brain tumor segmentation

NASA Astrophysics Data System (ADS)

Silvana Castillo, Laura; Alexandra Daza, Laura; Carlos Rivera, Luis; Arbeláez, Pablo

2017-11-01

Brain lesion segmentation is one of the hardest tasks to be solved in computer vision with an emphasis on the medical field. We present a convolutional neural network that produces a semantic segmentation of brain tumors, capable of processing volumetric data along with information from multiple MRI modalities at the same time. This results in the ability to learn from small training datasets and highly imbalanced data. Our method is based on DeepMedic, the state of the art in brain lesion segmentation. We develop a new architecture with more convolutional layers, organized in three parallel pathways with different input resolution, and additional fully connected layers. We tested our method over the 2015 BraTS Challenge dataset, reaching an average dice coefficient of 84%, while the standard DeepMedic implementation reached 74%.

Online graphic symbol recognition using neural network and ARG matching

NASA Astrophysics Data System (ADS)

Yang, Bing; Li, Changhua; Xie, Weixing

2001-09-01

This paper proposes a novel method for on-line recognition of line-based graphic symbol. The input strokes are usually warped into a cursive form due to the sundry drawing style, and classifying them is very difficult. To deal with this, an ART-2 neural network is used to classify the input strokes. It has the advantages of high recognition rate, less recognition time and forming classes in a self-organized manner. The symbol recognition is achieved by an Attribute Relational Graph (ARG) matching algorithm. The ARG is very efficient for representing complex objects, but computation cost is very high. To over come this, we suggest a fast graph matching algorithm using symbol structure information. The experimental results show that the proposed method is effective for recognition of symbols with hierarchical structure.

Development of on-line monitoring system for Nuclear Power Plant (NPP) using neuro-expert, noise analysis, and modified neural networks

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

Subekti, M.; Center for Development of Reactor Safety Technology, National Nuclear Energy Agency of Indonesia, Puspiptek Complex BO.80, Serpong-Tangerang, 15340; Ohno, T.

2006-07-01

The neuro-expert has been utilized in previous monitoring-system research of Pressure Water Reactor (PWR). The research improved the monitoring system by utilizing neuro-expert, conventional noise analysis and modified neural networks for capability extension. The parallel method applications required distributed architecture of computer-network for performing real-time tasks. The research aimed to improve the previous monitoring system, which could detect sensor degradation, and to perform the monitoring demonstration in High Temperature Engineering Tested Reactor (HTTR). The developing monitoring system based on some methods that have been tested using the data from online PWR simulator, as well as RSG-GAS (30 MW research reactormore » in Indonesia), will be applied in HTTR for more complex monitoring. (authors)« less

Neuromechanic: a computational platform for simulation and analysis of the neural control of movement

PubMed Central

Bunderson, Nathan E.; Bingham, Jeffrey T.; Sohn, M. Hongchul; Ting, Lena H.; Burkholder, Thomas J.

2015-01-01

Neuromusculoskeletal models solve the basic problem of determining how the body moves under the influence of external and internal forces. Existing biomechanical modeling programs often emphasize dynamics with the goal of finding a feed-forward neural program to replicate experimental data or of estimating force contributions or individual muscles. The computation of rigid-body dynamics, muscle forces, and activation of the muscles are often performed separately. We have developed an intrinsically forward computational platform (Neuromechanic, www.neuromechanic.com) that explicitly represents the interdependencies among rigid body dynamics, frictional contact, muscle mechanics, and neural control modules. This formulation has significant advantages for optimization and forward simulation, particularly with application to neural controllers with feedback or regulatory features. Explicit inclusion of all state dependencies allows calculation of system derivatives with respect to kinematic states as well as muscle and neural control states, thus affording a wealth of analytical tools, including linearization, stability analyses and calculation of initial conditions for forward simulations. In this review, we describe our algorithm for generating state equations and explain how they may be used in integration, linearization and stability analysis tools to provide structural insights into the neural control of movement. PMID:23027632

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

NASA Technical Reports Server (NTRS)

Ross, Muriel D.

1991-01-01

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

Neuromechanic: a computational platform for simulation and analysis of the neural control of movement.

PubMed

Bunderson, Nathan E; Bingham, Jeffrey T; Sohn, M Hongchul; Ting, Lena H; Burkholder, Thomas J

2012-10-01

Neuromusculoskeletal models solve the basic problem of determining how the body moves under the influence of external and internal forces. Existing biomechanical modeling programs often emphasize dynamics with the goal of finding a feed-forward neural program to replicate experimental data or of estimating force contributions or individual muscles. The computation of rigid-body dynamics, muscle forces, and activation of the muscles are often performed separately. We have developed an intrinsically forward computational platform (Neuromechanic, www.neuromechanic.com) that explicitly represents the interdependencies among rigid body dynamics, frictional contact, muscle mechanics, and neural control modules. This formulation has significant advantages for optimization and forward simulation, particularly with application to neural controllers with feedback or regulatory features. Explicit inclusion of all state dependencies allows calculation of system derivatives with respect to kinematic states and muscle and neural control states, thus affording a wealth of analytical tools, including linearization, stability analyses and calculation of initial conditions for forward simulations. In this review, we describe our algorithm for generating state equations and explain how they may be used in integration, linearization, and stability analysis tools to provide structural insights into the neural control of movement. Copyright © 2012 John Wiley & Sons, Ltd.

Adversarial Threshold Neural Computer for Molecular de Novo Design.

PubMed

Putin, Evgeny; Asadulaev, Arip; Vanhaelen, Quentin; Ivanenkov, Yan; Aladinskaya, Anastasia V; Aliper, Alex; Zhavoronkov, Alex

2018-03-30

In this article, we propose the deep neural network Adversarial Threshold Neural Computer (ATNC). The ATNC model is intended for the de novo design of novel small-molecule organic structures. The model is based on generative adversarial network architecture and reinforcement learning. ATNC uses a Differentiable Neural Computer as a generator and has a new specific block, called adversarial threshold (AT). AT acts as a filter between the agent (generator) and the environment (discriminator + objective reward functions). Furthermore, to generate more diverse molecules we introduce a new objective reward function named Internal Diversity Clustering (IDC). In this work, ATNC is tested and compared with the ORGANIC model. Both models were trained on the SMILES string representation of the molecules, using four objective functions (internal similarity, Muegge druglikeness filter, presence or absence of sp 3 -rich fragments, and IDC). The SMILES representations of 15K druglike molecules from the ChemDiv collection were used as a training data set. For the different functions, ATNC outperforms ORGANIC. Combined with the IDC, ATNC generates 72% of valid and 77% of unique SMILES strings, while ORGANIC generates only 7% of valid and 86% of unique SMILES strings. For each set of molecules generated by ATNC and ORGANIC, we analyzed distributions of four molecular descriptors (number of atoms, molecular weight, logP, and tpsa) and calculated five chemical statistical features (internal diversity, number of unique heterocycles, number of clusters, number of singletons, and number of compounds that have not been passed through medicinal chemistry filters). Analysis of key molecular descriptors and chemical statistical features demonstrated that the molecules generated by ATNC elicited better druglikeness properties. We also performed in vitro validation of the molecules generated by ATNC; results indicated that ATNC is an effective method for producing hit compounds.

An Efficient Supervised Training Algorithm for Multilayer Spiking Neural Networks

PubMed Central

Xie, Xiurui; Qu, Hong; Liu, Guisong; Zhang, Malu; Kurths, Jürgen

2016-01-01

The spiking neural networks (SNNs) are the third generation of neural networks and perform remarkably well in cognitive tasks such as pattern recognition. The spike emitting and information processing mechanisms found in biological cognitive systems motivate the application of the hierarchical structure and temporal encoding mechanism in spiking neural networks, which have exhibited strong computational capability. However, the hierarchical structure and temporal encoding approach require neurons to process information serially in space and time respectively, which reduce the training efficiency significantly. For training the hierarchical SNNs, most existing methods are based on the traditional back-propagation algorithm, inheriting its drawbacks of the gradient diffusion and the sensitivity on parameters. To keep the powerful computation capability of the hierarchical structure and temporal encoding mechanism, but to overcome the low efficiency of the existing algorithms, a new training algorithm, the Normalized Spiking Error Back Propagation (NSEBP) is proposed in this paper. In the feedforward calculation, the output spike times are calculated by solving the quadratic function in the spike response model instead of detecting postsynaptic voltage states at all time points in traditional algorithms. Besides, in the feedback weight modification, the computational error is propagated to previous layers by the presynaptic spike jitter instead of the gradient decent rule, which realizes the layer-wised training. Furthermore, our algorithm investigates the mathematical relation between the weight variation and voltage error change, which makes the normalization in the weight modification applicable. Adopting these strategies, our algorithm outperforms the traditional SNN multi-layer algorithms in terms of learning efficiency and parameter sensitivity, that are also demonstrated by the comprehensive experimental results in this paper. PMID:27044001

Structure and weights optimisation of a modified Elman network emotion classifier using hybrid computational intelligence algorithms: a comparative study

NASA Astrophysics Data System (ADS)

Sheikhan, Mansour; Abbasnezhad Arabi, Mahdi; Gharavian, Davood

2015-10-01

Artificial neural networks are efficient models in pattern recognition applications, but their performance is dependent on employing suitable structure and connection weights. This study used a hybrid method for obtaining the optimal weight set and architecture of a recurrent neural emotion classifier based on gravitational search algorithm (GSA) and its binary version (BGSA), respectively. By considering the features of speech signal that were related to prosody, voice quality, and spectrum, a rich feature set was constructed. To select more efficient features, a fast feature selection method was employed. The performance of the proposed hybrid GSA-BGSA method was compared with similar hybrid methods based on particle swarm optimisation (PSO) algorithm and its binary version, PSO and discrete firefly algorithm, and hybrid of error back-propagation and genetic algorithm that were used for optimisation. Experimental tests on Berlin emotional database demonstrated the superior performance of the proposed method using a lighter network structure.

A Feature-Free 30-Disease Pathological Brain Detection System by Linear Regression Classifier.

PubMed

Chen, Yi; Shao, Ying; Yan, Jie; Yuan, Ti-Fei; Qu, Yanwen; Lee, Elizabeth; Wang, Shuihua

2017-01-01

Alzheimer's disease patients are increasing rapidly every year. Scholars tend to use computer vision methods to develop automatic diagnosis system. (Background) In 2015, Gorji et al. proposed a novel method using pseudo Zernike moment. They tested four classifiers: learning vector quantization neural network, pattern recognition neural network trained by Levenberg-Marquardt, by resilient backpropagation, and by scaled conjugate gradient. This study presents an improved method by introducing a relatively new classifier-linear regression classification. Our method selects one axial slice from 3D brain image, and employed pseudo Zernike moment with maximum order of 15 to extract 256 features from each image. Finally, linear regression classification was harnessed as the classifier. The proposed approach obtains an accuracy of 97.51%, a sensitivity of 96.71%, and a specificity of 97.73%. Our method performs better than Gorji's approach and five other state-of-the-art approaches. Therefore, it can be used to detect Alzheimer's disease. Copyright© Bentham Science Publishers; For any queries, please email at epub@benthamscience.org.

Neural networks in astronomy.

PubMed

Tagliaferri, Roberto; Longo, Giuseppe; Milano, Leopoldo; Acernese, Fausto; Barone, Fabrizio; Ciaramella, Angelo; De Rosa, Rosario; Donalek, Ciro; Eleuteri, Antonio; Raiconi, Giancarlo; Sessa, Salvatore; Staiano, Antonino; Volpicelli, Alfredo

2003-01-01

In the last decade, the use of neural networks (NN) and of other soft computing methods has begun to spread also in the astronomical community which, due to the required accuracy of the measurements, is usually reluctant to use automatic tools to perform even the most common tasks of data reduction and data mining. The federation of heterogeneous large astronomical databases which is foreseen in the framework of the astrophysical virtual observatory and national virtual observatory projects, is, however, posing unprecedented data mining and visualization problems which will find a rather natural and user friendly answer in artificial intelligence tools based on NNs, fuzzy sets or genetic algorithms. This review is aimed to both astronomers (who often have little knowledge of the methodological background) and computer scientists (who often know little about potentially interesting applications), and therefore will be structured as follows: after giving a short introduction to the subject, we shall summarize the methodological background and focus our attention on some of the most interesting fields of application, namely: object extraction and classification, time series analysis, noise identification, and data mining. Most of the original work described in the paper has been performed in the framework of the AstroNeural collaboration (Napoli-Salerno).

Vibration control of uncertain multiple launch rocket system using radial basis function neural network

NASA Astrophysics Data System (ADS)

Li, Bo; Rui, Xiaoting

2018-01-01

Poor dispersion characteristics of rockets due to the vibration of Multiple Launch Rocket System (MLRS) have always restricted the MLRS development for several decades. Vibration control is a key technique to improve the dispersion characteristics of rockets. For a mechanical system such as MLRS, the major difficulty in designing an appropriate control strategy that can achieve the desired vibration control performance is to guarantee the robustness and stability of the control system under the occurrence of uncertainties and nonlinearities. To approach this problem, a computed torque controller integrated with a radial basis function neural network is proposed to achieve the high-precision vibration control for MLRS. In this paper, the vibration response of a computed torque controlled MLRS is described. The azimuth and elevation mechanisms of the MLRS are driven by permanent magnet synchronous motors and supposed to be rigid. First, the dynamic model of motor-mechanism coupling system is established using Lagrange method and field-oriented control theory. Then, in order to deal with the nonlinearities, a computed torque controller is designed to control the vibration of the MLRS when it is firing a salvo of rockets. Furthermore, to compensate for the lumped uncertainty due to parametric variations and un-modeled dynamics in the design of the computed torque controller, a radial basis function neural network estimator is developed to adapt the uncertainty based on Lyapunov stability theory. Finally, the simulated results demonstrate the effectiveness of the proposed control system and show that the proposed controller is robust with regard to the uncertainty.

Neural and Computational Mechanisms of Action Processing: Interaction between Visual and Motor Representations.

PubMed

Giese, Martin A; Rizzolatti, Giacomo

2015-10-07

Action recognition has received enormous interest in the field of neuroscience over the last two decades. In spite of this interest, the knowledge in terms of fundamental neural mechanisms that provide constraints for underlying computations remains rather limited. This fact stands in contrast with a wide variety of speculative theories about how action recognition might work. This review focuses on new fundamental electrophysiological results in monkeys, which provide constraints for the detailed underlying computations. In addition, we review models for action recognition and processing that have concrete mathematical implementations, as opposed to conceptual models. We think that only such implemented models can be meaningfully linked quantitatively to physiological data and have a potential to narrow down the many possible computational explanations for action recognition. In addition, only concrete implementations allow judging whether postulated computational concepts have a feasible implementation in terms of realistic neural circuits. Copyright © 2015 Elsevier Inc. All rights reserved.

Deep Neural Networks: A New Framework for Modeling Biological Vision and Brain Information Processing.

PubMed

Kriegeskorte, Nikolaus

2015-11-24

Recent advances in neural network modeling have enabled major strides in computer vision and other artificial intelligence applications. Human-level visual recognition abilities are coming within reach of artificial systems. Artificial neural networks are inspired by the brain, and their computations could be implemented in biological neurons. Convolutional feedforward networks, which now dominate computer vision, take further inspiration from the architecture of the primate visual hierarchy. However, the current models are designed with engineering goals, not to model brain computations. Nevertheless, initial studies comparing internal representations between these models and primate brains find surprisingly similar representational spaces. With human-level performance no longer out of reach, we are entering an exciting new era, in which we will be able to build biologically faithful feedforward and recurrent computational models of how biological brains perform high-level feats of intelligence, including vision.

Vehicle Detection in Aerial Images Based on Region Convolutional Neural Networks and Hard Negative Example Mining.

PubMed

Tang, Tianyu; Zhou, Shilin; Deng, Zhipeng; Zou, Huanxin; Lei, Lin

2017-02-10

Detecting vehicles in aerial imagery plays an important role in a wide range of applications. The current vehicle detection methods are mostly based on sliding-window search and handcrafted or shallow-learning-based features, having limited description capability and heavy computational costs. Recently, due to the powerful feature representations, region convolutional neural networks (CNN) based detection methods have achieved state-of-the-art performance in computer vision, especially Faster R-CNN. However, directly using it for vehicle detection in aerial images has many limitations: (1) region proposal network (RPN) in Faster R-CNN has poor performance for accurately locating small-sized vehicles, due to the relatively coarse feature maps; and (2) the classifier after RPN cannot distinguish vehicles and complex backgrounds well. In this study, an improved detection method based on Faster R-CNN is proposed in order to accomplish the two challenges mentioned above. Firstly, to improve the recall, we employ a hyper region proposal network (HRPN) to extract vehicle-like targets with a combination of hierarchical feature maps. Then, we replace the classifier after RPN by a cascade of boosted classifiers to verify the candidate regions, aiming at reducing false detection by negative example mining. We evaluate our method on the Munich vehicle dataset and the collected vehicle dataset, with improvements in accuracy and robustness compared to existing methods.

Neural control of cursor trajectory and click by a human with tetraplegia 1000 days after implant of an intracortical microelectrode array

NASA Astrophysics Data System (ADS)

Simeral, J. D.; Kim, S.-P.; Black, M. J.; Donoghue, J. P.; Hochberg, L. R.

2011-04-01

The ongoing pilot clinical trial of the BrainGate neural interface system aims in part to assess the feasibility of using neural activity obtained from a small-scale, chronically implanted, intracortical microelectrode array to provide control signals for a neural prosthesis system. Critical questions include how long implanted microelectrodes will record useful neural signals, how reliably those signals can be acquired and decoded, and how effectively they can be used to control various assistive technologies such as computers and robotic assistive devices, or to enable functional electrical stimulation of paralyzed muscles. Here we examined these questions by assessing neural cursor control and BrainGate system characteristics on five consecutive days 1000 days after implant of a 4 × 4 mm array of 100 microelectrodes in the motor cortex of a human with longstanding tetraplegia subsequent to a brainstem stroke. On each of five prospectively-selected days we performed time-amplitude sorting of neuronal spiking activity, trained a population-based Kalman velocity decoding filter combined with a linear discriminant click state classifier, and then assessed closed-loop point-and-click cursor control. The participant performed both an eight-target center-out task and a random target Fitts metric task which was adapted from a human-computer interaction ISO standard used to quantify performance of computer input devices. The neural interface system was further characterized by daily measurement of electrode impedances, unit waveforms and local field potentials. Across the five days, spiking signals were obtained from 41 of 96 electrodes and were successfully decoded to provide neural cursor point-and-click control with a mean task performance of 91.3% ± 0.1% (mean ± s.d.) correct target acquisition. Results across five consecutive days demonstrate that a neural interface system based on an intracortical microelectrode array can provide repeatable, accurate point-and-click control of a computer interface to an individual with tetraplegia 1000 days after implantation of this sensor.

Neural control of cursor trajectory and click by a human with tetraplegia 1000 days after implant of an intracortical microelectrode array

PubMed Central

Simeral, J D; Kim, S-P; Black, M J; Donoghue, J P; Hochberg, L R

2013-01-01

The ongoing pilot clinical trial of the BrainGate neural interface system aims in part to assess the feasibility of using neural activity obtained from a small-scale, chronically implanted, intracortical microelectrode array to provide control signals for a neural prosthesis system. Critical questions include how long implanted microelectrodes will record useful neural signals, how reliably those signals can be acquired and decoded, and how effectively they can be used to control various assistive technologies such as computers and robotic assistive devices, or to enable functional electrical stimulation of paralyzed muscles. Here we examined these questions by assessing neural cursor control and BrainGate system characteristics on five consecutive days 1000 days after implant of a 4 × 4 mm array of 100 microelectrodes in the motor cortex of a human with longstanding tetraplegia subsequent to a brainstem stroke. On each of five prospectively-selected days we performed time-amplitude sorting of neuronal spiking activity, trained a population-based Kalman velocity decoding filter combined with a linear discriminant click state classifier, and then assessed closed-loop point-and-click cursor control. The participant performed both an eight-target center-out task and a random target Fitts metric task which was adapted from a human-computer interaction ISO standard used to quantify performance of computer input devices. The neural interface system was further characterized by daily measurement of electrode impedances, unit waveforms and local field potentials. Across the five days, spiking signals were obtained from 41 of 96 electrodes and were successfully decoded to provide neural cursor point-and-click control with a mean task performance of 91.3% ± 0.1% (mean ± s.d.) correct target acquisition. Results across five consecutive days demonstrate that a neural interface system based on an intracortical microelectrode array can provide repeatable, accurate point-and-click control of a computer interface to an individual with tetraplegia 1000 days after implantation of this sensor. PMID:21436513

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.

Technologies for imaging neural activity in large volumes

PubMed Central

Ji, Na; Freeman, Jeremy; Smith, Spencer L.

2017-01-01

Neural circuitry has evolved to form distributed networks that act dynamically across large volumes. Collecting data from individual planes, conventional microscopy cannot sample circuitry across large volumes at the temporal resolution relevant to neural circuit function and behaviors. Here, we review emerging technologies for rapid volume imaging of neural circuitry. We focus on two critical challenges: the inertia of optical systems, which limits image speed, and aberrations, which restrict the image volume. Optical sampling time must be long enough to ensure high-fidelity measurements, but optimized sampling strategies and point spread function engineering can facilitate rapid volume imaging of neural activity within this constraint. We also discuss new computational strategies for the processing and analysis of volume imaging data of increasing size and complexity. Together, optical and computational advances are providing a broader view of neural circuit dynamics, and help elucidate how brain regions work in concert to support behavior. PMID:27571194

Neural priming in human frontal cortex: multiple forms of learning reduce demands on the prefrontal executive system.

PubMed

Race, Elizabeth A; Shanker, Shanti; Wagner, Anthony D

2009-09-01

Past experience is hypothesized to reduce computational demands in PFC by providing bottom-up predictive information that informs subsequent stimulus-action mapping. The present fMRI study measured cortical activity reductions ("neural priming"/"repetition suppression") during repeated stimulus classification to investigate the mechanisms through which learning from the past decreases demands on the prefrontal executive system. Manipulation of learning at three levels of representation-stimulus, decision, and response-revealed dissociable neural priming effects in distinct frontotemporal regions, supporting a multiprocess model of neural priming. Critically, three distinct patterns of neural priming were identified in lateral frontal cortex, indicating that frontal computational demands are reduced by three forms of learning: (a) cortical tuning of stimulus-specific representations, (b) retrieval of learned stimulus-decision mappings, and (c) retrieval of learned stimulus-response mappings. The topographic distribution of these neural priming effects suggests a rostrocaudal organization of executive function in lateral frontal cortex.

Human activity recognition based on feature selection in smart home using back-propagation algorithm.

PubMed

Fang, Hongqing; He, Lei; Si, Hao; Liu, Peng; Xie, Xiaolei

2014-09-01

In this paper, Back-propagation(BP) algorithm has been used to train the feed forward neural network for human activity recognition in smart home environments, and inter-class distance method for feature selection of observed motion sensor events is discussed and tested. And then, the human activity recognition performances of neural network using BP algorithm have been evaluated and compared with other probabilistic algorithms: Naïve Bayes(NB) classifier and Hidden Markov Model(HMM). The results show that different feature datasets yield different activity recognition accuracy. The selection of unsuitable feature datasets increases the computational complexity and degrades the activity recognition accuracy. Furthermore, neural network using BP algorithm has relatively better human activity recognition performances than NB classifier and HMM. Copyright © 2014 ISA. Published by Elsevier Ltd. All rights reserved.

Evaluation of somatosensory cortical differences between flutter and vibration tactile stimuli.

PubMed

Han, Sang Woo; Chung, Yoon Gi; Kim, Hyung-Sik; Chung, Soon-Cheol; Park, Jang-Yeon; Kim, Sung-Phil

2013-01-01

In parallel with advances in haptic-based mobile computing systems, understanding of the neural processing of vibrotactile information becomes of great importance. In the human nervous system, two types of vibrotactile information, flutter and vibration, are delivered from mechanoreceptors to the somatosensory cortex through segregated neural afferents. To investigate how the somatosensory cortex differentiates flutter and vibration, we analyzed the cortical responses to vibrotactile stimuli with a wide range of frequencies. Specifically, we examined whether cortical activity changed most around 50 Hz, which is known as a boundary between flutter and vibration. We explored various measures to evaluate separability of cortical activity across frequency and found that the hypothesis margin method resulted in the greatest separability between flutter and vibration. This result suggests that flutter and vibration information may be processed by different neural processes in the somatosensory cortex.

Predicting the survival of diabetes using neural network

NASA Astrophysics Data System (ADS)

Mamuda, Mamman; Sathasivam, Saratha

2017-08-01

Data mining techniques at the present time are used in predicting diseases of health care industries. Neural Network is one among the prevailing method in data mining techniques of an intelligent field for predicting diseases in health care industries. This paper presents a study on the prediction of the survival of diabetes diseases using different learning algorithms from the supervised learning algorithms of neural network. Three learning algorithms are considered in this study: (i) The levenberg-marquardt learning algorithm (ii) The Bayesian regulation learning algorithm and (iii) The scaled conjugate gradient learning algorithm. The network is trained using the Pima Indian Diabetes Dataset with the help of MATLAB R2014(a) software. The performance of each algorithm is further discussed through regression analysis. The prediction accuracy of the best algorithm is further computed to validate the accurate prediction

Application of ANNs approach for wave-like and heat-like equations

NASA Astrophysics Data System (ADS)

Jafarian, Ahmad; Baleanu, Dumitru

2017-12-01

Artificial neural networks are data processing systems which originate from human brain tissue studies. The remarkable abilities of these networks help us to derive desired results from complicated raw data. In this study, we intend to duplicate an efficient iterative method to the numerical solution of two famous partial differential equations, namely the wave-like and heat-like problems. It should be noted that many physical phenomena such as coupling currents in a flat multi-strand two-layer super conducting cable, non-homogeneous elastic waves in soils and earthquake stresses, are described by initial-boundary value wave and heat partial differential equations with variable coefficients. To the numerical solution of these equations, a combination of the power series method and artificial neural networks approach, is used to seek an appropriate bivariate polynomial solution of the mentioned initial-boundary value problem. Finally, several computer simulations confirmed the theoretical results and demonstrating applicability of the method.

Hierarchical Feature Extraction With Local Neural Response for Image Recognition.

PubMed

Li, Hong; Wei, Yantao; Li, Luoqing; Chen, C L P

2013-04-01

In this paper, a hierarchical feature extraction method is proposed for image recognition. The key idea of the proposed method is to extract an effective feature, called local neural response (LNR), of the input image with nontrivial discrimination and invariance properties by alternating between local coding and maximum pooling operation. The local coding, which is carried out on the locally linear manifold, can extract the salient feature of image patches and leads to a sparse measure matrix on which maximum pooling is carried out. The maximum pooling operation builds the translation invariance into the model. We also show that other invariant properties, such as rotation and scaling, can be induced by the proposed model. In addition, a template selection algorithm is presented to reduce computational complexity and to improve the discrimination ability of the LNR. Experimental results show that our method is robust to local distortion and clutter compared with state-of-the-art algorithms.

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.

Efficient shortest-path-tree computation in network routing based on pulse-coupled neural networks.

PubMed

Qu, Hong; Yi, Zhang; Yang, Simon X

2013-06-01

Shortest path tree (SPT) computation is a critical issue for routers using link-state routing protocols, such as the most commonly used open shortest path first and intermediate system to intermediate system. Each router needs to recompute a new SPT rooted from itself whenever a change happens in the link state. Most commercial routers do this computation by deleting the current SPT and building a new one using static algorithms such as the Dijkstra algorithm at the beginning. Such recomputation of an entire SPT is inefficient, which may consume a considerable amount of CPU time and result in a time delay in the network. Some dynamic updating methods using the information in the updated SPT have been proposed in recent years. However, there are still many limitations in those dynamic algorithms. In this paper, a new modified model of pulse-coupled neural networks (M-PCNNs) is proposed for the SPT computation. It is rigorously proved that the proposed model is capable of solving some optimization problems, such as the SPT. A static algorithm is proposed based on the M-PCNNs to compute the SPT efficiently for large-scale problems. In addition, a dynamic algorithm that makes use of the structure of the previously computed SPT is proposed, which significantly improves the efficiency of the algorithm. Simulation results demonstrate the effective and efficient performance of the proposed approach.

Linear methods for reducing EMG contamination in peripheral nerve motor decodes.

PubMed

Kagan, Zachary B; Wendelken, Suzanne; Page, David M; Davis, Tyler; Hutchinson, Douglas T; Clark, Gregory A; Warren, David J

2016-08-01

Signals recorded from the peripheral nervous system (PNS) with high channel count penetrating microelectrode arrays, such as the Utah Slanted Electrode Array (USEA), often have electromyographic (EMG) signals contaminating the neural signal. This common-mode signal source may prevent single neural units from successfully being detected, thus hindering motor decode algorithms. Reducing this EMG contamination may lead to more accurate motor decode performance. A virtual reference (VR), created by a weighted linear combination of signals from a subset of all available channels, can be used to reduce this EMG contamination. Four methods of determining individual channel weights and six different methods of selecting subsets of channels were investigated (24 different VR types in total). The methods of determining individual channel weights were equal weighting, regression-based weighting, and two different proximity-based weightings. The subsets of channels were selected by a radius-based criteria, such that a channel was included if it was within a particular radius of inclusion from the target channel. These six radii of inclusion were 1.5, 2.9, 3.2, 5, 8.4, and 12.8 electrode-distances; the 12.8 electrode radius includes all USEA electrodes. We found that application of a VR improves the detectability of neural events via increasing the SNR, but we found no statistically meaningful difference amongst the VR types we examined. The computational complexity of implementation varies with respect to the method of determining channel weights and the number of channels in a subset, but does not correlate with VR performance. Hence, we examined the computational costs of calculating and applying the VR and based on these criteria, we recommend an equal weighting method of assigning weights with a 3.2 electrode-distance radius of inclusion. Further, we found empirically that application of the recommended VR will require less than 1 ms for 33.3 ms of data from one USEA.

Discrete-time neural network for fast solving large linear L1 estimation problems and its application to image restoration.

PubMed

Xia, Youshen; Sun, Changyin; Zheng, Wei Xing

2012-05-01

There is growing interest in solving linear L1 estimation problems for sparsity of the solution and robustness against non-Gaussian noise. This paper proposes a discrete-time neural network which can calculate large linear L1 estimation problems fast. The proposed neural network has a fixed computational step length and is proved to be globally convergent to an optimal solution. Then, the proposed neural network is efficiently applied to image restoration. Numerical results show that the proposed neural network is not only efficient in solving degenerate problems resulting from the nonunique solutions of the linear L1 estimation problems but also needs much less computational time than the related algorithms in solving both linear L1 estimation and image restoration problems.

An Expedient Study on Back-Propagation (BPN) Neural Networks for Modeling Automated Evaluation of the Answers and Progress of Deaf Students' That Possess Basic Knowledge of the English Language and Computer Skills

NASA Astrophysics Data System (ADS)

Vrettaros, John; Vouros, George; Drigas, Athanasios S.

This article studies the expediency of using neural networks technology and the development of back-propagation networks (BPN) models for modeling automated evaluation of the answers and progress of deaf students' that possess basic knowledge of the English language and computer skills, within a virtual e-learning environment. The performance of the developed neural models is evaluated with the correlation factor between the neural networks' response values and the real value data as well as the percentage measurement of the error between the neural networks' estimate values and the real value data during its training process and afterwards with unknown data that weren't used in the training process.

A New Volumetric Radiologic Method to Assess Indirect Decompression After Extreme Lateral Interbody Fusion Using High-Resolution Intraoperative Computed Tomography.

PubMed

Navarro-Ramirez, Rodrigo; Berlin, Connor; Lang, Gernot; Hussain, Ibrahim; Janssen, Insa; Sloan, Stephen; Askin, Gulce; Avila, Mauricio J; Zubkov, Micaella; Härtl, Roger

2018-01-01

Two-dimensional radiographic methods have been proposed to evaluate the radiographic outcome after indirect decompression through extreme lateral interbody fusion (XLIF). However, the assessment of neural decompression in a single plane may underestimate the effect of indirect decompression on central canal and foraminal volumes. The present study aimed to assess the reliability and consistency of a novel 3-dimensional radiographic method that assesses neural decompression by volumetric analysis using a new generation of intraoperative fan-beam computed tomography scanner in patients undergoing XLIF. Prospectively collected data from 7 patients (9 levels) undergoing XLIF was retrospectively analyzed. Three independent, blind raters using imaging analysis software performed volumetric measurements pre- and postoperatively to determine central canal and foraminal volumes. Intrarater and Interrater reliability tests were performed to assess the reliability of this novel volumetric method. The interrater reliability between the three raters ranged from 0.800 to 0.952, P < 0.0001. The test-retest analysis on a randomly selected subset of three patients showed good to excellent internal reliability (range of 0.78-1.00) for all 3 raters. There was a significant increase in mean volume ≈20% for right foramen, left foramen, and central canal volumes postoperatively (P = 0.0472; P = 0.0066; P = 0.0003, respectively). Here we demonstrate a new volumetric analysis technique that is feasible, reliable, and reproducible amongst independent raters for central canal and foraminal volumes in the lumbar spine using an intraoperative computed tomography scanner. Copyright © 2017. Published by Elsevier Inc.

[Algorithms of artificial neural networks--practical application in medical science].

PubMed

Stefaniak, Bogusław; Cholewiński, Witold; Tarkowska, Anna

2005-12-01

Artificial Neural Networks (ANN) may be a tool alternative and complementary to typical statistical analysis. However, in spite of many computer applications of various ANN algorithms ready for use, artificial intelligence is relatively rarely applied to data processing. This paper presents practical aspects of scientific application of ANN in medicine using widely available algorithms. Several main steps of analysis with ANN were discussed starting from material selection and dividing it into groups, to the quality assessment of obtained results at the end. The most frequent, typical reasons for errors as well as the comparison of ANN method to the modeling by regression analysis were also described.

Compression fractures detection on CT

NASA Astrophysics Data System (ADS)

Bar, Amir; Wolf, Lior; Bergman Amitai, Orna; Toledano, Eyal; Elnekave, Eldad

2017-03-01

The presence of a vertebral compression fracture is highly indicative of osteoporosis and represents the single most robust predictor for development of a second osteoporotic fracture in the spine or elsewhere. Less than one third of vertebral compression fractures are diagnosed clinically. We present an automated method for detecting spine compression fractures in Computed Tomography (CT) scans. The algorithm is composed of three processes. First, the spinal column is segmented and sagittal patches are extracted. The patches are then binary classified using a Convolutional Neural Network (CNN). Finally a Recurrent Neural Network (RNN) is utilized to predict whether a vertebral fracture is present in the series of patches.

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.

A Case Study on Neural Inspired Dynamic Memory Management Strategies for High Performance Computing.

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

Vineyard, Craig Michael; Verzi, Stephen Joseph

As high performance computing architectures pursue more computational power there is a need for increased memory capacity and bandwidth as well. A multi-level memory (MLM) architecture addresses this need by combining multiple memory types with different characteristics as varying levels of the same architecture. How to efficiently utilize this memory infrastructure is an unknown challenge, and in this research we sought to investigate whether neural inspired approaches can meaningfully help with memory management. In particular we explored neurogenesis inspired re- source allocation, and were able to show a neural inspired mixed controller policy can beneficially impact how MLM architectures utilizemore » memory.« less

Multiplexing in the primate motion pathway.

PubMed

Huk, Alexander C

2012-06-01

This article begins by reviewing recent work on 3D motion processing in the primate visual system. Some of these results suggest that 3D motion signals may be processed in the same circuitry already known to compute 2D motion signals. Such "multiplexing" has implications for the study of visual cortical circuits and neural signals. A more explicit appreciation of multiplexing--and the computations required for demultiplexing--may enrich the study of the visual system by emphasizing the importance of a structured and balanced "encoding/decoding" framework. In addition to providing a fresh perspective on how successive stages of visual processing might be approached, multiplexing also raises caveats about the value of "neural correlates" for understanding neural computation.

Reward-Modulated Hebbian Plasticity as Leverage for Partially Embodied Control in Compliant Robotics

PubMed Central

Burms, Jeroen; Caluwaerts, Ken; Dambre, Joni

2015-01-01

In embodied computation (or morphological computation), part of the complexity of motor control is offloaded to the body dynamics. We demonstrate that a simple Hebbian-like learning rule can be used to train systems with (partial) embodiment, and can be extended outside of the scope of traditional neural networks. To this end, we apply the learning rule to optimize the connection weights of recurrent neural networks with different topologies and for various tasks. We then apply this learning rule to a simulated compliant tensegrity robot by optimizing static feedback controllers that directly exploit the dynamics of the robot body. This leads to partially embodied controllers, i.e., hybrid controllers that naturally integrate the computations that are performed by the robot body into a neural network architecture. Our results demonstrate the universal applicability of reward-modulated Hebbian learning. Furthermore, they demonstrate the robustness of systems trained with the learning rule. This study strengthens our belief that compliant robots should or can be seen as computational units, instead of dumb hardware that needs a complex controller. This link between compliant robotics and neural networks is also the main reason for our search for simple universal learning rules for both neural networks and robotics. PMID:26347645

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.

Neural network approaches to capture temporal information

NASA Astrophysics Data System (ADS)

van Veelen, Martijn; Nijhuis, Jos; Spaanenburg, Ben

2000-05-01

The automated design and construction of neural networks receives growing attention of the neural networks community. Both the growing availability of computing power and development of mathematical and probabilistic theory have had severe impact on the design and modelling approaches of neural networks. This impact is most apparent in the use of neural networks to time series prediction. In this paper, we give our views on past, contemporary and future design and modelling approaches to neural forecasting.

Neural Network Technique for Continous Transition from Ocean to Coastal Retrackers

NASA Astrophysics Data System (ADS)

Hazrina Idris, Nurul; Deng, Xiaoli; Hawani Idris, Nurul

2017-04-01

This paper presents the development of neural network for continuous transition of altimeter sea surface heights when switching from ocean to coastal waveform retrackers. In attempting to produce precise coastal sea level anomaly (SLA) via retracking waveforms, issue arose when employing multiple retracking algorithms (i.e. MLE-4, sub-waveform and threshold). The existence of relative offset between those retrackers creates 'jump' in the retracked SLA profiles. In this study, the offset between retrackers is minimized using multi-layer feed forward neural network technique. The technique reduces the offset values by modelling the complicated functions of those retracked SLAs. The technique is tested over the region of the Great Barrier Reef (GBR), Australia. The validation with Townsville and Bundaberg tide gauges shows that the threshold retracker achieves temporal correlations (r) of 0.84 and 0.75, respectively, and root mean square (RMS) error is 16 cm for both stations, indicating that the retracker produces more accurate SLAs than those of two retrackers. Meanwhile, values of r (RMS error) for MLE-4 is only 0.79 (18 cm) and 0.71 (16 cm), respectively, and for sub-waveform is 0.82 (16 cm) and 0.67 (16 cm), respectively. Therefore, with the neural network, retracked SLAs from MLE-4 and sub-waveform are aligned to those of the threshold retracker. The performance of neural network is compared with the normal procedure of offset removal, which is based on the mean of SLA differences (mean method). The performance is assessed by computing the standard deviation of difference (STD) between the SLAs above a referenced ellipsoid and the geoidal height, and the improvement of percentage (IMP). The results indicate that the neural network provides improvement in SLA precision in all 12 cases, while the mean method provides improvement in 10 out of 12 cases and deterioration is seen in two cases. In terms of STD and IMP, neural network reduces the offset better than those of the mean method. The IMPs with neural network reaches up to 67% for Jason-1 and 73% for Jason-2, meanwhile with mean method the IMPs only reaches up to 28% and 46%, respectively. In conclusion, the neural network technique is efficient to reduce the offset among retrackers by handling the linear and nonlinear relationship between retrackers, thus providing seamless transition from the open ocean to the coast, and vice versa. Studies in currently on-going are to consider other geophysical parameters, such as significant wave height that might be related to the variation of the offset, in the neural network.

Using Neural Networks to Improve the Performance of Radiative Transfer Modeling Used for Geometry Dependent LER Calculations

NASA Astrophysics Data System (ADS)

Fasnacht, Z.; Qin, W.; Haffner, D. P.; Loyola, D. G.; Joiner, J.; Krotkov, N. A.; Vasilkov, A. P.; Spurr, R. J. D.

2017-12-01

In order to estimate surface reflectance used in trace gas retrieval algorithms, radiative transfer models (RTM) such as the Vector Linearized Discrete Ordinate Radiative Transfer Model (VLIDORT) can be used to simulate the top of the atmosphere (TOA) radiances with advanced models of surface properties. With large volumes of satellite data, these model simulations can become computationally expensive. Look up table interpolation can improve the computational cost of the calculations, but the non-linear nature of the radiances requires a dense node structure if interpolation errors are to be minimized. In order to reduce our computational effort and improve the performance of look-up tables, neural networks can be trained to predict these radiances. We investigate the impact of using look-up table interpolation versus a neural network trained using the smart sampling technique, and show that neural networks can speed up calculations and reduce errors while using significantly less memory and RTM calls. In future work we will implement a neural network in operational processing to meet growing demands for reflectance modeling in support of high spatial resolution satellite missions.

Simplified and Yet Turing Universal Spiking Neural P Systems with Communication on Request.

PubMed

Wu, Tingfang; Bîlbîe, Florin-Daniel; Păun, Andrei; Pan, Linqiang; Neri, Ferrante

2018-04-02

Spiking neural P systems are a class of third generation neural networks belonging to the framework of membrane computing. Spiking neural P systems with communication on request (SNQ P systems) are a type of spiking neural P system where the spikes are requested from neighboring neurons. SNQ P systems have previously been proved to be universal (computationally equivalent to Turing machines) when two types of spikes are considered. This paper studies a simplified version of SNQ P systems, i.e. SNQ P systems with one type of spike. It is proved that one type of spike is enough to guarantee the Turing universality of SNQ P systems. Theoretical results are shown in the cases of the SNQ P system used in both generating and accepting modes. Furthermore, the influence of the number of unbounded neurons (the number of spikes in a neuron is not bounded) on the computation power of SNQ P systems with one type of spike is investigated. It is found that SNQ P systems functioning as number generating devices with one type of spike and four unbounded neurons are Turing universal.

Computational neural networks in chemistry: Model free mapping devices for predicting chemical reactivity from molecular structure

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

Elrod, D.W.

1992-01-01

Computational neural networks (CNNs) are a computational paradigm inspired by the brain's massively parallel network of highly interconnected neurons. The power of computational neural networks derives not so much from their ability to model the brain as from their ability to learn by example and to map highly complex, nonlinear functions, without the need to explicitly specify the functional relationship. Two central questions about CNNs were investigated in the context of predicting chemical reactions: (1) the mapping properties of neural networks and (2) the representation of chemical information for use in CNNs. Chemical reactivity is here considered an example ofmore » a complex, nonlinear function of molecular structure. CNN's were trained using modifications of the back propagation learning rule to map a three dimensional response surface similar to those typically observed in quantitative structure-activity and structure-property relationships. The computational neural network's mapping of the response surface was found to be robust to the effects of training sample size, noisy data and intercorrelated input variables. The investigation of chemical structure representation led to the development of a molecular structure-based connection-table representation suitable for neural network training. An extension of this work led to a BE-matrix structure representation that was found to be general for several classes of reactions. The CNN prediction of chemical reactivity and regiochemistry was investigated for electrophilic aromatic substitution reactions, Markovnikov addition to alkenes, Saytzeff elimination from haloalkanes, Diels-Alder cycloaddition, and retro Diels-Alder ring opening reactions using these connectivity-matrix derived representations. The reaction predictions made by the CNNs were more accurate than those of an expert system and were comparable to predictions made by chemists.« less

Changes in White Matter Microstructure Impact Cognition by Disrupting the Ability of Neural Assemblies to Synchronize.

PubMed

Bells, Sonya; Lefebvre, Jérémie; Prescott, Steven A; Dockstader, Colleen; Bouffet, Eric; Skocic, Jovanka; Laughlin, Suzanne; Mabbott, Donald J

2017-08-23

Cognition is compromised by white matter (WM) injury but the neurophysiological alterations linking them remain unclear. We hypothesized that reduced neural synchronization caused by disruption of neural signal propagation is involved. To test this, we evaluated group differences in: diffusion tensor WM microstructure measures within the optic radiations, primary visual area (V1), and cuneus; neural phase synchrony to a visual attention cue during visual-motor task; and reaction time to a response cue during the same task between 26 pediatric patients (17/9: male/female) treated with cranial radiation treatment for a brain tumor (12.67 ± 2.76 years), and 26 healthy children (16/10: male/female; 12.01 ± 3.9 years). We corroborated our findings using a corticocortical computational model representing perturbed signal conduction from myelin. Patients show delayed reaction time, WM compromise, and reduced phase synchrony during visual attention compared with healthy children. Notably, using partial least-squares-path modeling we found that WM insult within the optic radiations, V1, and cuneus is a strong predictor of the slower reaction times via disruption of neural synchrony in visual cortex. Observed changes in synchronization were reproduced in a computational model of WM injury. These findings provide new evidence linking cognition with WM via the reliance of neural synchronization on propagation of neural signals. SIGNIFICANCE STATEMENT By comparing brain tumor patients to healthy children, we establish that changes in the microstructure of the optic radiations and neural synchrony during visual attention predict reaction time. Furthermore, by testing the directionality of these links through statistical modeling and verifying our findings with computational modeling, we infer a causal relationship, namely that changes in white matter microstructure impact cognition in part by disturbing the ability of neural assemblies to synchronize. Together, our human imaging data and computer simulations show a fundamental connection between WM microstructure and neural synchronization that is critical for cognitive processing. Copyright © 2017 the authors 0270-6474/17/378227-12$15.00/0.

Neural network simulation of the atmospheric point spread function for the adjacency effect research

NASA Astrophysics Data System (ADS)

Ma, Xiaoshan; Wang, Haidong; Li, Ligang; Yang, Zhen; Meng, Xin

2016-10-01

Adjacency effect could be regarded as the convolution of the atmospheric point spread function (PSF) and the surface leaving radiance. Monte Carlo is a common method to simulate the atmospheric PSF. But it can't obtain analytic expression and the meaningful results can be only acquired by statistical analysis of millions of data. A backward Monte Carlo algorithm was employed to simulate photon emitting and propagating in the atmosphere under different conditions. The PSF was determined by recording the photon-receiving numbers in fixed bin at different position. A multilayer feed-forward neural network with a single hidden layer was designed to learn the relationship between the PSF's and the input condition parameters. The neural network used the back-propagation learning rule for training. Its input parameters involved atmosphere condition, spectrum range, observing geometry. The outputs of the network were photon-receiving numbers in the corresponding bin. Because the output units were too many to be allowed by neural network, the large network was divided into a collection of smaller ones. These small networks could be ran simultaneously on many workstations and/or PCs to speed up the training. It is important to note that the simulated PSF's by Monte Carlo technique in non-nadir viewing angles are more complicated than that in nadir conditions which brings difficulties in the design of the neural network. The results obtained show that the neural network approach could be very useful to compute the atmospheric PSF based on the simulated data generated by Monte Carlo method.

Cortical Neural Computation by Discrete Results Hypothesis

PubMed Central

Castejon, Carlos; Nuñez, Angel

2016-01-01

One of the most challenging problems we face in neuroscience is to understand how the cortex performs computations. There is increasing evidence that the power of the cortical processing is produced by populations of neurons forming dynamic neuronal ensembles. Theoretical proposals and multineuronal experimental studies have revealed that ensembles of neurons can form emergent functional units. However, how these ensembles are implicated in cortical computations is still a mystery. Although cell ensembles have been associated with brain rhythms, the functional interaction remains largely unclear. It is still unknown how spatially distributed neuronal activity can be temporally integrated to contribute to cortical computations. A theoretical explanation integrating spatial and temporal aspects of cortical processing is still lacking. In this Hypothesis and Theory article, we propose a new functional theoretical framework to explain the computational roles of these ensembles in cortical processing. We suggest that complex neural computations underlying cortical processing could be temporally discrete and that sensory information would need to be quantized to be computed by the cerebral cortex. Accordingly, we propose that cortical processing is produced by the computation of discrete spatio-temporal functional units that we have called “Discrete Results” (Discrete Results Hypothesis). This hypothesis represents a novel functional mechanism by which information processing is computed in the cortex. Furthermore, we propose that precise dynamic sequences of “Discrete Results” is the mechanism used by the cortex to extract, code, memorize and transmit neural information. The novel “Discrete Results” concept has the ability to match the spatial and temporal aspects of cortical processing. We discuss the possible neural underpinnings of these functional computational units and describe the empirical evidence supporting our hypothesis. We propose that fast-spiking (FS) interneuron may be a key element in our hypothesis providing the basis for this computation. PMID:27807408

Cortical Neural Computation by Discrete Results Hypothesis.

PubMed

Castejon, Carlos; Nuñez, Angel

2016-01-01

One of the most challenging problems we face in neuroscience is to understand how the cortex performs computations. There is increasing evidence that the power of the cortical processing is produced by populations of neurons forming dynamic neuronal ensembles. Theoretical proposals and multineuronal experimental studies have revealed that ensembles of neurons can form emergent functional units. However, how these ensembles are implicated in cortical computations is still a mystery. Although cell ensembles have been associated with brain rhythms, the functional interaction remains largely unclear. It is still unknown how spatially distributed neuronal activity can be temporally integrated to contribute to cortical computations. A theoretical explanation integrating spatial and temporal aspects of cortical processing is still lacking. In this Hypothesis and Theory article, we propose a new functional theoretical framework to explain the computational roles of these ensembles in cortical processing. We suggest that complex neural computations underlying cortical processing could be temporally discrete and that sensory information would need to be quantized to be computed by the cerebral cortex. Accordingly, we propose that cortical processing is produced by the computation of discrete spatio-temporal functional units that we have called "Discrete Results" (Discrete Results Hypothesis). This hypothesis represents a novel functional mechanism by which information processing is computed in the cortex. Furthermore, we propose that precise dynamic sequences of "Discrete Results" is the mechanism used by the cortex to extract, code, memorize and transmit neural information. The novel "Discrete Results" concept has the ability to match the spatial and temporal aspects of cortical processing. We discuss the possible neural underpinnings of these functional computational units and describe the empirical evidence supporting our hypothesis. We propose that fast-spiking (FS) interneuron may be a key element in our hypothesis providing the basis for this computation.

Cross hole GPR traveltime inversion using a fast and accurate neural network as a forward model

NASA Astrophysics Data System (ADS)

Mejer Hansen, Thomas

2017-04-01

Probabilistic formulated inverse problems can be solved using Monte Carlo based sampling methods. In principle both advanced prior information, such as based on geostatistics, and complex non-linear forward physical models can be considered. However, in practice these methods can be associated with huge computational costs that in practice limit their application. This is not least due to the computational requirements related to solving the forward problem, where the physical response of some earth model has to be evaluated. Here, it is suggested to replace a numerical complex evaluation of the forward problem, with a trained neural network that can be evaluated very fast. This will introduce a modeling error, that is quantified probabilistically such that it can be accounted for during inversion. This allows a very fast and efficient Monte Carlo sampling of the solution to an inverse problem. We demonstrate the methodology for first arrival travel time inversion of cross hole ground-penetrating radar (GPR) data. An accurate forward model, based on 2D full-waveform modeling followed by automatic travel time picking, is replaced by a fast neural network. This provides a sampling algorithm three orders of magnitude faster than using the full forward model, and considerably faster, and more accurate, than commonly used approximate forward models. The methodology has the potential to dramatically change the complexity of the types of inverse problems that can be solved using non-linear Monte Carlo sampling techniques.

Convolutional neural network architectures for predicting DNA–protein binding

PubMed Central

Zeng, Haoyang; Edwards, Matthew D.; Liu, Ge; Gifford, David K.

2016-01-01

Motivation: Convolutional neural networks (CNN) have outperformed conventional methods in modeling the sequence specificity of DNA–protein binding. Yet inappropriate CNN architectures can yield poorer performance than simpler models. Thus an in-depth understanding of how to match CNN architecture to a given task is needed to fully harness the power of CNNs for computational biology applications. Results: We present a systematic exploration of CNN architectures for predicting DNA sequence binding using a large compendium of transcription factor datasets. We identify the best-performing architectures by varying CNN width, depth and pooling designs. We find that adding convolutional kernels to a network is important for motif-based tasks. We show the benefits of CNNs in learning rich higher-order sequence features, such as secondary motifs and local sequence context, by comparing network performance on multiple modeling tasks ranging in difficulty. We also demonstrate how careful construction of sequence benchmark datasets, using approaches that control potentially confounding effects like positional or motif strength bias, is critical in making fair comparisons between competing methods. We explore how to establish the sufficiency of training data for these learning tasks, and we have created a flexible cloud-based framework that permits the rapid exploration of alternative neural network architectures for problems in computational biology. Availability and Implementation: All the models analyzed are available at http://cnn.csail.mit.edu. Contact: gifford@mit.edu Supplementary information: Supplementary data are available at Bioinformatics online. PMID:27307608

[Application of chemometrics in composition-activity relationship research of traditional Chinese medicine].

PubMed

Han, Sheng-Nan

2014-07-01

Chemometrics is a new branch of chemistry which is widely applied to various fields of analytical chemistry. Chemometrics can use theories and methods of mathematics, statistics, computer science and other related disciplines to optimize the chemical measurement process and maximize access to acquire chemical information and other information on material systems by analyzing chemical measurement data. In recent years, traditional Chinese medicine has attracted widespread attention. In the research of traditional Chinese medicine, it has been a key problem that how to interpret the relationship between various chemical components and its efficacy, which seriously restricts the modernization of Chinese medicine. As chemometrics brings the multivariate analysis methods into the chemical research, it has been applied as an effective research tool in the composition-activity relationship research of Chinese medicine. This article reviews the applications of chemometrics methods in the composition-activity relationship research in recent years. The applications of multivariate statistical analysis methods (such as regression analysis, correlation analysis, principal component analysis, etc. ) and artificial neural network (such as back propagation artificial neural network, radical basis function neural network, support vector machine, etc. ) are summarized, including the brief fundamental principles, the research contents and the advantages and disadvantages. Finally, the existing main problems and prospects of its future researches are proposed.

Computing with scale-invariant neural representations

NASA Astrophysics Data System (ADS)

Howard, Marc; Shankar, Karthik

The Weber-Fechner law is perhaps the oldest quantitative relationship in psychology. Consider the problem of the brain representing a function f (x) . Different neurons have receptive fields that support different parts of the range, such that the ith neuron has a receptive field at xi. Weber-Fechner scaling refers to the finding that the width of the receptive field scales with xi as does the difference between the centers of adjacent receptive fields. Weber-Fechner scaling is exponentially resource-conserving. Neurophysiological evidence suggests that neural representations obey Weber-Fechner scaling in the visual system and perhaps other systems as well. We describe an optimality constraint that is solved by Weber-Fechner scaling, providing an information-theoretic rationale for this principle of neural coding. Weber-Fechner scaling can be generated within a mathematical framework using the Laplace transform. Within this framework, simple computations such as translation, correlation and cross-correlation can be accomplished. This framework can in principle be extended to provide a general computational language for brain-inspired cognitive computation on scale-invariant representations. Supported by NSF PHY 1444389 and the BU Initiative for the Physics and Mathematics of Neural Systems,.

EDITORIAL: Special section on gaze-independent brain-computer interfaces Special section on gaze-independent brain-computer interfaces

NASA Astrophysics Data System (ADS)

Treder, Matthias S.

2012-08-01

Restoring the ability to communicate and interact with the environment in patients with severe motor disabilities is a vision that has been the main catalyst of early brain-computer interface (BCI) research. The past decade has brought a diversification of the field. BCIs have been examined as a tool for motor rehabilitation and their benefit in non-medical applications such as mental-state monitoring for improved human-computer interaction and gaming has been confirmed. At the same time, the weaknesses of some approaches have been pointed out. One of these weaknesses is gaze-dependence, that is, the requirement that the user of a BCI system voluntarily directs his or her eye gaze towards a visual target in order to efficiently operate a BCI. This not only contradicts the main doctrine of BCI research, namely that BCIs should be independent of muscle activity, but it can also limit its real-world applicability both in clinical and non-medical settings. It is only in a scenario devoid of any motor activity that a BCI solution is without alternative. Gaze-dependencies have surfaced at two different points in the BCI loop. Firstly, a BCI that relies on visual stimulation may require users to fixate on the target location. Secondly, feedback is often presented visually, which implies that the user may have to move his or her eyes in order to perceive the feedback. This special section was borne out of a BCI workshop on gaze-independent BCIs held at the 2011 Society for Applied Neurosciences (SAN) Conference and has then been extended with additional contributions from other research groups. It compiles experimental and methodological work that aims toward gaze-independent communication and mental-state monitoring. Riccio et al review the current state-of-the-art in research on gaze-independent BCIs [1]. Van der Waal et al present a tactile speller that builds on the stimulation of the fingers of the right and left hand [2]. H¨ohne et al analyze the ergonomic aspects of stimuli and systematic class confusions in auditory BCIs [3]. Andersson et al use fMRI for online-decoding of covert shifts of visual attention [4]. Thurlings et al show that multi-sensory integration of tactile and visual information can enhance the amplitude of ERP components [5]. Schaeff et al investigate the use of motion VEPs in gaze-independent visual BCIs [6]. Wilson et al substitute visual feedback by mapping the screen's cursor onto a tactor grid that stimulates the tongue [7]. Brouwer et al explore the use of ERP features and spectral features for estimating mental workload in an n-back task [8]. Falzon et al extend the Common Spatial Patterns (CSP) method to the complex plane, taking into account both amplitude and phase relationships [9]. Eliseyev et al present a method for the sparse sub-selection of electrodes for classification [10]. Tonin et al demonstrate that the classification of covert attention shifts is improved by considering sub-bands of the alpha band [11]. Aloise et al investigate effects of classification scheme and decimation on the performance of a gaze-independent BCI [12]. References [1] Riccio A et al 2012 J. Neural Eng. 9 045001 [2] van der Waal M et al 2012 J. Neural Eng. 9 045002 [3] Höhne J et al 2012 J. Neural Eng. 9 045003 [4] Andersson P et al 2012 J. Neural Eng. 9 045004 [5] Thurlings M E et al 2012 J. Neural Eng. 9 045005 [6] Schaeff S et al 2012 J. Neural Eng. 9 045006 [7] Wilson J A et al 2012 J. Neural Eng. 9 045007 [8] Brouwer A-M et al 2012 J. Neural Eng. 9 045008 [9] Falzon O et al 2012 J. Neural Eng. 9 045009 [10] Eliseyev A et al 2012 J. Neural Eng. 9 045010 [11] Tonin L et al 2012 J. Neural Eng. 9 045011 [12] Aloise F et al 2012 J. Neural Eng. 9 045012

Virus Particle Detection by Convolutional Neural Network in Transmission Electron Microscopy Images.

PubMed

Ito, Eisuke; Sato, Takaaki; Sano, Daisuke; Utagawa, Etsuko; Kato, Tsuyoshi

2018-06-01

A new computational method for the detection of virus particles in transmission electron microscopy (TEM) images is presented. Our approach is to use a convolutional neural network that transforms a TEM image to a probabilistic map that indicates where virus particles exist in the image. Our proposed approach automatically and simultaneously learns both discriminative features and classifier for virus particle detection by machine learning, in contrast to existing methods that are based on handcrafted features that yield many false positives and require several postprocessing steps. The detection performance of the proposed method was assessed against a dataset of TEM images containing feline calicivirus particles and compared with several existing detection methods, and the state-of-the-art performance of the developed method for detecting virus was demonstrated. Since our method is based on supervised learning that requires both the input images and their corresponding annotations, it is basically used for detection of already-known viruses. However, the method is highly flexible, and the convolutional networks can adapt themselves to any virus particles by learning automatically from an annotated dataset.