Learning text representation using recurrent convolutional neural network with highway layers

OpenAIRE

Wen, Ying; Zhang, Weinan; Luo, Rui; Wang, Jun

2016-01-01

Recently, the rapid development of word embedding and neural networks has brought new inspiration to various NLP and IR tasks. In this paper, we describe a staged hybrid model combining Recurrent Convolutional Neural Networks (RCNN) with highway layers. The highway network module is incorporated in the middle takes the output of the bi-directional Recurrent Neural Network (Bi-RNN) module in the first stage and provides the Convolutional Neural Network (CNN) module in the last stage with the i...

Encoding Time in Feedforward Trajectories of a Recurrent Neural Network Model.

Science.gov (United States)

Hardy, N F; Buonomano, Dean V

2018-02-01

Brain activity evolves through time, creating trajectories of activity that underlie sensorimotor processing, behavior, and learning and memory. Therefore, understanding the temporal nature of neural dynamics is essential to understanding brain function and behavior. In vivo studies have demonstrated that sequential transient activation of neurons can encode time. However, it remains unclear whether these patterns emerge from feedforward network architectures or from recurrent networks and, furthermore, what role network structure plays in timing. We address these issues using a recurrent neural network (RNN) model with distinct populations of excitatory and inhibitory units. Consistent with experimental data, a single RNN could autonomously produce multiple functionally feedforward trajectories, thus potentially encoding multiple timed motor patterns lasting up to several seconds. Importantly, the model accounted for Weber's law, a hallmark of timing behavior. Analysis of network connectivity revealed that efficiency-a measure of network interconnectedness-decreased as the number of stored trajectories increased. Additionally, the balance of excitation (E) and inhibition (I) shifted toward excitation during each unit's activation time, generating the prediction that observed sequential activity relies on dynamic control of the E/I balance. Our results establish for the first time that the same RNN can generate multiple functionally feedforward patterns of activity as a result of dynamic shifts in the E/I balance imposed by the connectome of the RNN. We conclude that recurrent network architectures account for sequential neural activity, as well as for a fundamental signature of timing behavior: Weber's law.

Global dissipativity of continuous-time recurrent neural networks with time delay

International Nuclear Information System (INIS)

Liao Xiaoxin; Wang Jun

2003-01-01

This paper addresses the global dissipativity of a general class of continuous-time recurrent neural networks. First, the concepts of global dissipation and global exponential dissipation are defined and elaborated. Next, the sets of global dissipativity and global exponentially dissipativity are characterized using the parameters of recurrent neural network models. In particular, it is shown that the Hopfield network and cellular neural networks with or without time delays are dissipative systems

Recurrent Neural Network For Forecasting Time Series With Long Memory Pattern

Science.gov (United States)

Walid; Alamsyah

2017-04-01

Recurrent Neural Network as one of the hybrid models are often used to predict and estimate the issues related to electricity, can be used to describe the cause of the swelling of electrical load which experienced by PLN. In this research will be developed RNN forecasting procedures at the time series with long memory patterns. Considering the application is the national electrical load which of course has a different trend with the condition of the electrical load in any country. This research produces the algorithm of time series forecasting which has long memory pattern using E-RNN after this referred to the algorithm of integrated fractional recurrent neural networks (FIRNN).The prediction results of long memory time series using models Fractional Integrated Recurrent Neural Network (FIRNN) showed that the model with the selection of data difference in the range of [-1,1] and the model of Fractional Integrated Recurrent Neural Network (FIRNN) (24,6,1) provides the smallest MSE value, which is 0.00149684.

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

Science.gov (United States)

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

2017-01-01

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

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

Science.gov (United States)

Liu, Qingshan; Cao, Jinde; Chen, Guanrong

2010-11-01

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

Noise-enhanced categorization in a recurrently reconnected neural network

International Nuclear Information System (INIS)

Monterola, Christopher; Zapotocky, Martin

2005-01-01

We investigate the interplay of recurrence and noise in neural networks trained to categorize spatial patterns of neural activity. We develop the following procedure to demonstrate how, in the presence of noise, the introduction of recurrence permits to significantly extend and homogenize the operating range of a feed-forward neural network. We first train a two-level perceptron in the absence of noise. Following training, we identify the input and output units of the feed-forward network, and thus convert it into a two-layer recurrent network. We show that the performance of the reconnected network has features reminiscent of nondynamic stochastic resonance: the addition of noise enables the network to correctly categorize stimuli of subthreshold strength, with optimal noise magnitude significantly exceeding the stimulus strength. We characterize the dynamics leading to this effect and contrast it to the behavior of a more simple associative memory network in which noise-mediated categorization fails

Noise-enhanced categorization in a recurrently reconnected neural network

Science.gov (United States)

Monterola, Christopher; Zapotocky, Martin

2005-03-01

We investigate the interplay of recurrence and noise in neural networks trained to categorize spatial patterns of neural activity. We develop the following procedure to demonstrate how, in the presence of noise, the introduction of recurrence permits to significantly extend and homogenize the operating range of a feed-forward neural network. We first train a two-level perceptron in the absence of noise. Following training, we identify the input and output units of the feed-forward network, and thus convert it into a two-layer recurrent network. We show that the performance of the reconnected network has features reminiscent of nondynamic stochastic resonance: the addition of noise enables the network to correctly categorize stimuli of subthreshold strength, with optimal noise magnitude significantly exceeding the stimulus strength. We characterize the dynamics leading to this effect and contrast it to the behavior of a more simple associative memory network in which noise-mediated categorization fails.

Embedding recurrent neural networks into predator-prey models.

Science.gov (United States)

Moreau, Yves; Louiès, Stephane; Vandewalle, Joos; Brenig, Leon

1999-03-01

We study changes of coordinates that allow the embedding of ordinary differential equations describing continuous-time recurrent neural networks into differential equations describing predator-prey models-also called Lotka-Volterra systems. We transform the equations for the neural network first into quasi-monomial form (Brenig, L. (1988). Complete factorization and analytic solutions of generalized Lotka-Volterra equations. Physics Letters A, 133(7-8), 378-382), where we express the vector field of the dynamical system as a linear combination of products of powers of the variables. In practice, this transformation is possible only if the activation function is the hyperbolic tangent or the logistic sigmoid. From this quasi-monomial form, we can directly transform the system further into Lotka-Volterra equations. The resulting Lotka-Volterra system is of higher dimension than the original system, but the behavior of its first variables is equivalent to the behavior of the original neural network. We expect that this transformation will permit the application of existing techniques for the analysis of Lotka-Volterra systems to recurrent neural networks. Furthermore, our results show that Lotka-Volterra systems are universal approximators of dynamical systems, just as are continuous-time neural networks.

Recurrent Neural Network for Computing the Drazin Inverse.

Science.gov (United States)

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.

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

Science.gov (United States)

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

Deep Gate Recurrent Neural Network

Science.gov (United States)

2016-11-22

and Fred Cummins. Learning to forget: Continual prediction with lstm . Neural computation, 12(10):2451–2471, 2000. Alex Graves. Generating sequences...DSGU) and Simple Gated Unit (SGU), which are structures for learning long-term dependencies. Compared to traditional Long Short-Term Memory ( LSTM ) and...Gated Recurrent Unit (GRU), both structures require fewer parameters and less computation time in sequence classification tasks. Unlike GRU and LSTM

Parameter estimation in space systems using recurrent neural networks

Science.gov (United States)

Parlos, Alexander G.; Atiya, Amir F.; Sunkel, John W.

1991-01-01

The identification of time-varying parameters encountered in space systems is addressed, using artificial neural systems. A hybrid feedforward/feedback neural network, namely a recurrent multilayer perception, is used as the model structure in the nonlinear system identification. The feedforward portion of the network architecture provides its well-known interpolation property, while through recurrency and cross-talk, the local information feedback enables representation of temporal variations in the system nonlinearities. The standard back-propagation-learning algorithm is modified and it is used for both the off-line and on-line supervised training of the proposed hybrid network. The performance of recurrent multilayer perceptron networks in identifying parameters of nonlinear dynamic systems is investigated by estimating the mass properties of a representative large spacecraft. The changes in the spacecraft inertia are predicted using a trained neural network, during two configurations corresponding to the early and late stages of the spacecraft on-orbit assembly sequence. The proposed on-line mass properties estimation capability offers encouraging results, though, further research is warranted for training and testing the predictive capabilities of these networks beyond nominal spacecraft operations.

Synthesis of recurrent neural networks for dynamical system simulation.

Science.gov (United States)

Trischler, Adam P; D'Eleuterio, Gabriele M T

2016-08-01

We review several of the most widely used techniques for training recurrent neural networks to approximate dynamical systems, then describe a novel algorithm for this task. The algorithm is based on an earlier theoretical result that guarantees the quality of the network approximation. We show that a feedforward neural network can be trained on the vector-field representation of a given dynamical system using backpropagation, then recast it as a recurrent network that replicates the original system's dynamics. After detailing this algorithm and its relation to earlier approaches, we present numerical examples that demonstrate its capabilities. One of the distinguishing features of our approach is that both the original dynamical systems and the recurrent networks that simulate them operate in continuous time. Copyright © 2016 Elsevier Ltd. All rights reserved.

Recursive Bayesian recurrent neural networks for time-series modeling.

Science.gov (United States)

Mirikitani, Derrick T; Nikolaev, Nikolay

2010-02-01

This paper develops a probabilistic approach to recursive second-order training of recurrent neural networks (RNNs) for improved time-series modeling. A general recursive Bayesian Levenberg-Marquardt algorithm is derived to sequentially update the weights and the covariance (Hessian) matrix. The main strengths of the approach are a principled handling of the regularization hyperparameters that leads to better generalization, and stable numerical performance. The framework involves the adaptation of a noise hyperparameter and local weight prior hyperparameters, which represent the noise in the data and the uncertainties in the model parameters. Experimental investigations using artificial and real-world data sets show that RNNs equipped with the proposed approach outperform standard real-time recurrent learning and extended Kalman training algorithms for recurrent networks, as well as other contemporary nonlinear neural models, on time-series modeling.

Analysis of surface ozone using a recurrent neural network.

Science.gov (United States)

Biancofiore, Fabio; Verdecchia, Marco; Di Carlo, Piero; Tomassetti, Barbara; Aruffo, Eleonora; Busilacchio, Marcella; Bianco, Sebastiano; Di Tommaso, Sinibaldo; Colangeli, Carlo

2015-05-01

Hourly concentrations of ozone (O₃) and nitrogen dioxide (NO₂) have been measured for 16 years, from 1998 to 2013, in a seaside town in central Italy. The seasonal trends of O₃ and NO₂ recorded in this period have been studied. Furthermore, we used the data collected during one year (2005), to define the characteristics of a multiple linear regression model and a neural network model. Both models are used to model the hourly O₃ concentration, using, two scenarios: 1) in the first as inputs, only meteorological parameters and 2) in the second adding photochemical parameters at those of the first scenario. In order to evaluate the performance of the model four statistical criteria are used: correlation coefficient, fractional bias, normalized mean squared error and a factor of two. All the criteria show that the neural network gives better results, compared to the regression model, in all the model scenarios. Predictions of O₃ have been carried out by many authors using a feed forward neural architecture. In this paper we show that a recurrent architecture significantly improves the performances of neural predictors. Using only the meteorological parameters as input, the recurrent architecture shows performance better than the multiple linear regression model that uses meteorological and photochemical data as input, making the neural network model with recurrent architecture a more useful tool in areas where only weather measurements are available. Finally, we used the neural network model to forecast the O₃ hourly concentrations 1, 3, 6, 12, 24 and 48 h ahead. The performances of the model in predicting O₃ levels are discussed. Emphasis is given to the possibility of using the neural network model in operational ways in areas where only meteorological data are available, in order to predict O₃ also in sites where it has not been measured yet. Copyright © 2015 Elsevier B.V. All rights reserved.

Multistability and instability analysis of recurrent neural networks with time-varying delays.

Science.gov (United States)

Zhang, Fanghai; Zeng, Zhigang

2018-01-01

This paper provides new theoretical results on the multistability and instability analysis of recurrent neural networks with time-varying delays. It is shown that such n-neuronal recurrent neural networks have exactly [Formula: see text] equilibria, [Formula: see text] of which are locally exponentially stable and the others are unstable, where k 0 is a nonnegative integer such that k 0 ≤n. By using the combination method of two different divisions, recurrent neural networks can possess more dynamic properties. This method improves and extends the existing results in the literature. Finally, one numerical example is provided to show the superiority and effectiveness of the presented results. Copyright © 2017 Elsevier Ltd. All rights reserved.

Synaptic plasticity in a recurrent neural network for versatile and adaptive behaviors of a walking robot

DEFF Research Database (Denmark)

Grinke, Eduard; Tetzlaff, Christian; Wörgötter, Florentin

2015-01-01

correlation-based learning with synaptic scaling is applied to adequately change the connections of the network. By doing so, we can effectively exploit neural dynamics (i.e., hysteresis effects and single attractors) in the network to generate different turning angles with short-term memory for a walking...... dynamics, plasticity, sensory feedback, and biomechanics. Generating such versatile and adaptive behaviors for a many degrees-of-freedom (DOFs) walking robot is a challenging task. Thus, in this study, we present a bio-inspired approach to solve this task. Specifically, the approach combines neural...... mechanisms with plasticity, exteroceptive sensory feedback, and biomechanics. The neural mechanisms consist of adaptive neural sensory processing and modular neural locomotion control. The sensory processing is based on a small recurrent neural network consisting of two fully connected neurons. Online...

Supervised Sequence Labelling with Recurrent Neural Networks

CERN Document Server

Graves, Alex

2012-01-01

Supervised sequence labelling is a vital area of machine learning, encompassing tasks such as speech, handwriting and gesture recognition, protein secondary structure prediction and part-of-speech tagging. Recurrent neural networks are powerful sequence learning tools—robust to input noise and distortion, able to exploit long-range contextual information—that would seem ideally suited to such problems. However their role in large-scale sequence labelling systems has so far been auxiliary.    The goal of this book is a complete framework for classifying and transcribing sequential data with recurrent neural networks only. Three main innovations are introduced in order to realise this goal. Firstly, the connectionist temporal classification output layer allows the framework to be trained with unsegmented target sequences, such as phoneme-level speech transcriptions; this is in contrast to previous connectionist approaches, which were dependent on error-prone prior segmentation. Secondly, multidimensional...

Nonlinear recurrent neural networks for finite-time solution of general time-varying linear matrix equations.

Science.gov (United States)

Xiao, Lin; Liao, Bolin; Li, Shuai; Chen, Ke

2018-02-01

In order to solve general time-varying linear matrix equations (LMEs) more efficiently, this paper proposes two nonlinear recurrent neural networks based on two nonlinear activation functions. According to Lyapunov theory, such two nonlinear recurrent neural networks are proved to be convergent within finite-time. Besides, by solving differential equation, the upper bounds of the finite convergence time are determined analytically. Compared with existing recurrent neural networks, the proposed two nonlinear recurrent neural networks have a better convergence property (i.e., the upper bound is lower), and thus the accurate solutions of general time-varying LMEs can be obtained with less time. At last, various different situations have been considered by setting different coefficient matrices of general time-varying LMEs and a great variety of computer simulations (including the application to robot manipulators) have been conducted to validate the better finite-time convergence of the proposed two nonlinear recurrent neural networks. Copyright © 2017 Elsevier Ltd. All rights reserved.

Convolutional over Recurrent Encoder for Neural Machine Translation

Directory of Open Access Journals (Sweden)

Dakwale Praveen

2017-06-01

Full Text Available Neural machine translation is a recently proposed approach which has shown competitive results to traditional MT approaches. Standard neural MT is an end-to-end neural network where the source sentence is encoded by a recurrent neural network (RNN called encoder and the target words are predicted using another RNN known as decoder. Recently, various models have been proposed which replace the RNN encoder with a convolutional neural network (CNN. In this paper, we propose to augment the standard RNN encoder in NMT with additional convolutional layers in order to capture wider context in the encoder output. Experiments on English to German translation demonstrate that our approach can achieve significant improvements over a standard RNN-based baseline.

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

Science.gov (United States)

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.

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

Energy Technology Data Exchange (ETDEWEB)

Hamadneh, Nawaf; Sathasivam, Saratha; Choon, Ong Hong [School of Mathematical Sciences, Universiti Sains Malaysia, 11800 USM, Penang (Malaysia)

2014-07-10

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 (T{sub p}: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.

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

International Nuclear Information System (INIS)

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

2014-01-01

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 (T p :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

Iterative free-energy optimization for recurrent neural networks (INFERNO)

Science.gov (United States)

2017-01-01

The intra-parietal lobe coupled with the Basal Ganglia forms a working memory that demonstrates strong planning capabilities for generating robust yet flexible neuronal sequences. Neurocomputational models however, often fails to control long range neural synchrony in recurrent spiking networks due to spontaneous activity. As a novel framework based on the free-energy principle, we propose to see the problem of spikes’ synchrony as an optimization problem of the neurons sub-threshold activity for the generation of long neuronal chains. Using a stochastic gradient descent, a reinforcement signal (presumably dopaminergic) evaluates the quality of one input vector to move the recurrent neural network to a desired activity; depending on the error made, this input vector is strengthened to hill-climb the gradient or elicited to search for another solution. This vector can be learned then by one associative memory as a model of the basal-ganglia to control the recurrent neural network. Experiments on habit learning and on sequence retrieving demonstrate the capabilities of the dual system to generate very long and precise spatio-temporal sequences, above two hundred iterations. Its features are applied then to the sequential planning of arm movements. In line with neurobiological theories, we discuss its relevance for modeling the cortico-basal working memory to initiate flexible goal-directed neuronal chains of causation and its relation to novel architectures such as Deep Networks, Neural Turing Machines and the Free-Energy Principle. PMID:28282439

Representation of linguistic form and function in recurrent neural networks

NARCIS (Netherlands)

Kadar, Akos; Chrupala, Grzegorz; Alishahi, Afra

2017-01-01

We present novel methods for analyzing the activation patterns of recurrent neural networks from a linguistic point of view and explore the types of linguistic structure they learn. As a case study, we use a standard standalone language model, and a multi-task gated recurrent network architecture

From Imitation to Prediction, Data Compression vs Recurrent Neural Networks for Natural Language Processing

Directory of Open Access Journals (Sweden)

Juan Andres Laura

2018-03-01

Full Text Available In recent studies Recurrent Neural Networks were used for generative processes and their surprising performance can be explained by their ability to create good predictions. In addition, Data Compression is also based on prediction. What the problem comes down to is whether a data compressor could be used to perform as well as recurrent neural networks in the natural language processing tasks of sentiment analysis and automatic text generation. If this is possible, then the problem comes down to determining if a compression algorithm is even more intelligent than a neural network in such tasks. In our journey, a fundamental difference between a Data Compression Algorithm and Recurrent Neural Networks has been discovered.

Encoding sensory and motor patterns as time-invariant trajectories in recurrent neural networks.

Science.gov (United States)

Goudar, Vishwa; Buonomano, Dean V

2018-03-14

Much of the information the brain processes and stores is temporal in nature-a spoken word or a handwritten signature, for example, is defined by how it unfolds in time. However, it remains unclear how neural circuits encode complex time-varying patterns. We show that by tuning the weights of a recurrent neural network (RNN), it can recognize and then transcribe spoken digits. The model elucidates how neural dynamics in cortical networks may resolve three fundamental challenges: first, encode multiple time-varying sensory and motor patterns as stable neural trajectories; second, generalize across relevant spatial features; third, identify the same stimuli played at different speeds-we show that this temporal invariance emerges because the recurrent dynamics generate neural trajectories with appropriately modulated angular velocities. Together our results generate testable predictions as to how recurrent networks may use different mechanisms to generalize across the relevant spatial and temporal features of complex time-varying stimuli. © 2018, Goudar et al.

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

Science.gov (United States)

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

2018-05-01

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

Protein secondary structure prediction using modular reciprocal bidirectional recurrent neural networks.

Science.gov (United States)

Babaei, Sepideh; Geranmayeh, Amir; Seyyedsalehi, Seyyed Ali

2010-12-01

The supervised learning of recurrent neural networks well-suited for prediction of protein secondary structures from the underlying amino acids sequence is studied. Modular reciprocal recurrent neural networks (MRR-NN) are proposed to model the strong correlations between adjacent secondary structure elements. Besides, a multilayer bidirectional recurrent neural network (MBR-NN) is introduced to capture the long-range intramolecular interactions between amino acids in formation of the secondary structure. The final modular prediction system is devised based on the interactive integration of the MRR-NN and the MBR-NN structures to arbitrarily engage the neighboring effects of the secondary structure types concurrent with memorizing the sequential dependencies of amino acids along the protein chain. The advanced combined network augments the percentage accuracy (Q₃) to 79.36% and boosts the segment overlap (SOV) up to 70.09% when tested on the PSIPRED dataset in three-fold cross-validation. Copyright © 2010 Elsevier Ireland Ltd. All rights reserved.

Multi-step-prediction of chaotic time series based on co-evolutionary recurrent neural network

International Nuclear Information System (INIS)

Ma Qianli; Zheng Qilun; Peng Hong; Qin Jiangwei; Zhong Tanwei

2008-01-01

This paper proposes a co-evolutionary recurrent neural network (CERNN) for the multi-step-prediction of chaotic time series, it estimates the proper parameters of phase space reconstruction and optimizes the structure of recurrent neural networks by co-evolutionary strategy. The searching space was separated into two subspaces and the individuals are trained in a parallel computational procedure. It can dynamically combine the embedding method with the capability of recurrent neural network to incorporate past experience due to internal recurrence. The effectiveness of CERNN is evaluated by using three benchmark chaotic time series data sets: the Lorenz series, Mackey-Glass series and real-world sun spot series. The simulation results show that CERNN improves the performances of multi-step-prediction of chaotic time series

Local Dynamics in Trained Recurrent Neural Networks.

Science.gov (United States)

Rivkind, Alexander; Barak, Omri

2017-06-23

Learning a task induces connectivity changes in neural circuits, thereby changing their dynamics. To elucidate task-related neural dynamics, we study trained recurrent neural networks. We develop a mean field theory for reservoir computing networks trained to have multiple fixed point attractors. Our main result is that the dynamics of the network's output in the vicinity of attractors is governed by a low-order linear ordinary differential equation. The stability of the resulting equation can be assessed, predicting training success or failure. As a consequence, networks of rectified linear units and of sigmoidal nonlinearities are shown to have diametrically different properties when it comes to learning attractors. Furthermore, a characteristic time constant, which remains finite at the edge of chaos, offers an explanation of the network's output robustness in the presence of variability of the internal neural dynamics. Finally, the proposed theory predicts state-dependent frequency selectivity in the network response.

Local Dynamics in Trained Recurrent Neural Networks

Science.gov (United States)

Rivkind, Alexander; Barak, Omri

2017-06-01

Learning a task induces connectivity changes in neural circuits, thereby changing their dynamics. To elucidate task-related neural dynamics, we study trained recurrent neural networks. We develop a mean field theory for reservoir computing networks trained to have multiple fixed point attractors. Our main result is that the dynamics of the network's output in the vicinity of attractors is governed by a low-order linear ordinary differential equation. The stability of the resulting equation can be assessed, predicting training success or failure. As a consequence, networks of rectified linear units and of sigmoidal nonlinearities are shown to have diametrically different properties when it comes to learning attractors. Furthermore, a characteristic time constant, which remains finite at the edge of chaos, offers an explanation of the network's output robustness in the presence of variability of the internal neural dynamics. Finally, the proposed theory predicts state-dependent frequency selectivity in the network response.

Evaluation of the Performance of Feedforward and Recurrent Neural Networks in Active Cancellation of Sound Noise

Directory of Open Access Journals (Sweden)

Mehrshad Salmasi

2012-07-01

Full Text Available Active noise control is based on the destructive interference between the primary noise and generated noise from the secondary source. An antinoise of equal amplitude and opposite phase is generated and combined with the primary noise. In this paper, performance of the neural networks is evaluated in active cancellation of sound noise. For this reason, feedforward and recurrent neural networks are designed and trained. After training, performance of the feedforwrad and recurrent networks in noise attenuation are compared. We use Elman network as a recurrent neural network. For simulations, noise signals from a SPIB database are used. In order to compare the networks appropriately, equal number of layers and neurons are considered for the networks. Moreover, training and test samples are similar. Simulation results show that feedforward and recurrent neural networks present good performance in noise cancellation. As it is seen, the ability of recurrent neural network in noise attenuation is better than feedforward network.

Statistical downscaling of precipitation using long short-term memory recurrent neural networks

Science.gov (United States)

Misra, Saptarshi; Sarkar, Sudeshna; Mitra, Pabitra

2017-11-01

Hydrological impacts of global climate change on regional scale are generally assessed by downscaling large-scale climatic variables, simulated by General Circulation Models (GCMs), to regional, small-scale hydrometeorological variables like precipitation, temperature, etc. In this study, we propose a new statistical downscaling model based on Recurrent Neural Network with Long Short-Term Memory which captures the spatio-temporal dependencies in local rainfall. The previous studies have used several other methods such as linear regression, quantile regression, kernel regression, beta regression, and artificial neural networks. Deep neural networks and recurrent neural networks have been shown to be highly promising in modeling complex and highly non-linear relationships between input and output variables in different domains and hence we investigated their performance in the task of statistical downscaling. We have tested this model on two datasets—one on precipitation in Mahanadi basin in India and the second on precipitation in Campbell River basin in Canada. Our autoencoder coupled long short-term memory recurrent neural network model performs the best compared to other existing methods on both the datasets with respect to temporal cross-correlation, mean squared error, and capturing the extremes.

Recurrent Neural Network Approach Based on the Integral Representation of the Drazin Inverse.

Science.gov (United States)

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

2015-10-01

In this letter, we present the dynamical equation and corresponding artificial recurrent neural network for computing the Drazin inverse for arbitrary square real matrix, without any restriction on its eigenvalues. Conditions that ensure the stability of the defined recurrent neural network as well as its convergence toward the Drazin inverse are considered. Several illustrative examples present the results of computer simulations.

Multistability of delayed complex-valued recurrent neural networks with discontinuous real-imaginary-type activation functions

International Nuclear Information System (INIS)

Huang Yu-Jiao; Hu Hai-Gen

2015-01-01

In this paper, the multistability issue is discussed for delayed complex-valued recurrent neural networks with discontinuous real-imaginary-type activation functions. Based on a fixed theorem and stability definition, sufficient criteria are established for the existence and stability of multiple equilibria of complex-valued recurrent neural networks. The number of stable equilibria is larger than that of real-valued recurrent neural networks, which can be used to achieve high-capacity associative memories. One numerical example is provided to show the effectiveness and superiority of the presented results. (paper)

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

Science.gov (United States)

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.

A novel joint-processing adaptive nonlinear equalizer using a modular recurrent neural network for chaotic communication systems.

Science.gov (United States)

Zhao, Haiquan; Zeng, Xiangping; Zhang, Jiashu; Liu, Yangguang; Wang, Xiaomin; Li, Tianrui

2011-01-01

To eliminate nonlinear channel distortion in chaotic communication systems, a novel joint-processing adaptive nonlinear equalizer based on a pipelined recurrent neural network (JPRNN) is proposed, using a modified real-time recurrent learning (RTRL) algorithm. Furthermore, an adaptive amplitude RTRL algorithm is adopted to overcome the deteriorating effect introduced by the nesting process. Computer simulations illustrate that the proposed equalizer outperforms the pipelined recurrent neural network (PRNN) and recurrent neural network (RNN) equalizers. Copyright © 2010 Elsevier Ltd. All rights reserved.

Global exponential stability and periodicity of reaction-diffusion delayed recurrent neural networks with Dirichlet boundary conditions

International Nuclear Information System (INIS)

Lu Junguo

2008-01-01

In this paper, the global exponential stability and periodicity for a class of reaction-diffusion delayed recurrent neural networks with Dirichlet boundary conditions are addressed by constructing suitable Lyapunov functionals and utilizing some inequality techniques. We first prove global exponential converge to 0 of the difference between any two solutions of the original reaction-diffusion delayed recurrent neural networks with Dirichlet boundary conditions, the existence and uniqueness of equilibrium is the direct results of this procedure. This approach is different from the usually used one where the existence, uniqueness of equilibrium and stability are proved in two separate steps. Furthermore, we prove periodicity of the reaction-diffusion delayed recurrent neural networks with Dirichlet boundary conditions. Sufficient conditions ensuring the global exponential stability and the existence of periodic oscillatory solutions for the reaction-diffusion delayed recurrent neural networks with Dirichlet boundary conditions are given. These conditions are easy to check and have important leading significance in the design and application of reaction-diffusion recurrent neural networks with delays. Finally, two numerical examples are given to show the effectiveness of the obtained results

Global robust stability of delayed recurrent neural networks

International Nuclear Information System (INIS)

Cao Jinde; Huang Deshuang; Qu Yuzhong

2005-01-01

This paper is concerned with the global robust stability of a class of delayed interval recurrent neural networks which contain time-invariant uncertain parameters whose values are unknown but bounded in given compact sets. A new sufficient condition is presented for the existence, uniqueness, and global robust stability of equilibria for interval neural networks with time delays by constructing Lyapunov functional and using matrix-norm inequality. An error is corrected in an earlier publication, and an example is given to show the effectiveness of the obtained results

Global exponential stability of reaction-diffusion recurrent neural networks with time-varying delays

International Nuclear Information System (INIS)

Liang Jinling; Cao Jinde

2003-01-01

Employing general Halanay inequality, we analyze the global exponential stability of a class of reaction-diffusion recurrent neural networks with time-varying delays. Several new sufficient conditions are obtained to ensure existence, uniqueness and global exponential stability of the equilibrium point of delayed reaction-diffusion recurrent neural networks. The results extend and improve the earlier publications. In addition, an example is given to show the effectiveness of the obtained result

Acoustic Event Detection in Multichannel Audio Using Gated Recurrent Neural Networks with High‐Resolution Spectral Features

Directory of Open Access Journals (Sweden)

Hyoung‐Gook Kim

2017-12-01

Full Text Available Recently, deep recurrent neural networks have achieved great success in various machine learning tasks, and have also been applied for sound event detection. The detection of temporally overlapping sound events in realistic environments is much more challenging than in monophonic detection problems. In this paper, we present an approach to improve the accuracy of polyphonic sound event detection in multichannel audio based on gated recurrent neural networks in combination with auditory spectral features. In the proposed method, human hearing perception‐based spatial and spectral‐domain noise‐reduced harmonic features are extracted from multichannel audio and used as high‐resolution spectral inputs to train gated recurrent neural networks. This provides a fast and stable convergence rate compared to long short‐term memory recurrent neural networks. Our evaluation reveals that the proposed method outperforms the conventional approaches.

A recurrent neural network with ever changing synapses

NARCIS (Netherlands)

Heerema, M.; van Leeuwen, W.A.

2000-01-01

A recurrent neural network with noisy input is studied analytically, on the basis of a Discrete Time Master Equation. The latter is derived from a biologically realizable learning rule for the weights of the connections. In a numerical study it is found that the fixed points of the dynamics of the

Ideomotor feedback control in a recurrent neural network.

Science.gov (United States)

Galtier, Mathieu

2015-06-01

The architecture of a neural network controlling an unknown environment is presented. It is based on a randomly connected recurrent neural network from which both perception and action are simultaneously read and fed back. There are two concurrent learning rules implementing a sort of ideomotor control: (i) perception is learned along the principle that the network should predict reliably its incoming stimuli; (ii) action is learned along the principle that the prediction of the network should match a target time series. The coherent behavior of the neural network in its environment is a consequence of the interaction between the two principles. Numerical simulations show a promising performance of the approach, which can be turned into a local and better "biologically plausible" algorithm.

Delay-Dependent Stability Criteria of Uncertain Periodic Switched Recurrent Neural Networks with Time-Varying Delays

Directory of Open Access Journals (Sweden)

Xing Yin

2011-01-01

uncertain periodic switched recurrent neural networks with time-varying delays. When uncertain discrete-time recurrent neural network is a periodic system, it is expressed as switched neural network for the finite switching state. Based on the switched quadratic Lyapunov functional approach (SQLF and free-weighting matrix approach (FWM, some linear matrix inequality criteria are found to guarantee the delay-dependent asymptotical stability of these systems. Two examples illustrate the exactness of the proposed criteria.

A Recurrent Neural Network for Nonlinear Fractional Programming

Directory of Open Access Journals (Sweden)

Quan-Ju Zhang

2012-01-01

Full Text Available This paper presents a novel recurrent time continuous neural network model which performs nonlinear fractional optimization subject to interval constraints on each of the optimization variables. The network is proved to be complete in the sense that the set of optima of the objective function to be minimized with interval constraints coincides with the set of equilibria of the neural network. It is also shown that the network is primal and globally convergent in the sense that its trajectory cannot escape from the feasible region and will converge to an exact optimal solution for any initial point being chosen in the feasible interval region. Simulation results are given to demonstrate further the global convergence and good performance of the proposing neural network for nonlinear fractional programming problems with interval constraints.

Identification and prediction of dynamic systems using an interactively recurrent self-evolving fuzzy neural network.

Science.gov (United States)

Lin, Yang-Yin; Chang, Jyh-Yeong; Lin, Chin-Teng

2013-02-01

This paper presents a novel recurrent fuzzy neural network, called an interactively recurrent self-evolving fuzzy neural network (IRSFNN), for prediction and identification of dynamic systems. The recurrent structure in an IRSFNN is formed as an external loops and internal feedback by feeding the rule firing strength of each rule to others rules and itself. The consequent part in the IRSFNN is composed of a Takagi-Sugeno-Kang (TSK) or functional-link-based type. The proposed IRSFNN employs a functional link neural network (FLNN) to the consequent part of fuzzy rules for promoting the mapping ability. Unlike a TSK-type fuzzy neural network, the FLNN in the consequent part is a nonlinear function of input variables. An IRSFNNs learning starts with an empty rule base and all of the rules are generated and learned online through a simultaneous structure and parameter learning. An on-line clustering algorithm is effective in generating fuzzy rules. The consequent update parameters are derived by a variable-dimensional Kalman filter algorithm. The premise and recurrent parameters are learned through a gradient descent algorithm. We test the IRSFNN for the prediction and identification of dynamic plants and compare it to other well-known recurrent FNNs. The proposed model obtains enhanced performance results.

Railway track circuit fault diagnosis using recurrent neural networks

NARCIS (Netherlands)

de Bruin, T.D.; Verbert, K.A.J.; Babuska, R.

2017-01-01

Timely detection and identification of faults in railway track circuits are crucial for the safety and availability of railway networks. In this paper, the use of the long-short-term memory (LSTM) recurrent neural network is proposed to accomplish these tasks based on the commonly available

Medical Concept Normalization in Social Media Posts with Recurrent Neural Networks.

Science.gov (United States)

Tutubalina, Elena; Miftahutdinov, Zulfat; Nikolenko, Sergey; Malykh, Valentin

2018-06-12

Text mining of scientific libraries and social media has already proven itself as a reliable tool for drug repurposing and hypothesis generation. The task of mapping a disease mention to a concept in a controlled vocabulary, typically to the standard thesaurus in the Unified Medical Language System (UMLS), is known as medical concept normalization. This task is challenging due to the differences in the use of medical terminology between health care professionals and social media texts coming from the lay public. To bridge this gap, we use sequence learning with recurrent neural networks and semantic representation of one- or multi-word expressions: we develop end-to-end architectures directly tailored to the task, including bidirectional Long Short-Term Memory, Gated Recurrent Units with an attention mechanism, and additional semantic similarity features based on UMLS. Our evaluation against a standard benchmark shows that recurrent neural networks improve results over an effective baseline for classification based on convolutional neural networks. A qualitative examination of mentions discovered in a dataset of user reviews collected from popular online health information platforms as well as a quantitative evaluation both show improvements in the semantic representation of health-related expressions in social media. Copyright © 2018. Published by Elsevier Inc.

Fine-tuning and the stability of recurrent neural networks.

Directory of Open Access Journals (Sweden)

David MacNeil

Full Text Available A central criticism of standard theoretical approaches to constructing stable, recurrent model networks is that the synaptic connection weights need to be finely-tuned. This criticism is severe because proposed rules for learning these weights have been shown to have various limitations to their biological plausibility. Hence it is unlikely that such rules are used to continuously fine-tune the network in vivo. We describe a learning rule that is able to tune synaptic weights in a biologically plausible manner. We demonstrate and test this rule in the context of the oculomotor integrator, showing that only known neural signals are needed to tune the weights. We demonstrate that the rule appropriately accounts for a wide variety of experimental results, and is robust under several kinds of perturbation. Furthermore, we show that the rule is able to achieve stability as good as or better than that provided by the linearly optimal weights often used in recurrent models of the integrator. Finally, we discuss how this rule can be generalized to tune a wide variety of recurrent attractor networks, such as those found in head direction and path integration systems, suggesting that it may be used to tune a wide variety of stable neural systems.

A recurrent neural network based on projection operator for extended general variational inequalities.

Science.gov (United States)

Liu, Qingshan; Cao, Jinde

2010-06-01

Based on the projection operator, a recurrent neural network is proposed for solving extended general variational inequalities (EGVIs). Sufficient conditions are provided to ensure the global convergence of the proposed neural network based on Lyapunov methods. Compared with the existing neural networks for variational inequalities, the proposed neural network is a modified version of the general projection neural network existing in the literature and capable of solving the EGVI problems. In addition, simulation results on numerical examples show the effectiveness and performance of the proposed neural network.

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

Science.gov (United States)

Liu, Qingshan; Dang, Chuangyin; Huang, Tingwen

2013-02-01

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

Recurrent Neural Network Based Boolean Factor Analysis and its Application to Word Clustering

Czech Academy of Sciences Publication Activity Database

Frolov, A. A.; Húsek, Dušan; Polyakov, P.Y.

2009-01-01

Roč. 20, č. 7 (2009), s. 1073-1086 ISSN 1045-9227 R&D Projects: GA MŠk(CZ) 1M0567 Institutional research plan: CEZ:AV0Z10300504 Keywords : recurrent neural network * Hopfield-like neural network * associative memory * unsupervised learning * neural network architecture * neural network application * statistics * Boolean factor analysis * concepts search * information retrieval Subject RIV: BB - Applied Statistics, Operational Research Impact factor: 2.889, year: 2009

Bayesian model ensembling using meta-trained recurrent neural networks

NARCIS (Netherlands)

Ambrogioni, L.; Berezutskaya, Y.; Gü ç lü , U.; Borne, E.W.P. van den; Gü ç lü tü rk, Y.; Gerven, M.A.J. van; Maris, E.G.G.

2017-01-01

In this paper we demonstrate that a recurrent neural network meta-trained on an ensemble of arbitrary classification tasks can be used as an approximation of the Bayes optimal classifier. This result is obtained by relying on the framework of e-free approximate Bayesian inference, where the Bayesian

A One-Layer Recurrent Neural Network for Constrained Complex-Variable Convex Optimization.

Science.gov (United States)

Qin, Sitian; Feng, Jiqiang; Song, Jiahui; Wen, Xingnan; Xu, Chen

2018-03-01

In this paper, based on calculus and penalty method, a one-layer recurrent neural network is proposed for solving constrained complex-variable convex optimization. It is proved that for any initial point from a given domain, the state of the proposed neural network reaches the feasible region in finite time and converges to an optimal solution of the constrained complex-variable convex optimization finally. In contrast to existing neural networks for complex-variable convex optimization, the proposed neural network has a lower model complexity and better convergence. Some numerical examples and application are presented to substantiate the effectiveness of the proposed neural network.

Bi-directional LSTM Recurrent Neural Network for Chinese Word Segmentation

OpenAIRE

Yao, Yushi; Huang, Zheng

2016-01-01

Recurrent neural network(RNN) has been broadly applied to natural language processing(NLP) problems. This kind of neural network is designed for modeling sequential data and has been testified to be quite efficient in sequential tagging tasks. In this paper, we propose to use bi-directional RNN with long short-term memory(LSTM) units for Chinese word segmentation, which is a crucial preprocess task for modeling Chinese sentences and articles. Classical methods focus on designing and combining...

A one-layer recurrent neural network for constrained nonconvex optimization.

Science.gov (United States)

Li, Guocheng; Yan, Zheng; Wang, Jun

2015-01-01

In this paper, a one-layer recurrent neural network is proposed for solving nonconvex optimization problems subject to general inequality constraints, designed based on an exact penalty function method. It is proved herein that any neuron state of the proposed neural network is convergent to the feasible region in finite time and stays there thereafter, provided that the penalty parameter is sufficiently large. The lower bounds of the penalty parameter and convergence time are also estimated. In addition, any neural state of the proposed neural network is convergent to its equilibrium point set which satisfies the Karush-Kuhn-Tucker conditions of the optimization problem. Moreover, the equilibrium point set is equivalent to the optimal solution to the nonconvex optimization problem if the objective function and constraints satisfy given conditions. Four numerical examples are provided to illustrate the performances of the proposed neural network.

Robust nonlinear autoregressive moving average model parameter estimation using stochastic recurrent artificial neural networks

DEFF Research Database (Denmark)

Chon, K H; Hoyer, D; Armoundas, A A

1999-01-01

In this study, we introduce a new approach for estimating linear and nonlinear stochastic autoregressive moving average (ARMA) model parameters, given a corrupt signal, using artificial recurrent neural networks. This new approach is a two-step approach in which the parameters of the deterministic...... part of the stochastic ARMA model are first estimated via a three-layer artificial neural network (deterministic estimation step) and then reestimated using the prediction error as one of the inputs to the artificial neural networks in an iterative algorithm (stochastic estimation step). The prediction...... error is obtained by subtracting the corrupt signal of the estimated ARMA model obtained via the deterministic estimation step from the system output response. We present computer simulation examples to show the efficacy of the proposed stochastic recurrent neural network approach in obtaining accurate...

A One-Layer Recurrent Neural Network for Pseudoconvex Optimization Problems With Equality and Inequality Constraints.

Science.gov (United States)

Qin, Sitian; Yang, Xiudong; Xue, Xiaoping; Song, Jiahui

2017-10-01

Pseudoconvex optimization problem, as an important nonconvex optimization problem, plays an important role in scientific and engineering applications. In this paper, a recurrent one-layer neural network is proposed for solving the pseudoconvex optimization problem with equality and inequality constraints. It is proved that from any initial state, the state of the proposed neural network reaches the feasible region in finite time and stays there thereafter. It is also proved that the state of the proposed neural network is convergent to an optimal solution of the related problem. Compared with the related existing recurrent neural networks for the pseudoconvex optimization problems, the proposed neural network in this paper does not need the penalty parameters and has a better convergence. Meanwhile, the proposed neural network is used to solve three nonsmooth optimization problems, and we make some detailed comparisons with the known related conclusions. In the end, some numerical examples are provided to illustrate the effectiveness of the performance of the proposed neural network.

Reactive Power Control of Single-Stage Three-Phase Photovoltaic System during Grid Faults Using Recurrent Fuzzy Cerebellar Model Articulation Neural Network

Directory of Open Access Journals (Sweden)

Faa-Jeng Lin

2014-01-01

Full Text Available This study presents a new active and reactive power control scheme for a single-stage three-phase grid-connected photovoltaic (PV system during grid faults. The presented PV system utilizes a single-stage three-phase current-controlled voltage-source inverter to achieve the maximum power point tracking (MPPT control of the PV panel with the function of low voltage ride through (LVRT. Moreover, a formula based on positive sequence voltage for evaluating the percentage of voltage sag is derived to determine the ratio of the injected reactive current to satisfy the LVRT regulations. To reduce the risk of overcurrent during LVRT operation, a current limit is predefined for the injection of reactive current. Furthermore, the control of active and reactive power is designed using a two-dimensional recurrent fuzzy cerebellar model articulation neural network (2D-RFCMANN. In addition, the online learning laws of 2D-RFCMANN are derived according to gradient descent method with varied learning-rate coefficients for network parameters to assure the convergence of the tracking error. Finally, some experimental tests are realized to validate the effectiveness of the proposed control scheme.

Analysis of Recurrent Analog Neural Networks

Directory of Open Access Journals (Sweden)

Z. Raida

1998-06-01

Full Text Available In this paper, an original rigorous analysis of recurrent analog neural networks, which are built from opamp neurons, is presented. The analysis, which comes from the approximate model of the operational amplifier, reveals causes of possible non-stable states and enables to determine convergence properties of the network. Results of the analysis are discussed in order to enable development of original robust and fast analog networks. In the analysis, the special attention is turned to the examination of the influence of real circuit elements and of the statistical parameters of processed signals to the parameters of the network.

Bifurcation analysis on a generalized recurrent neural network with two interconnected three-neuron components

International Nuclear Information System (INIS)

Hajihosseini, Amirhossein; Maleki, Farzaneh; Rokni Lamooki, Gholam Reza

2011-01-01

Highlights: → We construct a recurrent neural network by generalizing a specific n-neuron network. → Several codimension 1 and 2 bifurcations take place in the newly constructed network. → The newly constructed network has higher capabilities to learn periodic signals. → The normal form theorem is applied to investigate dynamics of the network. → A series of bifurcation diagrams is given to support theoretical results. - Abstract: A class of recurrent neural networks is constructed by generalizing a specific class of n-neuron networks. It is shown that the newly constructed network experiences generic pitchfork and Hopf codimension one bifurcations. It is also proved that the emergence of generic Bogdanov-Takens, pitchfork-Hopf and Hopf-Hopf codimension two, and the degenerate Bogdanov-Takens bifurcation points in the parameter space is possible due to the intersections of codimension one bifurcation curves. The occurrence of bifurcations of higher codimensions significantly increases the capability of the newly constructed recurrent neural network to learn broader families of periodic signals.

Probing the basins of attraction of a recurrent neural network

NARCIS (Netherlands)

Heerema, M.; van Leeuwen, W.A.

2000-01-01

Analytical expressions for the weights $w_{ij}(b)$ of the connections of a recurrent neural network are found by taking explicitly into account basins of attraction, the size of which is characterized by a basin parameter $b$. It is shown that a network with $b \

Active Control of Sound based on Diagonal Recurrent Neural Network

NARCIS (Netherlands)

Jayawardhana, Bayu; Xie, Lihua; Yuan, Shuqing

2002-01-01

Recurrent neural network has been known for its dynamic mapping and better suited for nonlinear dynamical system. Nonlinear controller may be needed in cases where the actuators exhibit the nonlinear characteristics, or in cases when the structure to be controlled exhibits nonlinear behavior. The

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

Science.gov (United States)

Liu, Qingshan; Wang, Jun

2011-04-01

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

Predicting local field potentials with recurrent neural networks.

Science.gov (United States)

Kim, Louis; Harer, Jacob; Rangamani, Akshay; Moran, James; Parks, Philip D; Widge, Alik; Eskandar, Emad; Dougherty, Darin; Chin, Sang Peter

2016-08-01

We present a Recurrent Neural Network using LSTM (Long Short Term Memory) that is capable of modeling and predicting Local Field Potentials. We train and test the network on real data recorded from epilepsy patients. We construct networks that predict multi-channel LFPs for 1, 10, and 100 milliseconds forward in time. Our results show that prediction using LSTM outperforms regression when predicting 10 and 100 millisecond forward in time.

Hysteretic recurrent neural networks: a tool for modeling hysteretic materials and systems

International Nuclear Information System (INIS)

Veeramani, Arun S; Crews, John H; Buckner, Gregory D

2009-01-01

This paper introduces a novel recurrent neural network, the hysteretic recurrent neural network (HRNN), that is ideally suited to modeling hysteretic materials and systems. This network incorporates a hysteretic neuron consisting of conjoined sigmoid activation functions. Although similar hysteretic neurons have been explored previously, the HRNN is unique in its utilization of simple recurrence to 'self-select' relevant activation functions. Furthermore, training is facilitated by placing the network weights on the output side, allowing standard backpropagation of error training algorithms to be used. We present two- and three-phase versions of the HRNN for modeling hysteretic materials with distinct phases. These models are experimentally validated using data collected from shape memory alloys and ferromagnetic materials. The results demonstrate the HRNN's ability to accurately generalize hysteretic behavior with a relatively small number of neurons. Additional benefits lie in the network's ability to identify statistical information concerning the macroscopic material by analyzing the weights of the individual neurons

Adaptive Filtering Using Recurrent Neural Networks

Science.gov (United States)

Parlos, Alexander G.; Menon, Sunil K.; Atiya, Amir F.

2005-01-01

A method for adaptive (or, optionally, nonadaptive) filtering has been developed for estimating the states of complex process systems (e.g., chemical plants, factories, or manufacturing processes at some level of abstraction) from time series of measurements of system inputs and outputs. The method is based partly on the fundamental principles of the Kalman filter and partly on the use of recurrent neural networks. The standard Kalman filter involves an assumption of linearity of the mathematical model used to describe a process system. The extended Kalman filter accommodates a nonlinear process model but still requires linearization about the state estimate. Both the standard and extended Kalman filters involve the often unrealistic assumption that process and measurement noise are zero-mean, Gaussian, and white. In contrast, the present method does not involve any assumptions of linearity of process models or of the nature of process noise; on the contrary, few (if any) assumptions are made about process models, noise models, or the parameters of such models. In this regard, the method can be characterized as one of nonlinear, nonparametric filtering. The method exploits the unique ability of neural networks to approximate nonlinear functions. In a given case, the process model is limited mainly by limitations of the approximation ability of the neural networks chosen for that case. Moreover, despite the lack of assumptions regarding process noise, the method yields minimum- variance filters. In that they do not require statistical models of noise, the neural- network-based state filters of this method are comparable to conventional nonlinear least-squares estimators.

ReSeg: A Recurrent Neural Network-Based Model for Semantic Segmentation

OpenAIRE

Visin, Francesco; Ciccone, Marco; Romero, Adriana; Kastner, Kyle; Cho, Kyunghyun; Bengio, Yoshua; Matteucci, Matteo; Courville, Aaron

2015-01-01

We propose a structured prediction architecture, which exploits the local generic features extracted by Convolutional Neural Networks and the capacity of Recurrent Neural Networks (RNN) to retrieve distant dependencies. The proposed architecture, called ReSeg, is based on the recently introduced ReNet model for image classification. We modify and extend it to perform the more challenging task of semantic segmentation. Each ReNet layer is composed of four RNN that sweep the image horizontally ...

Individual Identification Using Functional Brain Fingerprint Detected by Recurrent Neural Network.

Science.gov (United States)

Chen, Shiyang; Hu, Xiaoping P

2018-03-20

Individual identification based on brain function has gained traction in literature. Investigating individual differences in brain function can provide additional insights into the brain. In this work, we introduce a recurrent neural network based model for identifying individuals based on only a short segment of resting state functional MRI data. In addition, we demonstrate how the global signal and differences in atlases affect the individual identifiability. Furthermore, we investigate neural network features that exhibit the uniqueness of each individual. The results indicate that our model is able to identify individuals based on neural features and provides additional information regarding brain dynamics.

Boundedness and stability for recurrent neural networks with variable coefficients and time-varying delays

International Nuclear Information System (INIS)

Liang Jinling; Cao Jinde

2003-01-01

In this Letter, the problems of boundedness and stability for a general class of non-autonomous recurrent neural networks with variable coefficients and time-varying delays are analyzed via employing Young inequality technique and Lyapunov method. Some simple sufficient conditions are given for boundedness and stability of the solutions for the recurrent neural networks. These results generalize and improve the previous works, and they are easy to check and apply in practice. Two illustrative examples and their numerical simulations are also given to demonstrate the effectiveness of the proposed results

Deep Recurrent Neural Network-Based Autoencoders for Acoustic Novelty Detection

Directory of Open Access Journals (Sweden)

Erik Marchi

2017-01-01

Full Text Available In the emerging field of acoustic novelty detection, most research efforts are devoted to probabilistic approaches such as mixture models or state-space models. Only recent studies introduced (pseudo-generative models for acoustic novelty detection with recurrent neural networks in the form of an autoencoder. In these approaches, auditory spectral features of the next short term frame are predicted from the previous frames by means of Long-Short Term Memory recurrent denoising autoencoders. The reconstruction error between the input and the output of the autoencoder is used as activation signal to detect novel events. There is no evidence of studies focused on comparing previous efforts to automatically recognize novel events from audio signals and giving a broad and in depth evaluation of recurrent neural network-based autoencoders. The present contribution aims to consistently evaluate our recent novel approaches to fill this white spot in the literature and provide insight by extensive evaluations carried out on three databases: A3Novelty, PASCAL CHiME, and PROMETHEUS. Besides providing an extensive analysis of novel and state-of-the-art methods, the article shows how RNN-based autoencoders outperform statistical approaches up to an absolute improvement of 16.4% average F-measure over the three databases.

Deep Recurrent Neural Network-Based Autoencoders for Acoustic Novelty Detection.

Science.gov (United States)

Marchi, Erik; Vesperini, Fabio; Squartini, Stefano; Schuller, Björn

2017-01-01

In the emerging field of acoustic novelty detection, most research efforts are devoted to probabilistic approaches such as mixture models or state-space models. Only recent studies introduced (pseudo-)generative models for acoustic novelty detection with recurrent neural networks in the form of an autoencoder. In these approaches, auditory spectral features of the next short term frame are predicted from the previous frames by means of Long-Short Term Memory recurrent denoising autoencoders. The reconstruction error between the input and the output of the autoencoder is used as activation signal to detect novel events. There is no evidence of studies focused on comparing previous efforts to automatically recognize novel events from audio signals and giving a broad and in depth evaluation of recurrent neural network-based autoencoders. The present contribution aims to consistently evaluate our recent novel approaches to fill this white spot in the literature and provide insight by extensive evaluations carried out on three databases: A3Novelty, PASCAL CHiME, and PROMETHEUS. Besides providing an extensive analysis of novel and state-of-the-art methods, the article shows how RNN-based autoencoders outperform statistical approaches up to an absolute improvement of 16.4% average F -measure over the three databases.

Binary Factorization in Hopfield-Like Neural Networks: Single-Step Approximation and Computer Simulations

Czech Academy of Sciences Publication Activity Database

Frolov, A. A.; Sirota, A.M.; Húsek, Dušan; Muraviev, I. P.

2004-01-01

Roč. 14, č. 2 (2004), s. 139-152 ISSN 1210-0552 R&D Projects: GA ČR GA201/01/1192 Grant - others:BARRANDE(EU) 99010-2/99053; Intellectual computer Systems(EU) Grant 2.45 Institutional research plan: CEZ:AV0Z1030915 Keywords : nonlinear binary factor analysis * feature extraction * recurrent neural network * Single-Step approximation * neurodynamics simulation * attraction basins * Hebbian learning * unsupervised learning * neuroscience * brain function modeling Subject RIV: BA - General Mathematics

Bach in 2014: Music Composition with Recurrent Neural Network

OpenAIRE

Liu, I-Ting; Ramakrishnan, Bhiksha

2014-01-01

We propose a framework for computer music composition that uses resilient propagation (RProp) and long short term memory (LSTM) recurrent neural network. In this paper, we show that LSTM network learns the structure and characteristics of music pieces properly by demonstrating its ability to recreate music. We also show that predicting existing music using RProp outperforms Back propagation through time (BPTT).

Convolutional neural networks for prostate cancer recurrence prediction

Science.gov (United States)

Kumar, Neeraj; Verma, Ruchika; Arora, Ashish; Kumar, Abhay; Gupta, Sanchit; Sethi, Amit; Gann, Peter H.

2017-03-01

Accurate prediction of the treatment outcome is important for cancer treatment planning. We present an approach to predict prostate cancer (PCa) recurrence after radical prostatectomy using tissue images. We used a cohort whose case vs. control (recurrent vs. non-recurrent) status had been determined using post-treatment follow up. Further, to aid the development of novel biomarkers of PCa recurrence, cases and controls were paired based on matching of other predictive clinical variables such as Gleason grade, stage, age, and race. For this cohort, tissue resection microarray with up to four cores per patient was available. The proposed approach is based on deep learning, and its novelty lies in the use of two separate convolutional neural networks (CNNs) - one to detect individual nuclei even in the crowded areas, and the other to classify them. To detect nuclear centers in an image, the first CNN predicts distance transform of the underlying (but unknown) multi-nuclear map from the input HE image. The second CNN classifies the patches centered at nuclear centers into those belonging to cases or controls. Voting across patches extracted from image(s) of a patient yields the probability of recurrence for the patient. The proposed approach gave 0.81 AUC for a sample of 30 recurrent cases and 30 non-recurrent controls, after being trained on an independent set of 80 case-controls pairs. If validated further, such an approach might help in choosing between a combination of treatment options such as active surveillance, radical prostatectomy, radiation, and hormone therapy. It can also generalize to the prediction of treatment outcomes in other cancers.

A one-layer recurrent neural network for constrained nonsmooth invex optimization.

Science.gov (United States)

Li, Guocheng; Yan, Zheng; Wang, Jun

2014-02-01

Invexity is an important notion in nonconvex optimization. In this paper, a one-layer recurrent neural network is proposed for solving constrained nonsmooth invex optimization problems, designed based on an exact penalty function method. It is proved herein that any state of the proposed neural network is globally convergent to the optimal solution set of constrained invex optimization problems, with a sufficiently large penalty parameter. In addition, any neural state is globally convergent to the unique optimal solution, provided that the objective function and constraint functions are pseudoconvex. Moreover, any neural state is globally convergent to the feasible region in finite time and stays there thereafter. The lower bounds of the penalty parameter and convergence time are also estimated. Two numerical examples are provided to illustrate the performances of the proposed neural network. Copyright © 2013 Elsevier Ltd. All rights reserved.

A two-layer recurrent neural network for nonsmooth convex optimization problems.

Science.gov (United States)

Qin, Sitian; Xue, Xiaoping

2015-06-01

In this paper, a two-layer recurrent neural network is proposed to solve the nonsmooth convex optimization problem subject to convex inequality and linear equality constraints. Compared with existing neural network models, the proposed neural network has a low model complexity and avoids penalty parameters. It is proved that from any initial point, the state of the proposed neural network reaches the equality feasible region in finite time and stays there thereafter. Moreover, the state is unique if the initial point lies in the equality feasible region. The equilibrium point set of the proposed neural network is proved to be equivalent to the Karush-Kuhn-Tucker optimality set of the original optimization problem. It is further proved that the equilibrium point of the proposed neural network is stable in the sense of Lyapunov. Moreover, from any initial point, the state is proved to be convergent to an equilibrium point of the proposed neural network. Finally, as applications, the proposed neural network is used to solve nonlinear convex programming with linear constraints and L1 -norm minimization problems.

Using a multi-state recurrent neural network to optimize loading patterns in BWRs

International Nuclear Information System (INIS)

Ortiz, Juan Jose; Requena, Ignacio

2004-01-01

A Multi-State Recurrent Neural Network is used to optimize Loading Patterns (LP) in BWRs. We have proposed an energy function that depends on fuel assembly positions and their nuclear cross sections to carry out optimisation. Multi-State Recurrent Neural Networks creates LPs that satisfy the Radial Power Peaking Factor and maximize the effective multiplication factor at the Beginning of the Cycle, and also satisfy the Minimum Critical Power Ratio and Maximum Linear Heat Generation Rate at the End of the Cycle, thereby maximizing the effective multiplication factor. In order to evaluate the LPs, we have used a trained back-propagation neural network to predict the parameter values, instead of using a reactor core simulator, which saved considerable computation time in the search process. We applied this method to find optimal LPs for five cycles of Laguna Verde Nuclear Power Plant (LVNPP) in Mexico

Evaluation of the Performance of Feedforward and Recurrent Neural Networks in Active Cancellation of Sound Noise

OpenAIRE

Mehrshad Salmasi; Homayoun Mahdavi-Nasab

2012-01-01

Active noise control is based on the destructive interference between the primary noise and generated noise from the secondary source. An antinoise of equal amplitude and opposite phase is generated and combined with the primary noise. In this paper, performance of the neural networks is evaluated in active cancellation of sound noise. For this reason, feedforward and recurrent neural networks are designed and trained. After training, performance of the feedforwrad and recurrent networks in n...

A recurrent neural network for solving bilevel linear programming problem.

Science.gov (United States)

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

2014-04-01

In this brief, based on the method of penalty functions, a recurrent neural network (NN) modeled by means of a differential inclusion is proposed for solving the bilevel linear programming problem (BLPP). Compared with the existing NNs for BLPP, the model has the least number of state variables and simple structure. Using nonsmooth analysis, the theory of differential inclusions, and Lyapunov-like method, the equilibrium point sequence of the proposed NNs can approximately converge to an optimal solution of BLPP under certain conditions. Finally, the numerical simulations of a supply chain distribution model have shown excellent performance of the proposed recurrent NNs.

Deep Convolutional and LSTM Recurrent Neural Networks for Multimodal Wearable Activity Recognition

OpenAIRE

Francisco Javier Ordóñez; Daniel Roggen

2016-01-01

Human activity recognition (HAR) tasks have traditionally been solved using engineered features obtained by heuristic processes. Current research suggests that deep convolutional neural networks are suited to automate feature extraction from raw sensor inputs. However, human activities are made of complex sequences of motor movements, and capturing this temporal dynamics is fundamental for successful HAR. Based on the recent success of recurrent neural networks for time series domains, we pro...

Prediction of Bladder Cancer Recurrences Using Artificial Neural Networks

Science.gov (United States)

Zulueta Guerrero, Ekaitz; Garay, Naiara Telleria; Lopez-Guede, Jose Manuel; Vilches, Borja Ayerdi; Iragorri, Eider Egilegor; Castaños, David Lecumberri; de La Hoz Rastrollo, Ana Belén; Peña, Carlos Pertusa

Even if considerable advances have been made in the field of early diagnosis, there is no simple, cheap and non-invasive method that can be applied to the clinical monitorisation of bladder cancer patients. Moreover, bladder cancer recurrences or the reappearance of the tumour after its surgical resection cannot be predicted in the current clinical setting. In this study, Artificial Neural Networks (ANN) were used to assess how different combinations of classical clinical parameters (stage-grade and age) and two urinary markers (growth factor and pro-inflammatory mediator) could predict post surgical recurrences in bladder cancer patients. Different ANN methods, input parameter combinations and recurrence related output variables were used and the resulting positive and negative prediction rates compared. MultiLayer Perceptron (MLP) was selected as the most predictive model and urinary markers showed the highest sensitivity, predicting correctly 50% of the patients that would recur in a 2 year follow-up period.

Web server's reliability improvements using recurrent neural networks

DEFF Research Database (Denmark)

Madsen, Henrik; Albu, Rǎzvan-Daniel; Felea, Ioan

2012-01-01

In this paper we describe an interesting approach to error prediction illustrated by experimental results. The application consists of monitoring the activity for the web servers in order to collect the specific data. Predicting an error with severe consequences for the performance of a server (t...... usage, network usage and memory usage. We collect different data sets from monitoring the web server's activity and for each one we predict the server's reliability with the proposed recurrent neural network. © 2012 Taylor & Francis Group...

Evaluation of the cranial base in amnion rupture sequence involving the anterior neural tube: implications regarding recurrence risk.

Science.gov (United States)

Jones, Kenneth Lyons; Robinson, Luther K; Benirschke, Kurt

2006-09-01

Amniotic bands can cause disruption of the cranial end of the developing fetus, leading in some cases to a neural tube closure defect. Although recurrence for unaffected parents of an affected child with a defect in which the neural tube closed normally but was subsequently disrupted by amniotic bands is negligible; for a primary defect in closure of the neural tube to which amnion has subsequently adhered, recurrence risk is 1.7%. In that primary defects of neural tube closure are characterized by typical abnormalities of the base of the skull, evaluation of the cranial base in such fetuses provides an approach for making a distinction between these 2 mechanisms. This distinction has implications regarding recurrence risk. The skull base of 2 fetuses with amnion rupture sequence involving the cranial end of the neural tube were compared to that of 1 fetus with anencephaly as well as that of a structurally normal fetus. The skulls were cleaned, fixed in 10% formalin, recleaned, and then exposed to 10% KOH solution. After washing and recleaning, the skulls were exposed to hydrogen peroxide for bleaching and photography. Despite involvement of the anterior neural tube in both fetuses with amnion rupture sequence, in Case 3 the cranial base was normal while in Case 4 the cranial base was similar to that seen in anencephaly. This technique provides a method for determining the developmental pathogenesis of anterior neural tube defects in cases of amnion rupture sequence. As such, it provides information that can be used to counsel parents of affected children with respect to recurrence risk.

Diagonal recurrent neural network based adaptive control of nonlinear dynamical systems using lyapunov stability criterion.

Science.gov (United States)

Kumar, Rajesh; Srivastava, Smriti; Gupta, J R P

2017-03-01

In this paper adaptive control of nonlinear dynamical systems using diagonal recurrent neural network (DRNN) is proposed. The structure of DRNN is a modification of fully connected recurrent neural network (FCRNN). Presence of self-recurrent neurons in the hidden layer of DRNN gives it an ability to capture the dynamic behaviour of the nonlinear plant under consideration (to be controlled). To ensure stability, update rules are developed using lyapunov stability criterion. These rules are then used for adjusting the various parameters of DRNN. The responses of plants obtained with DRNN are compared with those obtained when multi-layer feed forward neural network (MLFFNN) is used as a controller. Also, in example 4, FCRNN is also investigated and compared with DRNN and MLFFNN. Robustness of the proposed control scheme is also tested against parameter variations and disturbance signals. Four simulation examples including one-link robotic manipulator and inverted pendulum are considered on which the proposed controller is applied. The results so obtained show the superiority of DRNN over MLFFNN as a controller. Copyright © 2017 ISA. Published by Elsevier Ltd. All rights reserved.

A Novel Neural Network Vector Control for Single-Phase Grid-Connected Converters with L, LC and LCL Filters

Directory of Open Access Journals (Sweden)

Xingang Fu

2016-04-01

Full Text Available This paper investigates a novel recurrent neural network (NN-based vector control approach for single-phase grid-connected converters (GCCs with L (inductor, LC (inductor-capacitor and LCL (inductor-capacitor-inductor filters and provides their comparison study with the conventional standard vector control method. A single neural network controller replaces two current-loop PI controllers, and the NN training approximates the optimal control for the single-phase GCC system. The Levenberg–Marquardt (LM algorithm was used to train the NN controller based on the complete system equations without any decoupling policies. The proposed NN approach can solve the decoupling problem associated with the conventional vector control methods for L, LC and LCL-filter-based single-phase GCCs. Both simulation study and hardware experiments demonstrate that the neural network vector controller shows much more improved performance than that of conventional vector controllers, including faster response speed and lower overshoot. Especially, NN vector control could achieve very good performance using low switch frequency. More importantly, the neural network vector controller is a damping free controller, which is generally required by a conventional vector controller for an LCL-filter-based single-phase grid-connected converter and, therefore, can overcome the inefficiency problem caused by damping policies.

Encoding of phonology in a recurrent neural model of grounded speech

NARCIS (Netherlands)

Alishahi, Afra; Barking, Marie; Chrupala, Grzegorz; Levy, Roger; Specia, Lucia

2017-01-01

We study the representation and encoding of phonemes in a recurrent neural network model of grounded speech. We use a model which processes images and their spoken descriptions, and projects the visual and auditory representations into the same semantic space. We perform a number of analyses on how

Detection of nonstationary transition to synchronized states of a neural network using recurrence analyses

Science.gov (United States)

Budzinski, R. C.; Boaretto, B. R. R.; Prado, T. L.; Lopes, S. R.

2017-07-01

We study the stability of asymptotic states displayed by a complex neural network. We focus on the loss of stability of a stationary state of networks using recurrence quantifiers as tools to diagnose local and global stabilities as well as the multistability of a coupled neural network. Numerical simulations of a neural network composed of 1024 neurons in a small-world connection scheme are performed using the model of Braun et al. [Int. J. Bifurcation Chaos 08, 881 (1998), 10.1142/S0218127498000681], which is a modified model from the Hodgkin-Huxley model [J. Phys. 117, 500 (1952)]. To validate the analyses, the results are compared with those produced by Kuramoto's order parameter [Chemical Oscillations, Waves, and Turbulence (Springer-Verlag, Berlin Heidelberg, 1984)]. We show that recurrence tools making use of just integrated signals provided by the networks, such as local field potential (LFP) (LFP signals) or mean field values bring new results on the understanding of neural behavior occurring before the synchronization states. In particular we show the occurrence of different stationary and nonstationarity asymptotic states.

Classification of conductance traces with recurrent neural networks

Science.gov (United States)

Lauritzen, Kasper P.; Magyarkuti, András; Balogh, Zoltán; Halbritter, András; Solomon, Gemma C.

2018-02-01

We present a new automated method for structural classification of the traces obtained in break junction experiments. Using recurrent neural networks trained on the traces of minimal cross-sectional area in molecular dynamics simulations, we successfully separate the traces into two classes: point contact or nanowire. This is done without any assumptions about the expected features of each class. The trained neural network is applied to experimental break junction conductance traces, and it separates the classes as well as the previously used experimental methods. The effect of using partial conductance traces is explored, and we show that the method performs equally well using full or partial traces (as long as the trace just prior to breaking is included). When only the initial part of the trace is included, the results are still better than random chance. Finally, we show that the neural network classification method can be used to classify experimental conductance traces without using simulated results for training, but instead training the network on a few representative experimental traces. This offers a tool to recognize some characteristic motifs of the traces, which can be hard to find by simple data selection algorithms.

Direction-of-change forecasting using a volatility-based recurrent neural network

NARCIS (Netherlands)

Bekiros, S.D.; Georgoutsos, D.A.

2008-01-01

This paper investigates the profitability of a trading strategy, based on recurrent neural networks, that attempts to predict the direction-of-change of the market in the case of the NASDAQ composite index. The sample extends over the period 8 February 1971 to 7 April 1998, while the sub-period 8

Interpretation of correlated neural variability from models of feed-forward and recurrent circuits

Science.gov (United States)

2018-01-01

Neural populations respond to the repeated presentations of a sensory stimulus with correlated variability. These correlations have been studied in detail, with respect to their mechanistic origin, as well as their influence on stimulus discrimination and on the performance of population codes. A number of theoretical studies have endeavored to link network architecture to the nature of the correlations in neural activity. Here, we contribute to this effort: in models of circuits of stochastic neurons, we elucidate the implications of various network architectures—recurrent connections, shared feed-forward projections, and shared gain fluctuations—on the stimulus dependence in correlations. Specifically, we derive mathematical relations that specify the dependence of population-averaged covariances on firing rates, for different network architectures. In turn, these relations can be used to analyze data on population activity. We examine recordings from neural populations in mouse auditory cortex. We find that a recurrent network model with random effective connections captures the observed statistics. Furthermore, using our circuit model, we investigate the relation between network parameters, correlations, and how well different stimuli can be discriminated from one another based on the population activity. As such, our approach allows us to relate properties of the neural circuit to information processing. PMID:29408930

Interpretation of correlated neural variability from models of feed-forward and recurrent circuits.

Directory of Open Access Journals (Sweden)

Volker Pernice

2018-02-01

Full Text Available Neural populations respond to the repeated presentations of a sensory stimulus with correlated variability. These correlations have been studied in detail, with respect to their mechanistic origin, as well as their influence on stimulus discrimination and on the performance of population codes. A number of theoretical studies have endeavored to link network architecture to the nature of the correlations in neural activity. Here, we contribute to this effort: in models of circuits of stochastic neurons, we elucidate the implications of various network architectures-recurrent connections, shared feed-forward projections, and shared gain fluctuations-on the stimulus dependence in correlations. Specifically, we derive mathematical relations that specify the dependence of population-averaged covariances on firing rates, for different network architectures. In turn, these relations can be used to analyze data on population activity. We examine recordings from neural populations in mouse auditory cortex. We find that a recurrent network model with random effective connections captures the observed statistics. Furthermore, using our circuit model, we investigate the relation between network parameters, correlations, and how well different stimuli can be discriminated from one another based on the population activity. As such, our approach allows us to relate properties of the neural circuit to information processing.

Estimating Ads’ Click through Rate with Recurrent Neural Network

Directory of Open Access Journals (Sweden)

Chen Qiao-Hong

2016-01-01

Full Text Available With the development of the Internet, online advertising spreads across every corner of the world, the ads' click through rate (CTR estimation is an important method to improve the online advertising revenue. Compared with the linear model, the nonlinear models can study much more complex relationships between a large number of nonlinear characteristics, so as to improve the accuracy of the estimation of the ads’ CTR. The recurrent neural network (RNN based on Long-Short Term Memory (LSTM is an improved model of the feedback neural network with ring structure. The model overcomes the problem of the gradient of the general RNN. Experiments show that the RNN based on LSTM exceeds the linear models, and it can effectively improve the estimation effect of the ads’ click through rate.

A Novel Recurrent Neural Network for Manipulator Control With Improved Noise Tolerance.

Science.gov (United States)

Li, Shuai; Wang, Huanqing; Rafique, Muhammad Usman

2017-04-12

In this paper, we propose a novel recurrent neural network to resolve the redundancy of manipulators for efficient kinematic control in the presence of noises in a polynomial type. Leveraging the high-order derivative properties of polynomial noises, a deliberately devised neural network is proposed to eliminate the impact of noises and recover the accurate tracking of desired trajectories in workspace. Rigorous analysis shows that the proposed neural law stabilizes the system dynamics and the position tracking error converges to zero in the presence of noises. Extensive simulations verify the theoretical results. Numerical comparisons show that existing dual neural solutions lose stability when exposed to large constant noises or time-varying noises. In contrast, the proposed approach works well and has a low tracking error comparable to noise-free situations.

Firing rate dynamics in recurrent spiking neural networks with intrinsic and network heterogeneity.

Science.gov (United States)

Ly, Cheng

2015-12-01

Heterogeneity of neural attributes has recently gained a lot of attention and is increasing recognized as a crucial feature in neural processing. Despite its importance, this physiological feature has traditionally been neglected in theoretical studies of cortical neural networks. Thus, there is still a lot unknown about the consequences of cellular and circuit heterogeneity in spiking neural networks. In particular, combining network or synaptic heterogeneity and intrinsic heterogeneity has yet to be considered systematically despite the fact that both are known to exist and likely have significant roles in neural network dynamics. In a canonical recurrent spiking neural network model, we study how these two forms of heterogeneity lead to different distributions of excitatory firing rates. To analytically characterize how these types of heterogeneities affect the network, we employ a dimension reduction method that relies on a combination of Monte Carlo simulations and probability density function equations. We find that the relationship between intrinsic and network heterogeneity has a strong effect on the overall level of heterogeneity of the firing rates. Specifically, this relationship can lead to amplification or attenuation of firing rate heterogeneity, and these effects depend on whether the recurrent network is firing asynchronously or rhythmically firing. These observations are captured with the aforementioned reduction method, and furthermore simpler analytic descriptions based on this dimension reduction method are developed. The final analytic descriptions provide compact and descriptive formulas for how the relationship between intrinsic and network heterogeneity determines the firing rate heterogeneity dynamics in various settings.

Multi-stability and almost periodic solutions of a class of recurrent neural networks

International Nuclear Information System (INIS)

Liu Yiguang; You Zhisheng

2007-01-01

This paper studies multi-stability, existence of almost periodic solutions of a class of recurrent neural networks with bounded activation functions. After introducing a sufficient condition insuring multi-stability, many criteria guaranteeing existence of almost periodic solutions are derived using Mawhin's coincidence degree theory. All the criteria are constructed without assuming the activation functions are smooth, monotonic or Lipschitz continuous, and that the networks contains periodic variables (such as periodic coefficients, periodic inputs or periodic activation functions), so all criteria can be easily extended to fit many concrete forms of neural networks such as Hopfield neural networks, or cellular neural networks, etc. Finally, all kinds of simulations are employed to illustrate the criteria

Study of hourly and daily solar irradiation forecast using diagonal recurrent wavelet neural networks

International Nuclear Information System (INIS)

Cao Jiacong; Lin Xingchun

2008-01-01

An accurate forecast of solar irradiation is required for various solar energy applications and environmental impact analyses in recent years. Comparatively, various irradiation forecast models based on artificial neural networks (ANN) perform much better in accuracy than many conventional prediction models. However, the forecast precision of most existing ANN based forecast models has not been satisfactory to researchers and engineers so far, and the generalization capability of these networks needs further improving. Combining the prominent dynamic properties of a recurrent neural network (RNN) with the enhanced ability of a wavelet neural network (WNN) in mapping nonlinear functions, a diagonal recurrent wavelet neural network (DRWNN) is newly established in this paper to perform fine forecasting of hourly and daily global solar irradiance. Some additional steps, e.g. applying historical information of cloud cover to sample data sets and the cloud cover from the weather forecast to network input, are adopted to help enhance the forecast precision. Besides, a specially scheduled two phase training algorithm is adopted. As examples, both hourly and daily irradiance forecasts are completed using sample data sets in Shanghai and Macau, and comparisons between irradiation models show that the DRWNN models are definitely more accurate

Simultaneous multichannel signal transfers via chaos in a recurrent neural network.

Science.gov (United States)

Soma, Ken-ichiro; Mori, Ryota; Sato, Ryuichi; Furumai, Noriyuki; Nara, Shigetoshi

2015-05-01

We propose neural network model that demonstrates the phenomenon of signal transfer between separated neuron groups via other chaotic neurons that show no apparent correlations with the input signal. The model is a recurrent neural network in which it is supposed that synchronous behavior between small groups of input and output neurons has been learned as fragments of high-dimensional memory patterns, and depletion of neural connections results in chaotic wandering dynamics. Computer experiments show that when a strong oscillatory signal is applied to an input group in the chaotic regime, the signal is successfully transferred to the corresponding output group, although no correlation is observed between the input signal and the intermediary neurons. Signal transfer is also observed when multiple signals are applied simultaneously to separate input groups belonging to different memory attractors. In this sense simultaneous multichannel communications are realized, and the chaotic neural dynamics acts as a signal transfer medium in which the signal appears to be hidden.

A novel recurrent neural network with one neuron and finite-time convergence for k-winners-take-all operation.

Science.gov (United States)

Liu, Qingshan; Dang, Chuangyin; Cao, Jinde

2010-07-01

In this paper, based on a one-neuron recurrent neural network, a novel k-winners-take-all ( k -WTA) network is proposed. Finite time convergence of the proposed neural network is proved using the Lyapunov method. The k-WTA operation is first converted equivalently into a linear programming problem. Then, a one-neuron recurrent neural network is proposed to get the kth or (k+1)th largest inputs of the k-WTA problem. Furthermore, a k-WTA network is designed based on the proposed neural network to perform the k-WTA operation. Compared with the existing k-WTA networks, the proposed network has simple structure and finite time convergence. In addition, simulation results on numerical examples show the effectiveness and performance of the proposed k-WTA network.

Indirect intelligent sliding mode control of a shape memory alloy actuated flexible beam using hysteretic recurrent neural networks

International Nuclear Information System (INIS)

Hannen, Jennifer C; Buckner, Gregory D; Crews, John H

2012-01-01

This paper introduces an indirect intelligent sliding mode controller (IISMC) for shape memory alloy (SMA) actuators, specifically a flexible beam deflected by a single offset SMA tendon. The controller manipulates applied voltage, which alters SMA tendon temperature to track reference bending angles. A hysteretic recurrent neural network (HRNN) captures the nonlinear, hysteretic relationship between SMA temperature and bending angle. The variable structure control strategy provides robustness to model uncertainties and parameter variations, while effectively compensating for system nonlinearities, achieving superior tracking compared to an optimized PI controller. (paper)

Global stability of discrete-time recurrent neural networks with impulse effects

International Nuclear Information System (INIS)

Zhou, L; Li, C; Wan, J

2008-01-01

This paper formulates and studies a class of discrete-time recurrent neural networks with impulse effects. A stability criterion, which characterizes the effects of impulse and stability property of the corresponding impulse-free networks on the stability of the impulsive networks in an aggregate form, is established. Two simplified and numerically tractable criteria are also provided

Deep Convolutional and LSTM Recurrent Neural Networks for Multimodal Wearable Activity Recognition

Directory of Open Access Journals (Sweden)

Francisco Javier Ordóñez

2016-01-01

Full Text Available Human activity recognition (HAR tasks have traditionally been solved using engineered features obtained by heuristic processes. Current research suggests that deep convolutional neural networks are suited to automate feature extraction from raw sensor inputs. However, human activities are made of complex sequences of motor movements, and capturing this temporal dynamics is fundamental for successful HAR. Based on the recent success of recurrent neural networks for time series domains, we propose a generic deep framework for activity recognition based on convolutional and LSTM recurrent units, which: (i is suitable for multimodal wearable sensors; (ii can perform sensor fusion naturally; (iii does not require expert knowledge in designing features; and (iv explicitly models the temporal dynamics of feature activations. We evaluate our framework on two datasets, one of which has been used in a public activity recognition challenge. Our results show that our framework outperforms competing deep non-recurrent networks on the challenge dataset by 4% on average; outperforming some of the previous reported results by up to 9%. Our results show that the framework can be applied to homogeneous sensor modalities, but can also fuse multimodal sensors to improve performance. We characterise key architectural hyperparameters’ influence on performance to provide insights about their optimisation.

Deep Convolutional and LSTM Recurrent Neural Networks for Multimodal Wearable Activity Recognition.

Science.gov (United States)

Ordóñez, Francisco Javier; Roggen, Daniel

2016-01-18

Human activity recognition (HAR) tasks have traditionally been solved using engineered features obtained by heuristic processes. Current research suggests that deep convolutional neural networks are suited to automate feature extraction from raw sensor inputs. However, human activities are made of complex sequences of motor movements, and capturing this temporal dynamics is fundamental for successful HAR. Based on the recent success of recurrent neural networks for time series domains, we propose a generic deep framework for activity recognition based on convolutional and LSTM recurrent units, which: (i) is suitable for multimodal wearable sensors; (ii) can perform sensor fusion naturally; (iii) does not require expert knowledge in designing features; and (iv) explicitly models the temporal dynamics of feature activations. We evaluate our framework on two datasets, one of which has been used in a public activity recognition challenge. Our results show that our framework outperforms competing deep non-recurrent networks on the challenge dataset by 4% on average; outperforming some of the previous reported results by up to 9%. Our results show that the framework can be applied to homogeneous sensor modalities, but can also fuse multimodal sensors to improve performance. We characterise key architectural hyperparameters' influence on performance to provide insights about their optimisation.

Deep Convolutional and LSTM Recurrent Neural Networks for Multimodal Wearable Activity Recognition

Science.gov (United States)

Ordóñez, Francisco Javier; Roggen, Daniel

2016-01-01

Human activity recognition (HAR) tasks have traditionally been solved using engineered features obtained by heuristic processes. Current research suggests that deep convolutional neural networks are suited to automate feature extraction from raw sensor inputs. However, human activities are made of complex sequences of motor movements, and capturing this temporal dynamics is fundamental for successful HAR. Based on the recent success of recurrent neural networks for time series domains, we propose a generic deep framework for activity recognition based on convolutional and LSTM recurrent units, which: (i) is suitable for multimodal wearable sensors; (ii) can perform sensor fusion naturally; (iii) does not require expert knowledge in designing features; and (iv) explicitly models the temporal dynamics of feature activations. We evaluate our framework on two datasets, one of which has been used in a public activity recognition challenge. Our results show that our framework outperforms competing deep non-recurrent networks on the challenge dataset by 4% on average; outperforming some of the previous reported results by up to 9%. Our results show that the framework can be applied to homogeneous sensor modalities, but can also fuse multimodal sensors to improve performance. We characterise key architectural hyperparameters’ influence on performance to provide insights about their optimisation. PMID:26797612

A novel word spotting method based on recurrent neural networks.

Science.gov (United States)

Frinken, Volkmar; Fischer, Andreas; Manmatha, R; Bunke, Horst

2012-02-01

Keyword spotting refers to the process of retrieving all instances of a given keyword from a document. In the present paper, a novel keyword spotting method for handwritten documents is described. It is derived from a neural network-based system for unconstrained handwriting recognition. As such it performs template-free spotting, i.e., it is not necessary for a keyword to appear in the training set. The keyword spotting is done using a modification of the CTC Token Passing algorithm in conjunction with a recurrent neural network. We demonstrate that the proposed systems outperform not only a classical dynamic time warping-based approach but also a modern keyword spotting system, based on hidden Markov models. Furthermore, we analyze the performance of the underlying neural networks when using them in a recognition task followed by keyword spotting on the produced transcription. We point out the advantages of keyword spotting when compared to classic text line recognition.

Model for a flexible motor memory based on a self-active recurrent neural network.

Science.gov (United States)

Boström, Kim Joris; Wagner, Heiko; Prieske, Markus; de Lussanet, Marc

2013-10-01

Using recent recurrent network architecture based on the reservoir computing approach, we propose and numerically simulate a model that is focused on the aspects of a flexible motor memory for the storage of elementary movement patterns into the synaptic weights of a neural network, so that the patterns can be retrieved at any time by simple static commands. The resulting motor memory is flexible in that it is capable to continuously modulate the stored patterns. The modulation consists in an approximately linear inter- and extrapolation, generating a large space of possible movements that have not been learned before. A recurrent network of thousand neurons is trained in a manner that corresponds to a realistic exercising scenario, with experimentally measured muscular activations and with kinetic data representing proprioceptive feedback. The network is "self-active" in that it maintains recurrent flow of activation even in the absence of input, a feature that resembles the "resting-state activity" found in the human and animal brain. The model involves the concept of "neural outsourcing" which amounts to the permanent shifting of computational load from higher to lower-level neural structures, which might help to explain why humans are able to execute learned skills in a fluent and flexible manner without the need for attention to the details of the movement. Copyright © 2013 Elsevier B.V. All rights reserved.

Global exponential stability for reaction-diffusion recurrent neural networks with multiple time varying delays

International Nuclear Information System (INIS)

Lou, X.; Cui, B.

2008-01-01

In this paper we consider the problem of exponential stability for recurrent neural networks with multiple time varying delays and reaction-diffusion terms. The activation functions are supposed to be bounded and globally Lipschitz continuous. By means of Lyapunov functional, sufficient conditions are derived, which guarantee global exponential stability of the delayed neural network. Finally, a numerical example is given to show the correctness of our analysis. (author)

Indirect adaptive fuzzy wavelet neural network with self- recurrent consequent part for AC servo system.

Science.gov (United States)

Hou, Runmin; Wang, Li; Gao, Qiang; Hou, Yuanglong; Wang, Chao

2017-09-01

This paper proposes a novel indirect adaptive fuzzy wavelet neural network (IAFWNN) to control the nonlinearity, wide variations in loads, time-variation and uncertain disturbance of the ac servo system. In the proposed approach, the self-recurrent wavelet neural network (SRWNN) is employed to construct an adaptive self-recurrent consequent part for each fuzzy rule of TSK fuzzy model. For the IAFWNN controller, the online learning algorithm is based on back propagation (BP) algorithm. Moreover, an improved particle swarm optimization (IPSO) is used to adapt the learning rate. The aid of an adaptive SRWNN identifier offers the real-time gradient information to the adaptive fuzzy wavelet neural controller to overcome the impact of parameter variations, load disturbances and other uncertainties effectively, and has a good dynamic. The asymptotical stability of the system is guaranteed by using the Lyapunov method. The result of the simulation and the prototype test prove that the proposed are effective and suitable. Copyright © 2017. Published by Elsevier Ltd.

Tuning Recurrent Neural Networks for Recognizing Handwritten Arabic Words

KAUST Repository

Qaralleh, Esam

2013-10-01

Artificial neural networks have the abilities to learn by example and are capable of solving problems that are hard to solve using ordinary rule-based programming. They have many design parameters that affect their performance such as the number and sizes of the hidden layers. Large sizes are slow and small sizes are generally not accurate. Tuning the neural network size is a hard task because the design space is often large and training is often a long process. We use design of experiments techniques to tune the recurrent neural network used in an Arabic handwriting recognition system. We show that best results are achieved with three hidden layers and two subsampling layers. To tune the sizes of these five layers, we use fractional factorial experiment design to limit the number of experiments to a feasible number. Moreover, we replicate the experiment configuration multiple times to overcome the randomness in the training process. The accuracy and time measurements are analyzed and modeled. The two models are then used to locate network sizes that are on the Pareto optimal frontier. The approach described in this paper reduces the label error from 26.2% to 19.8%.

Training the Recurrent neural network by the Fuzzy Min-Max algorithm for fault prediction

International Nuclear Information System (INIS)

Zemouri, Ryad; Racoceanu, Daniel; Zerhouni, Noureddine; Minca, Eugenia; Filip, Florin

2009-01-01

In this paper, we present a training technique of a Recurrent Radial Basis Function neural network for fault prediction. We use the Fuzzy Min-Max technique to initialize the k-center of the RRBF neural network. The k-means algorithm is then applied to calculate the centers that minimize the mean square error of the prediction task. The performances of the k-means algorithm are then boosted by the Fuzzy Min-Max technique.

Synchronization of chaotic recurrent neural networks with time-varying delays using nonlinear feedback control

International Nuclear Information System (INIS)

Cui Baotong; Lou Xuyang

2009-01-01

In this paper, a new method to synchronize two identical chaotic recurrent neural networks is proposed. Using the drive-response concept, a nonlinear feedback control law is derived to achieve the state synchronization of the two identical chaotic neural networks. Furthermore, based on the Lyapunov method, a delay independent sufficient synchronization condition in terms of linear matrix inequality (LMI) is obtained. A numerical example with graphical illustrations is given to illuminate the presented synchronization scheme

A state space approach for piecewise-linear recurrent neural networks for identifying computational dynamics from neural measurements.

Directory of Open Access Journals (Sweden)

Daniel Durstewitz

2017-06-01

Full Text Available The computational and cognitive properties of neural systems are often thought to be implemented in terms of their (stochastic network dynamics. Hence, recovering the system dynamics from experimentally observed neuronal time series, like multiple single-unit recordings or neuroimaging data, is an important step toward understanding its computations. Ideally, one would not only seek a (lower-dimensional state space representation of the dynamics, but would wish to have access to its statistical properties and their generative equations for in-depth analysis. Recurrent neural networks (RNNs are a computationally powerful and dynamically universal formal framework which has been extensively studied from both the computational and the dynamical systems perspective. Here we develop a semi-analytical maximum-likelihood estimation scheme for piecewise-linear RNNs (PLRNNs within the statistical framework of state space models, which accounts for noise in both the underlying latent dynamics and the observation process. The Expectation-Maximization algorithm is used to infer the latent state distribution, through a global Laplace approximation, and the PLRNN parameters iteratively. After validating the procedure on toy examples, and using inference through particle filters for comparison, the approach is applied to multiple single-unit recordings from the rodent anterior cingulate cortex (ACC obtained during performance of a classical working memory task, delayed alternation. Models estimated from kernel-smoothed spike time data were able to capture the essential computational dynamics underlying task performance, including stimulus-selective delay activity. The estimated models were rarely multi-stable, however, but rather were tuned to exhibit slow dynamics in the vicinity of a bifurcation point. In summary, the present work advances a semi-analytical (thus reasonably fast maximum-likelihood estimation framework for PLRNNs that may enable to recover

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

Science.gov (United States)

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.

Recurrent Neural Network Applications for Astronomical Time Series

Science.gov (United States)

Protopapas, Pavlos

2017-06-01

The benefits of good predictive models in astronomy lie in early event prediction systems and effective resource allocation. Current time series methods applicable to regular time series have not evolved to generalize for irregular time series. In this talk, I will describe two Recurrent Neural Network methods, Long Short-Term Memory (LSTM) and Echo State Networks (ESNs) for predicting irregular time series. Feature engineering along with a non-linear modeling proved to be an effective predictor. For noisy time series, the prediction is improved by training the network on error realizations using the error estimates from astronomical light curves. In addition to this, we propose a new neural network architecture to remove correlation from the residuals in order to improve prediction and compensate for the noisy data. Finally, I show how to set hyperparameters for a stable and performant solution correctly. In this work, we circumvent this obstacle by optimizing ESN hyperparameters using Bayesian optimization with Gaussian Process priors. This automates the tuning procedure, enabling users to employ the power of RNN without needing an in-depth understanding of the tuning procedure.

Language Identification in Short Utterances Using Long Short-Term Memory (LSTM) Recurrent Neural Networks.

Science.gov (United States)

Zazo, Ruben; Lozano-Diez, Alicia; Gonzalez-Dominguez, Javier; Toledano, Doroteo T; Gonzalez-Rodriguez, Joaquin

2016-01-01

Long Short Term Memory (LSTM) Recurrent Neural Networks (RNNs) have recently outperformed other state-of-the-art approaches, such as i-vector and Deep Neural Networks (DNNs), in automatic Language Identification (LID), particularly when dealing with very short utterances (∼3s). In this contribution we present an open-source, end-to-end, LSTM RNN system running on limited computational resources (a single GPU) that outperforms a reference i-vector system on a subset of the NIST Language Recognition Evaluation (8 target languages, 3s task) by up to a 26%. This result is in line with previously published research using proprietary LSTM implementations and huge computational resources, which made these former results hardly reproducible. Further, we extend those previous experiments modeling unseen languages (out of set, OOS, modeling), which is crucial in real applications. Results show that a LSTM RNN with OOS modeling is able to detect these languages and generalizes robustly to unseen OOS languages. Finally, we also analyze the effect of even more limited test data (from 2.25s to 0.1s) proving that with as little as 0.5s an accuracy of over 50% can be achieved.

A one-layer recurrent neural network for non-smooth convex optimization subject to linear inequality constraints

International Nuclear Information System (INIS)

Liu, Xiaolan; Zhou, Mi

2016-01-01

In this paper, a one-layer recurrent network is proposed for solving a non-smooth convex optimization subject to linear inequality constraints. Compared with the existing neural networks for optimization, the proposed neural network is capable of solving more general convex optimization with linear inequality constraints. The convergence of the state variables of the proposed neural network to achieve solution optimality is guaranteed as long as the designed parameters in the model are larger than the derived lower bounds.

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

Science.gov (United States)

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

Recurrent neural networks for breast lesion classification based on DCE-MRIs

Science.gov (United States)

Antropova, Natasha; Huynh, Benjamin; Giger, Maryellen

2018-02-01

Dynamic contrast-enhanced magnetic resonance imaging (DCE-MRI) plays a significant role in breast cancer screening, cancer staging, and monitoring response to therapy. Recently, deep learning methods are being rapidly incorporated in image-based breast cancer diagnosis and prognosis. However, most of the current deep learning methods make clinical decisions based on 2-dimentional (2D) or 3D images and are not well suited for temporal image data. In this study, we develop a deep learning methodology that enables integration of clinically valuable temporal components of DCE-MRIs into deep learning-based lesion classification. Our work is performed on a database of 703 DCE-MRI cases for the task of distinguishing benign and malignant lesions, and uses the area under the ROC curve (AUC) as the performance metric in conducting that task. We train a recurrent neural network, specifically a long short-term memory network (LSTM), on sequences of image features extracted from the dynamic MRI sequences. These features are extracted with VGGNet, a convolutional neural network pre-trained on a large dataset of natural images ImageNet. The features are obtained from various levels of the network, to capture low-, mid-, and high-level information about the lesion. Compared to a classification method that takes as input only images at a single time-point (yielding an AUC = 0.81 (se = 0.04)), our LSTM method improves lesion classification with an AUC of 0.85 (se = 0.03).

Stability results for stochastic delayed recurrent neural networks with discrete and distributed delays

Science.gov (United States)

Chen, Guiling; Li, Dingshi; Shi, Lin; van Gaans, Onno; Verduyn Lunel, Sjoerd

2018-03-01

We present new conditions for asymptotic stability and exponential stability of a class of stochastic recurrent neural networks with discrete and distributed time varying delays. Our approach is based on the method using fixed point theory, which do not resort to any Liapunov function or Liapunov functional. Our results neither require the boundedness, monotonicity and differentiability of the activation functions nor differentiability of the time varying delays. In particular, a class of neural networks without stochastic perturbations is also considered. Examples are given to illustrate our main results.

Spatial Clockwork Recurrent Neural Network for Muscle Perimysium Segmentation.

Science.gov (United States)

Xie, Yuanpu; Zhang, Zizhao; Sapkota, Manish; Yang, Lin

2016-10-01

Accurate segmentation of perimysium plays an important role in early diagnosis of many muscle diseases because many diseases contain different perimysium inflammation. However, it remains as a challenging task due to the complex appearance of the perymisum morphology and its ambiguity to the background area. The muscle perimysium also exhibits strong structure spanned in the entire tissue, which makes it difficult for current local patch-based methods to capture this long-range context information. In this paper, we propose a novel spatial clockwork recurrent neural network (spatial CW-RNN) to address those issues. Specifically, we split the entire image into a set of non-overlapping image patches, and the semantic dependencies among them are modeled by the proposed spatial CW-RNN. Our method directly takes the 2D structure of the image into consideration and is capable of encoding the context information of the entire image into the local representation of each patch. Meanwhile, we leverage on the structured regression to assign one prediction mask rather than a single class label to each local patch, which enables both efficient training and testing. We extensively test our method for perimysium segmentation using digitized muscle microscopy images. Experimental results demonstrate the superiority of the novel spatial CW-RNN over other existing state of the arts.

Robust sliding mode control for uncertain servo system using friction observer and recurrent fuzzy neural networks

International Nuclear Information System (INIS)

Han, Seong Ik; Jeong, Chan Se; Yang, Soon Yong

2012-01-01

A robust positioning control scheme has been developed using friction parameter observer and recurrent fuzzy neural networks based on the sliding mode control. As a dynamic friction model, the LuGre model is adopted for handling friction compensation because it has been known to capture sufficiently the properties of a nonlinear dynamic friction. A developed friction parameter observer has a simple structure and also well estimates friction parameters of the LuGre friction model. In addition, an approximation method for the system uncertainty is developed using recurrent fuzzy neural networks technology to improve the precision positioning degree. Some simulation and experiment provide the verification on the performance of a proposed robust control scheme

Novel criteria for global exponential periodicity and stability of recurrent neural networks with time-varying delays

International Nuclear Information System (INIS)

Song Qiankun

2008-01-01

In this paper, the global exponential periodicity and stability of recurrent neural networks with time-varying delays are investigated by applying the idea of vector Lyapunov function, M-matrix theory and inequality technique. We assume neither the global Lipschitz conditions on these activation functions nor the differentiability on these time-varying delays, which were needed in other papers. Several novel criteria are found to ascertain the existence, uniqueness and global exponential stability of periodic solution for recurrent neural network with time-varying delays. Moreover, the exponential convergence rate index is estimated, which depends on the system parameters. Some previous results are improved and generalized, and an example is given to show the effectiveness of our method

Robust sliding mode control for uncertain servo system using friction observer and recurrent fuzzy neural networks

Energy Technology Data Exchange (ETDEWEB)

Han, Seong Ik [Pusan National University, Busan (Korea, Republic of); Jeong, Chan Se; Yang, Soon Yong [University of Ulsan, Ulsan (Korea, Republic of)

2012-04-15

A robust positioning control scheme has been developed using friction parameter observer and recurrent fuzzy neural networks based on the sliding mode control. As a dynamic friction model, the LuGre model is adopted for handling friction compensation because it has been known to capture sufficiently the properties of a nonlinear dynamic friction. A developed friction parameter observer has a simple structure and also well estimates friction parameters of the LuGre friction model. In addition, an approximation method for the system uncertainty is developed using recurrent fuzzy neural networks technology to improve the precision positioning degree. Some simulation and experiment provide the verification on the performance of a proposed robust control scheme.

Synaptic plasticity in a recurrent neural network for versatile and adaptive behaviors of a walking robot

Directory of Open Access Journals (Sweden)

Eduard eGrinke

2015-10-01

Full Text Available Walking animals, like insects, with little neural computing can effectively perform complex behaviors. They can walk around their environment, escape from corners/deadlocks, and avoid or climb over obstacles. While performing all these behaviors, they can also adapt their movements to deal with an unknown situation. As a consequence, they successfully navigate through their complex environment. The versatile and adaptive abilities are the result of an integration of several ingredients embedded in their sensorimotor loop. Biological studies reveal that the ingredients include neural dynamics, plasticity, sensory feedback, and biomechanics. Generating such versatile and adaptive behaviors for a walking robot is a challenging task. In this study, we present a bio-inspired approach to solve this task. Specifically, the approach combines neural mechanisms with plasticity, sensory feedback, and biomechanics. The neural mechanisms consist of adaptive neural sensory processing and modular neural locomotion control. The sensory processing is based on a small recurrent network consisting of two fully connected neurons. Online correlation-based learning with synaptic scaling is applied to adequately change the connections of the network. By doing so, we can effectively exploit neural dynamics (i.e., hysteresis effects and single attractors in the network to generate different turning angles with short-term memory for a biomechanical walking robot. The turning information is transmitted as descending steering signals to the locomotion control which translates the signals into motor actions. As a result, the robot can walk around and adapt its turning angle for avoiding obstacles in different situations as well as escaping from sharp corners or deadlocks. Using backbone joint control embedded in the locomotion control allows the robot to climb over small obstacles. Consequently, it can successfully explore and navigate in complex environments.

Long Short-Term Memory Projection Recurrent Neural Network Architectures for Piano’s Continuous Note Recognition

Directory of Open Access Journals (Sweden)

YuKang Jia

2017-01-01

Full Text Available Long Short-Term Memory (LSTM is a kind of Recurrent Neural Networks (RNN relating to time series, which has achieved good performance in speech recogniton and image recognition. Long Short-Term Memory Projection (LSTMP is a variant of LSTM to further optimize speed and performance of LSTM by adding a projection layer. As LSTM and LSTMP have performed well in pattern recognition, in this paper, we combine them with Connectionist Temporal Classification (CTC to study piano’s continuous note recognition for robotics. Based on the Beijing Forestry University music library, we conduct experiments to show recognition rates and numbers of iterations of LSTM with a single layer, LSTMP with a single layer, and Deep LSTM (DLSTM, LSTM with multilayers. As a result, the single layer LSTMP proves performing much better than the single layer LSTM in both time and the recognition rate; that is, LSTMP has fewer parameters and therefore reduces the training time, and, moreover, benefiting from the projection layer, LSTMP has better performance, too. The best recognition rate of LSTMP is 99.8%. As for DLSTM, the recognition rate can reach 100% because of the effectiveness of the deep structure, but compared with the single layer LSTMP, DLSTM needs more training time.

Recurrence in Benign Paroxysmal Positional Vertigo: A Large, Single-Institution Study.

Science.gov (United States)

Luryi, Alexander L; Lawrence, Juliana; Bojrab, Dennis I; LaRouere, Michael; Babu, Seilesh; Zappia, John; Sargent, Eric W; Chan, Eleanor; Naumann, Ilka; Hong, Robert S; Schutt, Christopher A

2018-04-11

To report rates of recurrence in benign paroxysmal positional vertigo (BPPV) and associated patient and disease factors. Retrospective chart review. Single high-volume otology practice. Patients diagnosed with BPPV from 2007 to 2016 with documented resolution of symptoms. Diagnostic and particle repositioning maneuvers for BPPV. BPPV recurrence, time to recurrence, and ear(s) affected at recurrence. A total of 1,105 patients meeting criteria were identified. Of this population, 37% had recurrence of BPPV in either ear or both ears. Overall same-ear recurrence rate was 28%; 76% of recurrences involved the same ear(s) as initial presentation. Recurrences that occurred after longer disease-free intervals were more likely to involve the opposite ear than early recurrences (p = 0.02). Female sex (40.4% versus 32.7%, p = 0.01) and history of previous BPPV (57.5% versus 32.4%, p diabetes mellitus, and traumatic etiology were not. Approximately, half (56%) of recurrences occurred within 1 year of resolution. A large single-institution study of recurrence in BPPV is presented along with Kaplan-Meier disease-free survival curves. Female sex and history of previous BPPV were associated with increased recurrence, while previously suspected risk factors for recurrence including history of Menière's disease, diabetes, and trauma were not. Remote recurrence is more likely to involve the contralateral ear than early recurrence. These data solidify the expected course of treated BPPV allowing for improved clinical care and patient counseling.

A non-penalty recurrent neural network for solving a class of constrained optimization problems.

Science.gov (United States)

Hosseini, Alireza

2016-01-01

In this paper, we explain a methodology to analyze convergence of some differential inclusion-based neural networks for solving nonsmooth optimization problems. For a general differential inclusion, we show that if its right hand-side set valued map satisfies some conditions, then solution trajectory of the differential inclusion converges to optimal solution set of its corresponding in optimization problem. Based on the obtained methodology, we introduce a new recurrent neural network for solving nonsmooth optimization problems. Objective function does not need to be convex on R(n) nor does the new neural network model require any penalty parameter. We compare our new method with some penalty-based and non-penalty based models. Moreover for differentiable cases, we implement circuit diagram of the new neural network. Copyright © 2015 Elsevier Ltd. All rights reserved.

Synaptic plasticity in a recurrent neural network for versatile and adaptive behaviors of a walking robot.

Science.gov (United States)

Grinke, Eduard; Tetzlaff, Christian; Wörgötter, Florentin; Manoonpong, Poramate

2015-01-01

Walking animals, like insects, with little neural computing can effectively perform complex behaviors. For example, they can walk around their environment, escape from corners/deadlocks, and avoid or climb over obstacles. While performing all these behaviors, they can also adapt their movements to deal with an unknown situation. As a consequence, they successfully navigate through their complex environment. The versatile and adaptive abilities are the result of an integration of several ingredients embedded in their sensorimotor loop. Biological studies reveal that the ingredients include neural dynamics, plasticity, sensory feedback, and biomechanics. Generating such versatile and adaptive behaviors for a many degrees-of-freedom (DOFs) walking robot is a challenging task. Thus, in this study, we present a bio-inspired approach to solve this task. Specifically, the approach combines neural mechanisms with plasticity, exteroceptive sensory feedback, and biomechanics. The neural mechanisms consist of adaptive neural sensory processing and modular neural locomotion control. The sensory processing is based on a small recurrent neural network consisting of two fully connected neurons. Online correlation-based learning with synaptic scaling is applied to adequately change the connections of the network. By doing so, we can effectively exploit neural dynamics (i.e., hysteresis effects and single attractors) in the network to generate different turning angles with short-term memory for a walking robot. The turning information is transmitted as descending steering signals to the neural locomotion control which translates the signals into motor actions. As a result, the robot can walk around and adapt its turning angle for avoiding obstacles in different situations. The adaptation also enables the robot to effectively escape from sharp corners or deadlocks. Using backbone joint control embedded in the the locomotion control allows the robot to climb over small obstacles

Online Sequence Training of Recurrent Neural Networks with Connectionist Temporal Classification

OpenAIRE

Hwang, Kyuyeon; Sung, Wonyong

2015-01-01

Connectionist temporal classification (CTC) based supervised sequence training of recurrent neural networks (RNNs) has shown great success in many machine learning areas including end-to-end speech and handwritten character recognition. For the CTC training, however, it is required to unroll (or unfold) the RNN by the length of an input sequence. This unrolling requires a lot of memory and hinders a small footprint implementation of online learning or adaptation. Furthermore, the length of tr...

Different-Level Simultaneous Minimization Scheme for Fault Tolerance of Redundant Manipulator Aided with Discrete-Time Recurrent Neural Network.

Science.gov (United States)

Jin, Long; Liao, Bolin; Liu, Mei; Xiao, Lin; Guo, Dongsheng; Yan, Xiaogang

2017-01-01

By incorporating the physical constraints in joint space, a different-level simultaneous minimization scheme, which takes both the robot kinematics and robot dynamics into account, is presented and investigated for fault-tolerant motion planning of redundant manipulator in this paper. The scheme is reformulated as a quadratic program (QP) with equality and bound constraints, which is then solved by a discrete-time recurrent neural network. Simulative verifications based on a six-link planar redundant robot manipulator substantiate the efficacy and accuracy of the presented acceleration fault-tolerant scheme, the resultant QP and the corresponding discrete-time recurrent neural network.

Internal representation of task rules by recurrent dynamics: the importance of the diversity of neural responses

Directory of Open Access Journals (Sweden)

Mattia Rigotti

2010-10-01

Full Text Available Neural activity of behaving animals, especially in the prefrontal cortex, is highly heterogeneous, with selective responses to diverse aspects of the executed task. We propose a general model of recurrent neural networks that perform complex rule-based tasks, and we show that the diversity of neuronal responses plays a fundamental role when the behavioral responses are context dependent. Specifically, we found that when the inner mental states encoding the task rules are represented by stable patterns of neural activity (attractors of the neural dynamics, the neurons must be selective for combinations of sensory stimuli and inner mental states. Such mixed selectivity is easily obtained by neurons that connect with random synaptic strengths both to the recurrent network and to neurons encoding sensory inputs. The number of randomly connected neurons needed to solve a task is on average only three times as large as the number of neurons needed in a network designed ad hoc. Moreover, the number of needed neurons grows only linearly with the number of task-relevant events and mental states, provided that each neuron responds to a large proportion of events (dense/distributed coding. A biologically realistic implementation of the model captures several aspects of the activity recorded from monkeys performing context dependent tasks. Our findings explain the importance of the diversity of neural responses and provide us with simple and general principles for designing attractor neural networks that perform complex computation.

Nonlinear Model Predictive Control Based on a Self-Organizing Recurrent Neural Network.

Science.gov (United States)

Han, Hong-Gui; Zhang, Lu; Hou, Ying; Qiao, Jun-Fei

2016-02-01

A nonlinear model predictive control (NMPC) scheme is developed in this paper based on a self-organizing recurrent radial basis function (SR-RBF) neural network, whose structure and parameters are adjusted concurrently in the training process. The proposed SR-RBF neural network is represented in a general nonlinear form for predicting the future dynamic behaviors of nonlinear systems. To improve the modeling accuracy, a spiking-based growing and pruning algorithm and an adaptive learning algorithm are developed to tune the structure and parameters of the SR-RBF neural network, respectively. Meanwhile, for the control problem, an improved gradient method is utilized for the solution of the optimization problem in NMPC. The stability of the resulting control system is proved based on the Lyapunov stability theory. Finally, the proposed SR-RBF neural network-based NMPC (SR-RBF-NMPC) is used to control the dissolved oxygen (DO) concentration in a wastewater treatment process (WWTP). Comparisons with other existing methods demonstrate that the SR-RBF-NMPC can achieve a considerably better model fitting for WWTP and a better control performance for DO concentration.

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

Science.gov (United States)

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.

Brain Dynamics in Predicting Driving Fatigue Using a Recurrent Self-Evolving Fuzzy Neural Network.

Science.gov (United States)

Liu, Yu-Ting; Lin, Yang-Yin; Wu, Shang-Lin; Chuang, Chun-Hsiang; Lin, Chin-Teng

2016-02-01

This paper proposes a generalized prediction system called a recurrent self-evolving fuzzy neural network (RSEFNN) that employs an on-line gradient descent learning rule to address the electroencephalography (EEG) regression problem in brain dynamics for driving fatigue. The cognitive states of drivers significantly affect driving safety; in particular, fatigue driving, or drowsy driving, endangers both the individual and the public. For this reason, the development of brain-computer interfaces (BCIs) that can identify drowsy driving states is a crucial and urgent topic of study. Many EEG-based BCIs have been developed as artificial auxiliary systems for use in various practical applications because of the benefits of measuring EEG signals. In the literature, the efficacy of EEG-based BCIs in recognition tasks has been limited by low resolutions. The system proposed in this paper represents the first attempt to use the recurrent fuzzy neural network (RFNN) architecture to increase adaptability in realistic EEG applications to overcome this bottleneck. This paper further analyzes brain dynamics in a simulated car driving task in a virtual-reality environment. The proposed RSEFNN model is evaluated using the generalized cross-subject approach, and the results indicate that the RSEFNN is superior to competing models regardless of the use of recurrent or nonrecurrent structures.

Precipitation Nowcast using Deep Recurrent Neural Network

Science.gov (United States)

Akbari Asanjan, A.; Yang, T.; Gao, X.; Hsu, K. L.; Sorooshian, S.

2016-12-01

An accurate precipitation nowcast (0-6 hours) with a fine temporal and spatial resolution has always been an important prerequisite for flood warning, streamflow prediction and risk management. Most of the popular approaches used for forecasting precipitation can be categorized into two groups. One type of precipitation forecast relies on numerical modeling of the physical dynamics of atmosphere and another is based on empirical and statistical regression models derived by local hydrologists or meteorologists. Given the recent advances in artificial intelligence, in this study a powerful Deep Recurrent Neural Network, termed as Long Short-Term Memory (LSTM) model, is creatively used to extract the patterns and forecast the spatial and temporal variability of Cloud Top Brightness Temperature (CTBT) observed from GOES satellite. Then, a 0-6 hours precipitation nowcast is produced using a Precipitation Estimation from Remote Sensing Information using Artificial Neural Network (PERSIANN) algorithm, in which the CTBT nowcast is used as the PERSIANN algorithm's raw inputs. Two case studies over the continental U.S. have been conducted that demonstrate the improvement of proposed approach as compared to a classical Feed Forward Neural Network and a couple simple regression models. The advantages and disadvantages of the proposed method are summarized with regard to its capability of pattern recognition through time, handling of vanishing gradient during model learning, and working with sparse data. The studies show that the LSTM model performs better than other methods, and it is able to learn the temporal evolution of the precipitation events through over 1000 time lags. The uniqueness of PERSIANN's algorithm enables an alternative precipitation nowcast approach as demonstrated in this study, in which the CTBT prediction is produced and used as the inputs for generating precipitation nowcast.

Large-Scale Recurrent Neural Network Based Modelling of Gene Regulatory Network Using Cuckoo Search-Flower Pollination Algorithm.

Science.gov (United States)

Mandal, Sudip; Khan, Abhinandan; Saha, Goutam; Pal, Rajat K

2016-01-01

The accurate prediction of genetic networks using computational tools is one of the greatest challenges in the postgenomic era. Recurrent Neural Network is one of the most popular but simple approaches to model the network dynamics from time-series microarray data. To date, it has been successfully applied to computationally derive small-scale artificial and real-world genetic networks with high accuracy. However, they underperformed for large-scale genetic networks. Here, a new methodology has been proposed where a hybrid Cuckoo Search-Flower Pollination Algorithm has been implemented with Recurrent Neural Network. Cuckoo Search is used to search the best combination of regulators. Moreover, Flower Pollination Algorithm is applied to optimize the model parameters of the Recurrent Neural Network formalism. Initially, the proposed method is tested on a benchmark large-scale artificial network for both noiseless and noisy data. The results obtained show that the proposed methodology is capable of increasing the inference of correct regulations and decreasing false regulations to a high degree. Secondly, the proposed methodology has been validated against the real-world dataset of the DNA SOS repair network of Escherichia coli. However, the proposed method sacrifices computational time complexity in both cases due to the hybrid optimization process.

Recurrent Neural Networks to Correct Satellite Image Classification Maps

Science.gov (United States)

Maggiori, Emmanuel; Charpiat, Guillaume; Tarabalka, Yuliya; Alliez, Pierre

2017-09-01

While initially devised for image categorization, convolutional neural networks (CNNs) are being increasingly used for the pixelwise semantic labeling of images. However, the proper nature of the most common CNN architectures makes them good at recognizing but poor at localizing objects precisely. This problem is magnified in the context of aerial and satellite image labeling, where a spatially fine object outlining is of paramount importance. Different iterative enhancement algorithms have been presented in the literature to progressively improve the coarse CNN outputs, seeking to sharpen object boundaries around real image edges. However, one must carefully design, choose and tune such algorithms. Instead, our goal is to directly learn the iterative process itself. For this, we formulate a generic iterative enhancement process inspired from partial differential equations, and observe that it can be expressed as a recurrent neural network (RNN). Consequently, we train such a network from manually labeled data for our enhancement task. In a series of experiments we show that our RNN effectively learns an iterative process that significantly improves the quality of satellite image classification maps.

Very deep recurrent convolutional neural network for object recognition

Science.gov (United States)

Brahimi, Sourour; Ben Aoun, Najib; Ben Amar, Chokri

2017-03-01

In recent years, Computer vision has become a very active field. This field includes methods for processing, analyzing, and understanding images. The most challenging problems in computer vision are image classification and object recognition. This paper presents a new approach for object recognition task. This approach exploits the success of the Very Deep Convolutional Neural Network for object recognition. In fact, it improves the convolutional layers by adding recurrent connections. This proposed approach was evaluated on two object recognition benchmarks: Pascal VOC 2007 and CIFAR-10. The experimental results prove the efficiency of our method in comparison with the state of the art methods.

Analysis of recurrent neural networks for short-term energy load forecasting

Science.gov (United States)

Di Persio, Luca; Honchar, Oleksandr

2017-11-01

Short-term forecasts have recently gained an increasing attention because of the rise of competitive electricity markets. In fact, short-terms forecast of possible future loads turn out to be fundamental to build efficient energy management strategies as well as to avoid energy wastage. Such type of challenges are difficult to tackle both from a theoretical and applied point of view. Latter tasks require sophisticated methods to manage multidimensional time series related to stochastic phenomena which are often highly interconnected. In the present work we first review novel approaches to energy load forecasting based on recurrent neural network, focusing our attention on long/short term memory architectures (LSTMs). Such type of artificial neural networks have been widely applied to problems dealing with sequential data such it happens, e.g., in socio-economics settings, for text recognition purposes, concerning video signals, etc., always showing their effectiveness to model complex temporal data. Moreover, we consider different novel variations of basic LSTMs, such as sequence-to-sequence approach and bidirectional LSTMs, aiming at providing effective models for energy load data. Last but not least, we test all the described algorithms on real energy load data showing not only that deep recurrent networks can be successfully applied to energy load forecasting, but also that this approach can be extended to other problems based on time series prediction.

Optimal Formation of Multirobot Systems Based on a Recurrent Neural Network.

Science.gov (United States)

Wang, Yunpeng; Cheng, Long; Hou, Zeng-Guang; Yu, Junzhi; Tan, Min

2016-02-01

The optimal formation problem of multirobot systems is solved by a recurrent neural network in this paper. The desired formation is described by the shape theory. This theory can generate a set of feasible formations that share the same relative relation among robots. An optimal formation means that finding one formation from the feasible formation set, which has the minimum distance to the initial formation of the multirobot system. Then, the formation problem is transformed into an optimization problem. In addition, the orientation, scale, and admissible range of the formation can also be considered as the constraints in the optimization problem. Furthermore, if all robots are identical, their positions in the system are exchangeable. Then, each robot does not necessarily move to one specific position in the formation. In this case, the optimal formation problem becomes a combinational optimization problem, whose optimal solution is very hard to obtain. Inspired by the penalty method, this combinational optimization problem can be approximately transformed into a convex optimization problem. Due to the involvement of the Euclidean norm in the distance, the objective function of these optimization problems are nonsmooth. To solve these nonsmooth optimization problems efficiently, a recurrent neural network approach is employed, owing to its parallel computation ability. Finally, some simulations and experiments are given to validate the effectiveness and efficiency of the proposed optimal formation approach.

A novel prosodic-information synthesizer based on recurrent fuzzy neural network for the Chinese TTS system.

Science.gov (United States)

Lin, Chin-Teng; Wu, Rui-Cheng; Chang, Jyh-Yeong; Liang, Sheng-Fu

2004-02-01

In this paper, a new technique for the Chinese text-to-speech (TTS) system is proposed. Our major effort focuses on the prosodic information generation. New methodologies for constructing fuzzy rules in a prosodic model simulating human's pronouncing rules are developed. The proposed Recurrent Fuzzy Neural Network (RFNN) is a multilayer recurrent neural network (RNN) which integrates a Self-cOnstructing Neural Fuzzy Inference Network (SONFIN) into a recurrent connectionist structure. The RFNN can be functionally divided into two parts. The first part adopts the SONFIN as a prosodic model to explore the relationship between high-level linguistic features and prosodic information based on fuzzy inference rules. As compared to conventional neural networks, the SONFIN can always construct itself with an economic network size in high learning speed. The second part employs a five-layer network to generate all prosodic parameters by directly using the prosodic fuzzy rules inferred from the first part as well as other important features of syllables. The TTS system combined with the proposed method can behave not only sandhi rules but also the other prosodic phenomena existing in the traditional TTS systems. Moreover, the proposed scheme can even find out some new rules about prosodic phrase structure. The performance of the proposed RFNN-based prosodic model is verified by imbedding it into a Chinese TTS system with a Chinese monosyllable database based on the time-domain pitch synchronous overlap add (TD-PSOLA) method. Our experimental results show that the proposed RFNN can generate proper prosodic parameters including pitch means, pitch shapes, maximum energy levels, syllable duration, and pause duration. Some synthetic sounds are online available for demonstration.

A statistical framework for evaluating neural networks to predict recurrent events in breast cancer

Science.gov (United States)

Gorunescu, Florin; Gorunescu, Marina; El-Darzi, Elia; Gorunescu, Smaranda

2010-07-01

Breast cancer is the second leading cause of cancer deaths in women today. Sometimes, breast cancer can return after primary treatment. A medical diagnosis of recurrent cancer is often a more challenging task than the initial one. In this paper, we investigate the potential contribution of neural networks (NNs) to support health professionals in diagnosing such events. The NN algorithms are tested and applied to two different datasets. An extensive statistical analysis has been performed to verify our experiments. The results show that a simple network structure for both the multi-layer perceptron and radial basis function can produce equally good results, not all attributes are needed to train these algorithms and, finally, the classification performances of all algorithms are statistically robust. Moreover, we have shown that the best performing algorithm will strongly depend on the features of the datasets, and hence, there is not necessarily a single best classifier.

Reinforcement Learning of Linking and Tracing Contours in Recurrent Neural Networks

Science.gov (United States)

Brosch, Tobias; Neumann, Heiko; Roelfsema, Pieter R.

2015-01-01

The processing of a visual stimulus can be subdivided into a number of stages. Upon stimulus presentation there is an early phase of feedforward processing where the visual information is propagated from lower to higher visual areas for the extraction of basic and complex stimulus features. This is followed by a later phase where horizontal connections within areas and feedback connections from higher areas back to lower areas come into play. In this later phase, image elements that are behaviorally relevant are grouped by Gestalt grouping rules and are labeled in the cortex with enhanced neuronal activity (object-based attention in psychology). Recent neurophysiological studies revealed that reward-based learning influences these recurrent grouping processes, but it is not well understood how rewards train recurrent circuits for perceptual organization. This paper examines the mechanisms for reward-based learning of new grouping rules. We derive a learning rule that can explain how rewards influence the information flow through feedforward, horizontal and feedback connections. We illustrate the efficiency with two tasks that have been used to study the neuronal correlates of perceptual organization in early visual cortex. The first task is called contour-integration and demands the integration of collinear contour elements into an elongated curve. We show how reward-based learning causes an enhancement of the representation of the to-be-grouped elements at early levels of a recurrent neural network, just as is observed in the visual cortex of monkeys. The second task is curve-tracing where the aim is to determine the endpoint of an elongated curve composed of connected image elements. If trained with the new learning rule, neural networks learn to propagate enhanced activity over the curve, in accordance with neurophysiological data. We close the paper with a number of model predictions that can be tested in future neurophysiological and computational studies

Robust recurrent neural network modeling for software fault detection and correction prediction

International Nuclear Information System (INIS)

Hu, Q.P.; Xie, M.; Ng, S.H.; Levitin, G.

2007-01-01

Software fault detection and correction processes are related although different, and they should be studied together. A practical approach is to apply software reliability growth models to model fault detection, and fault correction process is assumed to be a delayed process. On the other hand, the artificial neural networks model, as a data-driven approach, tries to model these two processes together with no assumptions. Specifically, feedforward backpropagation networks have shown their advantages over analytical models in fault number predictions. In this paper, the following approach is explored. First, recurrent neural networks are applied to model these two processes together. Within this framework, a systematic networks configuration approach is developed with genetic algorithm according to the prediction performance. In order to provide robust predictions, an extra factor characterizing the dispersion of prediction repetitions is incorporated into the performance function. Comparisons with feedforward neural networks and analytical models are developed with respect to a real data set

Folk music style modelling by recurrent neural networks with long short term memory units

OpenAIRE

Sturm, Bob; Santos, João Felipe; Korshunova, Iryna

2015-01-01

We demonstrate two generative models created by training a recurrent neural network (RNN) with three hidden layers of long short-term memory (LSTM) units. This extends past work in numerous directions, including training deeper models with nearly 24,000 high-level transcriptions of folk tunes. We discuss our on-going work.

A New Local Bipolar Autoassociative Memory Based on External Inputs of Discrete Recurrent Neural Networks With Time Delay.

Science.gov (United States)

Zhou, Caigen; Zeng, Xiaoqin; Luo, Chaomin; Zhang, Huaguang

In this paper, local bipolar auto-associative memories are presented based on discrete recurrent neural networks with a class of gain type activation function. The weight parameters of neural networks are acquired by a set of inequalities without the learning procedure. The global exponential stability criteria are established to ensure the accuracy of the restored patterns by considering time delays and external inputs. The proposed methodology is capable of effectively overcoming spurious memory patterns and achieving memory capacity. The effectiveness, robustness, and fault-tolerant capability are validated by simulated experiments.In this paper, local bipolar auto-associative memories are presented based on discrete recurrent neural networks with a class of gain type activation function. The weight parameters of neural networks are acquired by a set of inequalities without the learning procedure. The global exponential stability criteria are established to ensure the accuracy of the restored patterns by considering time delays and external inputs. The proposed methodology is capable of effectively overcoming spurious memory patterns and achieving memory capacity. The effectiveness, robustness, and fault-tolerant capability are validated by simulated experiments.

Deep Recurrent Neural Networks for Human Activity Recognition

Directory of Open Access Journals (Sweden)

Abdulmajid Murad

2017-11-01

Full Text Available Adopting deep learning methods for human activity recognition has been effective in extracting discriminative features from raw input sequences acquired from body-worn sensors. Although human movements are encoded in a sequence of successive samples in time, typical machine learning methods perform recognition tasks without exploiting the temporal correlations between input data samples. Convolutional neural networks (CNNs address this issue by using convolutions across a one-dimensional temporal sequence to capture dependencies among input data. However, the size of convolutional kernels restricts the captured range of dependencies between data samples. As a result, typical models are unadaptable to a wide range of activity-recognition configurations and require fixed-length input windows. In this paper, we propose the use of deep recurrent neural networks (DRNNs for building recognition models that are capable of capturing long-range dependencies in variable-length input sequences. We present unidirectional, bidirectional, and cascaded architectures based on long short-term memory (LSTM DRNNs and evaluate their effectiveness on miscellaneous benchmark datasets. Experimental results show that our proposed models outperform methods employing conventional machine learning, such as support vector machine (SVM and k-nearest neighbors (KNN. Additionally, the proposed models yield better performance than other deep learning techniques, such as deep believe networks (DBNs and CNNs.

Deep Recurrent Neural Networks for Human Activity Recognition.

Science.gov (United States)

Murad, Abdulmajid; Pyun, Jae-Young

2017-11-06

Adopting deep learning methods for human activity recognition has been effective in extracting discriminative features from raw input sequences acquired from body-worn sensors. Although human movements are encoded in a sequence of successive samples in time, typical machine learning methods perform recognition tasks without exploiting the temporal correlations between input data samples. Convolutional neural networks (CNNs) address this issue by using convolutions across a one-dimensional temporal sequence to capture dependencies among input data. However, the size of convolutional kernels restricts the captured range of dependencies between data samples. As a result, typical models are unadaptable to a wide range of activity-recognition configurations and require fixed-length input windows. In this paper, we propose the use of deep recurrent neural networks (DRNNs) for building recognition models that are capable of capturing long-range dependencies in variable-length input sequences. We present unidirectional, bidirectional, and cascaded architectures based on long short-term memory (LSTM) DRNNs and evaluate their effectiveness on miscellaneous benchmark datasets. Experimental results show that our proposed models outperform methods employing conventional machine learning, such as support vector machine (SVM) and k-nearest neighbors (KNN). Additionally, the proposed models yield better performance than other deep learning techniques, such as deep believe networks (DBNs) and CNNs.

Single-site neural tube closure in human embryos revisited.

Science.gov (United States)

de Bakker, Bernadette S; Driessen, Stan; Boukens, Bastiaan J D; van den Hoff, Maurice J B; Oostra, Roelof-Jan

2017-10-01

Since the multi-site closure theory was first proposed in 1991 as explanation for the preferential localizations of neural tube defects, the closure of the neural tube has been debated. Although the multi-site closure theory is much cited in clinical literature, single-site closure is most apparent in literature concerning embryology. Inspired by Victor Hamburgers (1900-2001) statement that "our real teacher has been and still is the embryo, who is, incidentally, the only teacher who is always right", we decided to critically review both theories of neural tube closure. To verify the theories of closure, we studied serial histological sections of 10 mouse embryos between 8.5 and 9.5 days of gestation and 18 human embryos of the Carnegie collection between Carnegie stage 9 (19-21 days) and 13 (28-32 days). Neural tube closure was histologically defined by the neuroepithelial remodeling of the two adjoining neural fold tips in the midline. We did not observe multiple fusion sites in neither mouse nor human embryos. A meta-analysis of case reports on neural tube defects showed that defects can occur at any level of the neural axis. Our data indicate that the human neural tube fuses at a single site and, therefore, we propose to reinstate the single-site closure theory for neural tube closure. We showed that neural tube defects are not restricted to a specific location, thereby refuting the reasoning underlying the multi-site closure theory. Clin. Anat. 30:988-999, 2017. © 2017 Wiley Periodicals, Inc. © 2017 Wiley Periodicals, Inc.

Neural processing of short-term recurrence in songbird vocal communication.

Directory of Open Access Journals (Sweden)

Gabriël J L Beckers

Full Text Available BACKGROUND: Many situations involving animal communication are dominated by recurring, stereotyped signals. How do receivers optimally distinguish between frequently recurring signals and novel ones? Cortical auditory systems are known to be pre-attentively sensitive to short-term delivery statistics of artificial stimuli, but it is unknown if this phenomenon extends to the level of behaviorally relevant delivery patterns, such as those used during communication. METHODOLOGY/PRINCIPAL FINDINGS: We recorded and analyzed complete auditory scenes of spontaneously communicating zebra finch (Taeniopygia guttata pairs over a week-long period, and show that they can produce tens of thousands of short-range contact calls per day. Individual calls recur at time scales (median interval 1.5 s matching those at which mammalian sensory systems are sensitive to recent stimulus history. Next, we presented to anesthetized birds sequences of frequently recurring calls interspersed with rare ones, and recorded, in parallel, action and local field potential responses in the medio-caudal auditory forebrain at 32 unique sites. Variation in call recurrence rate over natural ranges leads to widespread and significant modulation in strength of neural responses. Such modulation is highly call-specific in secondary auditory areas, but not in the main thalamo-recipient, primary auditory area. CONCLUSIONS/SIGNIFICANCE: Our results support the hypothesis that pre-attentive neural sensitivity to short-term stimulus recurrence is involved in the analysis of auditory scenes at the level of delivery patterns of meaningful sounds. This may enable birds to efficiently and automatically distinguish frequently recurring vocalizations from other events in their auditory scene.

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

Science.gov (United States)

Liu, Qingshan; Guo, Zhishan; Wang, Jun

2012-02-01

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

Optimizing Markovian modeling of chaotic systems with recurrent neural networks

International Nuclear Information System (INIS)

Cechin, Adelmo L.; Pechmann, Denise R.; Oliveira, Luiz P.L. de

2008-01-01

In this paper, we propose a methodology for optimizing the modeling of an one-dimensional chaotic time series with a Markov Chain. The model is extracted from a recurrent neural network trained for the attractor reconstructed from the data set. Each state of the obtained Markov Chain is a region of the reconstructed state space where the dynamics is approximated by a specific piecewise linear map, obtained from the network. The Markov Chain represents the dynamics of the time series in its statistical essence. An application to a time series resulted from Lorenz system is included

Online Signature Verification using Recurrent Neural Network and Length-normalized Path Signature

OpenAIRE

Lai, Songxuan; Jin, Lianwen; Yang, Weixin

2017-01-01

Inspired by the great success of recurrent neural networks (RNNs) in sequential modeling, we introduce a novel RNN system to improve the performance of online signature verification. The training objective is to directly minimize intra-class variations and to push the distances between skilled forgeries and genuine samples above a given threshold. By back-propagating the training signals, our RNN network produced discriminative features with desired metrics. Additionally, we propose a novel d...

ProLanGO: Protein Function Prediction Using Neural Machine Translation Based on a Recurrent Neural Network.

Science.gov (United States)

Cao, Renzhi; Freitas, Colton; Chan, Leong; Sun, Miao; Jiang, Haiqing; Chen, Zhangxin

2017-10-17

With the development of next generation sequencing techniques, it is fast and cheap to determine protein sequences but relatively slow and expensive to extract useful information from protein sequences because of limitations of traditional biological experimental techniques. Protein function prediction has been a long standing challenge to fill the gap between the huge amount of protein sequences and the known function. In this paper, we propose a novel method to convert the protein function problem into a language translation problem by the new proposed protein sequence language "ProLan" to the protein function language "GOLan", and build a neural machine translation model based on recurrent neural networks to translate "ProLan" language to "GOLan" language. We blindly tested our method by attending the latest third Critical Assessment of Function Annotation (CAFA 3) in 2016, and also evaluate the performance of our methods on selected proteins whose function was released after CAFA competition. The good performance on the training and testing datasets demonstrates that our new proposed method is a promising direction for protein function prediction. In summary, we first time propose a method which converts the protein function prediction problem to a language translation problem and applies a neural machine translation model for protein function prediction.

Sequential neural models with stochastic layers

DEFF Research Database (Denmark)

Fraccaro, Marco; Sønderby, Søren Kaae; Paquet, Ulrich

2016-01-01

How can we efficiently propagate uncertainty in a latent state representation with recurrent neural networks? This paper introduces stochastic recurrent neural networks which glue a deterministic recurrent neural network and a state space model together to form a stochastic and sequential neural...... generative model. The clear separation of deterministic and stochastic layers allows a structured variational inference network to track the factorization of the model's posterior distribution. By retaining both the nonlinear recursive structure of a recurrent neural network and averaging over...

Complex Dynamical Network Control for Trajectory Tracking Using Delayed Recurrent Neural Networks

Directory of Open Access Journals (Sweden)

Jose P. Perez

2014-01-01

Full Text Available In this paper, the problem of trajectory tracking is studied. Based on the V-stability and Lyapunov theory, a control law that achieves the global asymptotic stability of the tracking error between a delayed recurrent neural network and a complex dynamical network is obtained. To illustrate the analytic results, we present a tracking simulation of a dynamical network with each node being just one Lorenz’s dynamical system and three identical Chen’s dynamical systems.

Deep Recurrent Neural Networks for Supernovae Classification

Science.gov (United States)

Charnock, Tom; Moss, Adam

2017-03-01

We apply deep recurrent neural networks, which are capable of learning complex sequential information, to classify supernovae (code available at https://github.com/adammoss/supernovae). The observational time and filter fluxes are used as inputs to the network, but since the inputs are agnostic, additional data such as host galaxy information can also be included. Using the Supernovae Photometric Classification Challenge (SPCC) data, we find that deep networks are capable of learning about light curves, however the performance of the network is highly sensitive to the amount of training data. For a training size of 50% of the representational SPCC data set (around 104 supernovae) we obtain a type-Ia versus non-type-Ia classification accuracy of 94.7%, an area under the Receiver Operating Characteristic curve AUC of 0.986 and an SPCC figure-of-merit F 1 = 0.64. When using only the data for the early-epoch challenge defined by the SPCC, we achieve a classification accuracy of 93.1%, AUC of 0.977, and F 1 = 0.58, results almost as good as with the whole light curve. By employing bidirectional neural networks, we can acquire impressive classification results between supernovae types I, II and III at an accuracy of 90.4% and AUC of 0.974. We also apply a pre-trained model to obtain classification probabilities as a function of time and show that it can give early indications of supernovae type. Our method is competitive with existing algorithms and has applications for future large-scale photometric surveys.

Reward-based training of recurrent neural networks for cognitive and value-based tasks.

Science.gov (United States)

Song, H Francis; Yang, Guangyu R; Wang, Xiao-Jing

2017-01-13

Trained neural network models, which exhibit features of neural activity recorded from behaving animals, may provide insights into the circuit mechanisms of cognitive functions through systematic analysis of network activity and connectivity. However, in contrast to the graded error signals commonly used to train networks through supervised learning, animals learn from reward feedback on definite actions through reinforcement learning. Reward maximization is particularly relevant when optimal behavior depends on an animal's internal judgment of confidence or subjective preferences. Here, we implement reward-based training of recurrent neural networks in which a value network guides learning by using the activity of the decision network to predict future reward. We show that such models capture behavioral and electrophysiological findings from well-known experimental paradigms. Our work provides a unified framework for investigating diverse cognitive and value-based computations, and predicts a role for value representation that is essential for learning, but not executing, a task.

Intelligent fault diagnosis of rolling bearings using an improved deep recurrent neural network

Science.gov (United States)

Jiang, Hongkai; Li, Xingqiu; Shao, Haidong; Zhao, Ke

2018-06-01

Traditional intelligent fault diagnosis methods for rolling bearings heavily depend on manual feature extraction and feature selection. For this purpose, an intelligent deep learning method, named the improved deep recurrent neural network (DRNN), is proposed in this paper. Firstly, frequency spectrum sequences are used as inputs to reduce the input size and ensure good robustness. Secondly, DRNN is constructed by the stacks of the recurrent hidden layer to automatically extract the features from the input spectrum sequences. Thirdly, an adaptive learning rate is adopted to improve the training performance of the constructed DRNN. The proposed method is verified with experimental rolling bearing data, and the results confirm that the proposed method is more effective than traditional intelligent fault diagnosis methods.

Improving protein disorder prediction by deep bidirectional long short-term memory recurrent neural networks.

Science.gov (United States)

Hanson, Jack; Yang, Yuedong; Paliwal, Kuldip; Zhou, Yaoqi

2017-03-01

Capturing long-range interactions between structural but not sequence neighbors of proteins is a long-standing challenging problem in bioinformatics. Recently, long short-term memory (LSTM) networks have significantly improved the accuracy of speech and image classification problems by remembering useful past information in long sequential events. Here, we have implemented deep bidirectional LSTM recurrent neural networks in the problem of protein intrinsic disorder prediction. The new method, named SPOT-Disorder, has steadily improved over a similar method using a traditional, window-based neural network (SPINE-D) in all datasets tested without separate training on short and long disordered regions. Independent tests on four other datasets including the datasets from critical assessment of structure prediction (CASP) techniques and >10 000 annotated proteins from MobiDB, confirmed SPOT-Disorder as one of the best methods in disorder prediction. Moreover, initial studies indicate that the method is more accurate in predicting functional sites in disordered regions. These results highlight the usefulness combining LSTM with deep bidirectional recurrent neural networks in capturing non-local, long-range interactions for bioinformatics applications. SPOT-disorder is available as a web server and as a standalone program at: http://sparks-lab.org/server/SPOT-disorder/index.php . j.hanson@griffith.edu.au or yuedong.yang@griffith.edu.au or yaoqi.zhou@griffith.edu.au. Supplementary data is available at Bioinformatics online. © The Author 2016. Published by Oxford University Press. All rights reserved. For Permissions, please e-mail: journals.permissions@oup.com

Exponential stability of delayed recurrent neural networks with Markovian jumping parameters

International Nuclear Information System (INIS)

Wang Zidong; Liu Yurong; Yu Li; Liu Xiaohui

2006-01-01

In this Letter, the global exponential stability analysis problem is considered for a class of recurrent neural networks (RNNs) with time delays and Markovian jumping parameters. The jumping parameters considered here are generated from a continuous-time discrete-state homogeneous Markov process, which are governed by a Markov process with discrete and finite state space. The purpose of the problem addressed is to derive some easy-to-test conditions such that the dynamics of the neural network is stochastically exponentially stable in the mean square, independent of the time delay. By employing a new Lyapunov-Krasovskii functional, a linear matrix inequality (LMI) approach is developed to establish the desired sufficient conditions, and therefore the global exponential stability in the mean square for the delayed RNNs can be easily checked by utilizing the numerically efficient Matlab LMI toolbox, and no tuning of parameters is required. A numerical example is exploited to show the usefulness of the derived LMI-based stability conditions

Stochastic exponential stability of the delayed reaction-diffusion recurrent neural networks with Markovian jumping parameters

International Nuclear Information System (INIS)

Wang Linshan; Zhang Zhe; Wang Yangfan

2008-01-01

Some criteria for the global stochastic exponential stability of the delayed reaction-diffusion recurrent neural networks with Markovian jumping parameters are presented. The jumping parameters considered here are generated from a continuous-time discrete-state homogeneous Markov process, which are governed by a Markov process with discrete and finite state space. By employing a new Lyapunov-Krasovskii functional, a linear matrix inequality (LMI) approach is developed to establish some easy-to-test criteria of global exponential stability in the mean square for the stochastic neural networks. The criteria are computationally efficient, since they are in the forms of some linear matrix inequalities

Deep recurrent neural network reveals a hierarchy of process memory during dynamic natural vision.

Science.gov (United States)

Shi, Junxing; Wen, Haiguang; Zhang, Yizhen; Han, Kuan; Liu, Zhongming

2018-05-01

The human visual cortex extracts both spatial and temporal visual features to support perception and guide behavior. Deep convolutional neural networks (CNNs) provide a computational framework to model cortical representation and organization for spatial visual processing, but unable to explain how the brain processes temporal information. To overcome this limitation, we extended a CNN by adding recurrent connections to different layers of the CNN to allow spatial representations to be remembered and accumulated over time. The extended model, or the recurrent neural network (RNN), embodied a hierarchical and distributed model of process memory as an integral part of visual processing. Unlike the CNN, the RNN learned spatiotemporal features from videos to enable action recognition. The RNN better predicted cortical responses to natural movie stimuli than the CNN, at all visual areas, especially those along the dorsal stream. As a fully observable model of visual processing, the RNN also revealed a cortical hierarchy of temporal receptive window, dynamics of process memory, and spatiotemporal representations. These results support the hypothesis of process memory, and demonstrate the potential of using the RNN for in-depth computational understanding of dynamic natural vision. © 2018 Wiley Periodicals, Inc.

Forecasting energy market indices with recurrent neural networks: Case study of crude oil price fluctuations

International Nuclear Information System (INIS)

Wang, Jie; Wang, Jun

2016-01-01

In an attempt to improve the forecasting accuracy of crude oil price fluctuations, a new neural network architecture is established in this work which combines Multilayer perception and ERNN (Elman recurrent neural networks) with stochastic time effective function. ERNN is a time-varying predictive control system and is developed with the ability to keep memory of recent events in order to predict future output. The stochastic time effective function represents that the recent information has a stronger effect for the investors than the old information. With the established model the empirical research has a good performance in testing the predictive effects on four different time series indices. Compared to other models, the present model is possible to evaluate data from 1990s to today with extreme accuracy and speedy. The applied CID (complexity invariant distance) analysis and multiscale CID analysis, are provided as the new useful measures to evaluate a better predicting ability of the proposed model than other traditional models. - Highlights: • A new forecasting model is developed by a random Elman recurrent neural network. • The forecasting accuracy of crude oil price fluctuations is improved by the model. • The forecasting results of the proposed model are more accurate than compared models. • Two new distance analysis methods are applied to confirm the predicting results.

Some new results for recurrent neural networks with varying-time coefficients and delays

International Nuclear Information System (INIS)

Jiang Haijun; Teng Zhidong

2005-01-01

In this Letter, we consider the recurrent neural networks with varying-time coefficients and delays. By constructing new Lyapunov functional, introducing ingeniously many real parameters and applying the technique of Young inequality, we establish a series of criteria on the boundedness, global exponential stability and the existence of periodic solutions. In these criteria, we do not require that the response functions are differentiable, bounded and monotone nondecreasing. Some previous works are improved and extended

DeepProbe: Information Directed Sequence Understanding and Chatbot Design via Recurrent Neural Networks

OpenAIRE

Yin, Zi; Chang, Keng-hao; Zhang, Ruofei

2017-01-01

Information extraction and user intention identification are central topics in modern query understanding and recommendation systems. In this paper, we propose DeepProbe, a generic information-directed interaction framework which is built around an attention-based sequence to sequence (seq2seq) recurrent neural network. DeepProbe can rephrase, evaluate, and even actively ask questions, leveraging the generative ability and likelihood estimation made possible by seq2seq models. DeepProbe makes...

Identification of serial number on bank card using recurrent neural network

Science.gov (United States)

Liu, Li; Huang, Linlin; Xue, Jian

2018-04-01

Identification of serial number on bank card has many applications. Due to the different number printing mode, complex background, distortion in shape, etc., it is quite challenging to achieve high identification accuracy. In this paper, we propose a method using Normalization-Cooperated Gradient Feature (NCGF) and Recurrent Neural Network (RNN) based on Long Short-Term Memory (LSTM) for serial number identification. The NCGF maps the gradient direction elements of original image to direction planes such that the RNN with direction planes as input can recognize numbers more accurately. Taking the advantages of NCGF and RNN, we get 90%digit string recognition accuracy.

Global robust exponential stability analysis for interval recurrent neural networks

International Nuclear Information System (INIS)

Xu Shengyuan; Lam, James; Ho, Daniel W.C.; Zou Yun

2004-01-01

This Letter investigates the problem of robust global exponential stability analysis for interval recurrent neural networks (RNNs) via the linear matrix inequality (LMI) approach. The values of the time-invariant uncertain parameters are assumed to be bounded within given compact sets. An improved condition for the existence of a unique equilibrium point and its global exponential stability of RNNs with known parameters is proposed. Based on this, a sufficient condition for the global robust exponential stability for interval RNNs is obtained. Both of the conditions are expressed in terms of LMIs, which can be checked easily by various recently developed convex optimization algorithms. Examples are provided to demonstrate the reduced conservatism of the proposed exponential stability condition

Recurrent Neural Networks for Multivariate Time Series with Missing Values.

Science.gov (United States)

Che, Zhengping; Purushotham, Sanjay; Cho, Kyunghyun; Sontag, David; Liu, Yan

2018-04-17

Multivariate time series data in practical applications, such as health care, geoscience, and biology, are characterized by a variety of missing values. In time series prediction and other related tasks, it has been noted that missing values and their missing patterns are often correlated with the target labels, a.k.a., informative missingness. There is very limited work on exploiting the missing patterns for effective imputation and improving prediction performance. In this paper, we develop novel deep learning models, namely GRU-D, as one of the early attempts. GRU-D is based on Gated Recurrent Unit (GRU), a state-of-the-art recurrent neural network. It takes two representations of missing patterns, i.e., masking and time interval, and effectively incorporates them into a deep model architecture so that it not only captures the long-term temporal dependencies in time series, but also utilizes the missing patterns to achieve better prediction results. Experiments of time series classification tasks on real-world clinical datasets (MIMIC-III, PhysioNet) and synthetic datasets demonstrate that our models achieve state-of-the-art performance and provide useful insights for better understanding and utilization of missing values in time series analysis.

Learning to Generate Sequences with Combination of Hebbian and Non-hebbian Plasticity in Recurrent Spiking Neural Networks.

Science.gov (United States)

Panda, Priyadarshini; Roy, Kaushik

2017-01-01

Synaptic Plasticity, the foundation for learning and memory formation in the human brain, manifests in various forms. Here, we combine the standard spike timing correlation based Hebbian plasticity with a non-Hebbian synaptic decay mechanism for training a recurrent spiking neural model to generate sequences. We show that inclusion of the adaptive decay of synaptic weights with standard STDP helps learn stable contextual dependencies between temporal sequences, while reducing the strong attractor states that emerge in recurrent models due to feedback loops. Furthermore, we show that the combined learning scheme suppresses the chaotic activity in the recurrent model substantially, thereby enhancing its' ability to generate sequences consistently even in the presence of perturbations.

Using deep recurrent neural network for direct beam solar irradiance cloud screening

Science.gov (United States)

Chen, Maosi; Davis, John M.; Liu, Chaoshun; Sun, Zhibin; Zempila, Melina Maria; Gao, Wei

2017-09-01

Cloud screening is an essential procedure for in-situ calibration and atmospheric properties retrieval on (UV-)MultiFilter Rotating Shadowband Radiometer [(UV-)MFRSR]. Previous study has explored a cloud screening algorithm for direct-beam (UV-)MFRSR voltage measurements based on the stability assumption on a long time period (typically a half day or a whole day). To design such an algorithm requires in-depth understanding of radiative transfer and delicate data manipulation. Recent rapid developments on deep neural network and computation hardware have opened a window for modeling complicated End-to-End systems with a standardized strategy. In this study, a multi-layer dynamic bidirectional recurrent neural network is built for determining the cloudiness on each time point with a 17-year training dataset and tested with another 1-year dataset. The dataset is the daily 3-minute cosine corrected voltages, airmasses, and the corresponding cloud/clear-sky labels at two stations of the USDA UV-B Monitoring and Research Program. The results show that the optimized neural network model (3-layer, 250 hidden units, and 80 epochs of training) has an overall test accuracy of 97.87% (97.56% for the Oklahoma site and 98.16% for the Hawaii site). Generally, the neural network model grasps the key concept of the original model to use data in the entire day rather than short nearby measurements to perform cloud screening. A scrutiny of the logits layer suggests that the neural network model automatically learns a way to calculate a quantity similar to total optical depth and finds an appropriate threshold for cloud screening.

Pulsed neural networks consisting of single-flux-quantum spiking neurons

International Nuclear Information System (INIS)

Hirose, T.; Asai, T.; Amemiya, Y.

2007-01-01

An inhibitory pulsed neural network was developed for brain-like information processing, by using single-flux-quantum (SFQ) circuits. It consists of spiking neuron devices that are coupled to each other through all-to-all inhibitory connections. The network selects neural activity. The operation of the neural network was confirmed by computer simulation. SFQ neuron devices can imitate the operation of the inhibition phenomenon of neural networks

Identification of a Typical CSTR Using Optimal Focused Time Lagged Recurrent Neural Network Model with Gamma Memory Filter

OpenAIRE

Naikwad, S. N.; Dudul, S. V.

2009-01-01

A focused time lagged recurrent neural network (FTLR NN) with gamma memory filter is designed to learn the subtle complex dynamics of a typical CSTR process. Continuous stirred tank reactor exhibits complex nonlinear operations where reaction is exothermic. It is noticed from literature review that process control of CSTR using neuro-fuzzy systems was attempted by many, but optimal neural network model for identification of CSTR process is not yet available. As CSTR process includes tempora...

Fault diagnosis of rolling bearings with recurrent neural network-based autoencoders.

Science.gov (United States)

Liu, Han; Zhou, Jianzhong; Zheng, Yang; Jiang, Wei; Zhang, Yuncheng

2018-04-19

As the rolling bearings being the key part of rotary machine, its healthy condition is quite important for safety production. Fault diagnosis of rolling bearing has been research focus for the sake of improving the economic efficiency and guaranteeing the operation security. However, the collected signals are mixed with ambient noise during the operation of rotary machine, which brings great challenge to the exact diagnosis results. Using signals collected from multiple sensors can avoid the loss of local information and extract more helpful characteristics. Recurrent Neural Networks (RNN) is a type of artificial neural network which can deal with multiple time sequence data. The capacity of RNN has been proved outstanding for catching time relevance about time sequence data. This paper proposed a novel method for bearing fault diagnosis with RNN in the form of an autoencoder. In this approach, multiple vibration value of the rolling bearings of the next period are predicted from the previous period by means of Gated Recurrent Unit (GRU)-based denoising autoencoder. These GRU-based non-linear predictive denoising autoencoders (GRU-NP-DAEs) are trained with strong generalization ability for each different fault pattern. Then for the given input data, the reconstruction errors between the next period data and the output data generated by different GRU-NP-DAEs are used to detect anomalous conditions and classify fault type. Classic rotating machinery datasets have been employed to testify the effectiveness of the proposed diagnosis method and its preponderance over some state-of-the-art methods. The experiment results indicate that the proposed method achieves satisfactory performance with strong robustness and high classification accuracy. Copyright © 2018 ISA. Published by Elsevier Ltd. All rights reserved.

Identification of Jets Containing b-Hadrons with Recurrent Neural Networks at the ATLAS Experiment

CERN Multimedia

CERN. Geneva

2017-01-01

A novel b-jet identification algorithm is constructed with a Recurrent Neural Network (RNN) at the ATLAS Experiment. This talk presents the expected performance of the RNN based b-tagging in simulated $t \\bar t$ events. The RNN based b-tagging processes properties of tracks associated to jets which are represented in sequences. In contrast to traditional impact-parameter-based b-tagging algorithms which assume the tracks of jets are independent from each other, RNN based b-tagging can exploit the spatial and kinematic correlations of tracks which are initiated from the same b-hadrons. The neural network nature of the tagging algorithm also allows the flexibility of extending input features to include more track properties than can be effectively used in traditional algorithms.

A Three-Threshold Learning Rule Approaches the Maximal Capacity of Recurrent Neural Networks.

Directory of Open Access Journals (Sweden)

Alireza Alemi

2015-08-01

Full Text Available Understanding the theoretical foundations of how memories are encoded and retrieved in neural populations is a central challenge in neuroscience. A popular theoretical scenario for modeling memory function is the attractor neural network scenario, whose prototype is the Hopfield model. The model simplicity and the locality of the synaptic update rules come at the cost of a poor storage capacity, compared with the capacity achieved with perceptron learning algorithms. Here, by transforming the perceptron learning rule, we present an online learning rule for a recurrent neural network that achieves near-maximal storage capacity without an explicit supervisory error signal, relying only upon locally accessible information. The fully-connected network consists of excitatory binary neurons with plastic recurrent connections and non-plastic inhibitory feedback stabilizing the network dynamics; the memory patterns to be memorized are presented online as strong afferent currents, producing a bimodal distribution for the neuron synaptic inputs. Synapses corresponding to active inputs are modified as a function of the value of the local fields with respect to three thresholds. Above the highest threshold, and below the lowest threshold, no plasticity occurs. In between these two thresholds, potentiation/depression occurs when the local field is above/below an intermediate threshold. We simulated and analyzed a network of binary neurons implementing this rule and measured its storage capacity for different sizes of the basins of attraction. The storage capacity obtained through numerical simulations is shown to be close to the value predicted by analytical calculations. We also measured the dependence of capacity on the strength of external inputs. Finally, we quantified the statistics of the resulting synaptic connectivity matrix, and found that both the fraction of zero weight synapses and the degree of symmetry of the weight matrix increase with the

A recurrent neural network for adaptive beamforming and array correction.

Science.gov (United States)

Che, Hangjun; Li, Chuandong; He, Xing; Huang, Tingwen

2016-08-01

In this paper, a recurrent neural network (RNN) is proposed for solving adaptive beamforming problem. In order to minimize sidelobe interference, the problem is described as a convex optimization problem based on linear array model. RNN is designed to optimize system's weight values in the feasible region which is derived from arrays' state and plane wave's information. The new algorithm is proven to be stable and converge to optimal solution in the sense of Lyapunov. So as to verify new algorithm's performance, we apply it to beamforming under array mismatch situation. Comparing with other optimization algorithms, simulations suggest that RNN has strong ability to search for exact solutions under the condition of large scale constraints. Copyright © 2016 Elsevier Ltd. All rights reserved.

Multiple simultaneous fault diagnosis via hierarchical and single artificial neural networks

International Nuclear Information System (INIS)

Eslamloueyan, R.; Shahrokhi, M.; Bozorgmehri, R.

2003-01-01

Process fault diagnosis involves interpreting the current status of the plant given sensor reading and process knowledge. There has been considerable work done in this area with a variety of approaches being proposed for process fault diagnosis. Neural networks have been used to solve process fault diagnosis problems in chemical process, as they are well suited for recognizing multi-dimensional nonlinear patterns. In this work, the use of Hierarchical Artificial Neural Networks in diagnosing the multi-faults of a chemical process are discussed and compared with that of Single Artificial Neural Networks. The lower efficiency of Hierarchical Artificial Neural Networks , in comparison to Single Artificial Neural Networks, in process fault diagnosis is elaborated and analyzed. Also, the concept of a multi-level selection switch is presented and developed to improve the performance of hierarchical artificial neural networks. Simulation results indicate that application of multi-level selection switch increase the performance of the hierarchical artificial neural networks considerably

From phonemes to images : levels of representation in a recurrent neural model of visually-grounded language learning

NARCIS (Netherlands)

Gelderloos, L.J.; Chrupala, Grzegorz

2016-01-01

We present a model of visually-grounded language learning based on stacked gated recurrent neural networks which learns to predict visual features given an image description in the form of a sequence of phonemes. The learning task resembles that faced by human language learners who need to discover

A modular architecture for transparent computation in recurrent neural networks.

Science.gov (United States)

Carmantini, Giovanni S; Beim Graben, Peter; Desroches, Mathieu; Rodrigues, Serafim

2017-01-01

Computation is classically studied in terms of automata, formal languages and algorithms; yet, the relation between neural dynamics and symbolic representations and operations is still unclear in traditional eliminative connectionism. Therefore, we suggest a unique perspective on this central issue, to which we would like to refer as transparent connectionism, by proposing accounts of how symbolic computation can be implemented in neural substrates. In this study we first introduce a new model of dynamics on a symbolic space, the versatile shift, showing that it supports the real-time simulation of a range of automata. We then show that the Gödelization of versatile shifts defines nonlinear dynamical automata, dynamical systems evolving on a vectorial space. Finally, we present a mapping between nonlinear dynamical automata and recurrent artificial neural networks. The mapping defines an architecture characterized by its granular modularity, where data, symbolic operations and their control are not only distinguishable in activation space, but also spatially localizable in the network itself, while maintaining a distributed encoding of symbolic representations. The resulting networks simulate automata in real-time and are programmed directly, in the absence of network training. To discuss the unique characteristics of the architecture and their consequences, we present two examples: (i) the design of a Central Pattern Generator from a finite-state locomotive controller, and (ii) the creation of a network simulating a system of interactive automata that supports the parsing of garden-path sentences as investigated in psycholinguistics experiments. Copyright © 2016 Elsevier Ltd. All rights reserved.

Using recurrent neural network models for early detection of heart failure onset.

Science.gov (United States)

Choi, Edward; Schuetz, Andy; Stewart, Walter F; Sun, Jimeng

2017-03-01

We explored whether use of deep learning to model temporal relations among events in electronic health records (EHRs) would improve model performance in predicting initial diagnosis of heart failure (HF) compared to conventional methods that ignore temporality. Data were from a health system's EHR on 3884 incident HF cases and 28 903 controls, identified as primary care patients, between May 16, 2000, and May 23, 2013. Recurrent neural network (RNN) models using gated recurrent units (GRUs) were adapted to detect relations among time-stamped events (eg, disease diagnosis, medication orders, procedure orders, etc.) with a 12- to 18-month observation window of cases and controls. Model performance metrics were compared to regularized logistic regression, neural network, support vector machine, and K-nearest neighbor classifier approaches. Using a 12-month observation window, the area under the curve (AUC) for the RNN model was 0.777, compared to AUCs for logistic regression (0.747), multilayer perceptron (MLP) with 1 hidden layer (0.765), support vector machine (SVM) (0.743), and K-nearest neighbor (KNN) (0.730). When using an 18-month observation window, the AUC for the RNN model increased to 0.883 and was significantly higher than the 0.834 AUC for the best of the baseline methods (MLP). Deep learning models adapted to leverage temporal relations appear to improve performance of models for detection of incident heart failure with a short observation window of 12-18 months. © The Author 2016. Published by Oxford University Press on behalf of the American Medical Informatics Association.

Engine cylinder pressure reconstruction using crank kinematics and recurrently-trained neural networks

Science.gov (United States)

Bennett, C.; Dunne, J. F.; Trimby, S.; Richardson, D.

2017-02-01

A recurrent non-linear autoregressive with exogenous input (NARX) neural network is proposed, and a suitable fully-recurrent training methodology is adapted and tuned, for reconstructing cylinder pressure in multi-cylinder IC engines using measured crank kinematics. This type of indirect sensing is important for cost effective closed-loop combustion control and for On-Board Diagnostics. The challenge addressed is to accurately predict cylinder pressure traces within the cycle under generalisation conditions: i.e. using data not previously seen by the network during training. This involves direct construction and calibration of a suitable inverse crank dynamic model, which owing to singular behaviour at top-dead-centre (TDC), has proved difficult via physical model construction, calibration, and inversion. The NARX architecture is specialised and adapted to cylinder pressure reconstruction, using a fully-recurrent training methodology which is needed because the alternatives are too slow and unreliable for practical network training on production engines. The fully-recurrent Robust Adaptive Gradient Descent (RAGD) algorithm, is tuned initially using synthesised crank kinematics, and then tested on real engine data to assess the reconstruction capability. Real data is obtained from a 1.125 l, 3-cylinder, in-line, direct injection spark ignition (DISI) engine involving synchronised measurements of crank kinematics and cylinder pressure across a range of steady-state speed and load conditions. The paper shows that a RAGD-trained NARX network using both crank velocity and crank acceleration as input information, provides fast and robust training. By using the optimum epoch identified during RAGD training, acceptably accurate cylinder pressures, and especially accurate location-of-peak-pressure, can be reconstructed robustly under generalisation conditions, making it the most practical NARX configuration and recurrent training methodology for use on production engines.

Centralized and decentralized global outer-synchronization of asymmetric recurrent time-varying neural network by data-sampling.

Science.gov (United States)

Lu, Wenlian; Zheng, Ren; Chen, Tianping

2016-03-01

In this paper, we discuss outer-synchronization of the asymmetrically connected recurrent time-varying neural networks. By using both centralized and decentralized discretization data sampling principles, we derive several sufficient conditions based on three vector norms to guarantee that the difference of any two trajectories starting from different initial values of the neural network converges to zero. The lower bounds of the common time intervals between data samples in centralized and decentralized principles are proved to be positive, which guarantees exclusion of Zeno behavior. A numerical example is provided to illustrate the efficiency of the theoretical results. Copyright © 2015 Elsevier Ltd. All rights reserved.

Recurrent neural network for non-smooth convex optimization problems with application to the identification of genetic regulatory networks.

Science.gov (United States)

Cheng, Long; Hou, Zeng-Guang; Lin, Yingzi; Tan, Min; Zhang, Wenjun Chris; Wu, Fang-Xiang

2011-05-01

A recurrent neural network is proposed for solving the non-smooth convex optimization problem with the convex inequality and linear equality constraints. Since the objective function and inequality constraints may not be smooth, the Clarke's generalized gradients of the objective function and inequality constraints are employed to describe the dynamics of the proposed neural network. It is proved that the equilibrium point set of the proposed neural network is equivalent to the optimal solution of the original optimization problem by using the Lagrangian saddle-point theorem. Under weak conditions, the proposed neural network is proved to be stable, and the state of the neural network is convergent to one of its equilibrium points. Compared with the existing neural network models for non-smooth optimization problems, the proposed neural network can deal with a larger class of constraints and is not based on the penalty method. Finally, the proposed neural network is used to solve the identification problem of genetic regulatory networks, which can be transformed into a non-smooth convex optimization problem. The simulation results show the satisfactory identification accuracy, which demonstrates the effectiveness and efficiency of the proposed approach.

Automatic construction of a recurrent neural network based classifier for vehicle passage detection

Science.gov (United States)

Burnaev, Evgeny; Koptelov, Ivan; Novikov, German; Khanipov, Timur

2017-03-01

Recurrent Neural Networks (RNNs) are extensively used for time-series modeling and prediction. We propose an approach for automatic construction of a binary classifier based on Long Short-Term Memory RNNs (LSTM-RNNs) for detection of a vehicle passage through a checkpoint. As an input to the classifier we use multidimensional signals of various sensors that are installed on the checkpoint. Obtained results demonstrate that the previous approach to handcrafting a classifier, consisting of a set of deterministic rules, can be successfully replaced by an automatic RNN training on an appropriately labelled data.

Recurrent Neural Network Model for Constructive Peptide Design.

Science.gov (United States)

Müller, Alex T; Hiss, Jan A; Schneider, Gisbert

2018-02-26

We present a generative long short-term memory (LSTM) recurrent neural network (RNN) for combinatorial de novo peptide design. RNN models capture patterns in sequential data and generate new data instances from the learned context. Amino acid sequences represent a suitable input for these machine-learning models. Generative models trained on peptide sequences could therefore facilitate the design of bespoke peptide libraries. We trained RNNs with LSTM units on pattern recognition of helical antimicrobial peptides and used the resulting model for de novo sequence generation. Of these sequences, 82% were predicted to be active antimicrobial peptides compared to 65% of randomly sampled sequences with the same amino acid distribution as the training set. The generated sequences also lie closer to the training data than manually designed amphipathic helices. The results of this study showcase the ability of LSTM RNNs to construct new amino acid sequences within the applicability domain of the model and motivate their prospective application to peptide and protein design without the need for the exhaustive enumeration of sequence libraries.

An automatic microseismic or acoustic emission arrival identification scheme with deep recurrent neural networks

Science.gov (United States)

Zheng, Jing; Lu, Jiren; Peng, Suping; Jiang, Tianqi

2018-02-01

The conventional arrival pick-up algorithms cannot avoid the manual modification of the parameters for the simultaneous identification of multiple events under different signal-to-noise ratios (SNRs). Therefore, in order to automatically obtain the arrivals of multiple events with high precision under different SNRs, in this study an algorithm was proposed which had the ability to pick up the arrival of microseismic or acoustic emission events based on deep recurrent neural networks. The arrival identification was performed using two important steps, which included a training phase and a testing phase. The training process was mathematically modelled by deep recurrent neural networks using Long Short-Term Memory architecture. During the testing phase, the learned weights were utilized to identify the arrivals through the microseismic/acoustic emission data sets. The data sets were obtained by rock physics experiments of the acoustic emission. In order to obtain the data sets under different SNRs, this study added random noise to the raw experiments' data sets. The results showed that the outcome of the proposed method was able to attain an above 80 per cent hit-rate at SNR 0 dB, and an approximately 70 per cent hit-rate at SNR -5 dB, with an absolute error in 10 sampling points. These results indicated that the proposed method had high selection precision and robustness.

Drawing and Recognizing Chinese Characters with Recurrent Neural Network.

Science.gov (United States)

Zhang, Xu-Yao; Yin, Fei; Zhang, Yan-Ming; Liu, Cheng-Lin; Bengio, Yoshua

2018-04-01

Recent deep learning based approaches have achieved great success on handwriting recognition. Chinese characters are among the most widely adopted writing systems in the world. Previous research has mainly focused on recognizing handwritten Chinese characters. However, recognition is only one aspect for understanding a language, another challenging and interesting task is to teach a machine to automatically write (pictographic) Chinese characters. In this paper, we propose a framework by using the recurrent neural network (RNN) as both a discriminative model for recognizing Chinese characters and a generative model for drawing (generating) Chinese characters. To recognize Chinese characters, previous methods usually adopt the convolutional neural network (CNN) models which require transforming the online handwriting trajectory into image-like representations. Instead, our RNN based approach is an end-to-end system which directly deals with the sequential structure and does not require any domain-specific knowledge. With the RNN system (combining an LSTM and GRU), state-of-the-art performance can be achieved on the ICDAR-2013 competition database. Furthermore, under the RNN framework, a conditional generative model with character embedding is proposed for automatically drawing recognizable Chinese characters. The generated characters (in vector format) are human-readable and also can be recognized by the discriminative RNN model with high accuracy. Experimental results verify the effectiveness of using RNNs as both generative and discriminative models for the tasks of drawing and recognizing Chinese characters.

Global exponential stability and periodicity of reaction-diffusion recurrent neural networks with distributed delays and Dirichlet boundary conditions

International Nuclear Information System (INIS)

Lu Junguo; Lu Linji

2009-01-01

In this paper, global exponential stability and periodicity of a class of reaction-diffusion recurrent neural networks with distributed delays and Dirichlet boundary conditions are studied by constructing suitable Lyapunov functionals and utilizing some inequality techniques. We first prove global exponential convergence to 0 of the difference between any two solutions of the original neural networks, the existence and uniqueness of equilibrium is the direct results of this procedure. This approach is different from the usually used one where the existence, uniqueness of equilibrium and stability are proved in two separate steps. Secondly, we prove periodicity. Sufficient conditions ensuring the existence, uniqueness, and global exponential stability of the equilibrium and periodic solution are given. These conditions are easy to verify and our results play an important role in the design and application of globally exponentially stable neural circuits and periodic oscillatory neural circuits.

Identification of a Typical CSTR Using Optimal Focused Time Lagged Recurrent Neural Network Model with Gamma Memory Filter

Directory of Open Access Journals (Sweden)

S. N. Naikwad

2009-01-01

Full Text Available A focused time lagged recurrent neural network (FTLR NN with gamma memory filter is designed to learn the subtle complex dynamics of a typical CSTR process. Continuous stirred tank reactor exhibits complex nonlinear operations where reaction is exothermic. It is noticed from literature review that process control of CSTR using neuro-fuzzy systems was attempted by many, but optimal neural network model for identification of CSTR process is not yet available. As CSTR process includes temporal relationship in the input-output mappings, time lagged recurrent neural network is particularly used for identification purpose. The standard back propagation algorithm with momentum term has been proposed in this model. The various parameters like number of processing elements, number of hidden layers, training and testing percentage, learning rule and transfer function in hidden and output layer are investigated on the basis of performance measures like MSE, NMSE, and correlation coefficient on testing data set. Finally effects of different norms are tested along with variation in gamma memory filter. It is demonstrated that dynamic NN model has a remarkable system identification capability for the problems considered in this paper. Thus FTLR NN with gamma memory filter can be used to learn underlying highly nonlinear dynamics of the system, which is a major contribution of this paper.

Constructing Long Short-Term Memory based Deep Recurrent Neural Networks for Large Vocabulary Speech Recognition

OpenAIRE

Li, Xiangang; Wu, Xihong

2014-01-01

Long short-term memory (LSTM) based acoustic modeling methods have recently been shown to give state-of-the-art performance on some speech recognition tasks. To achieve a further performance improvement, in this research, deep extensions on LSTM are investigated considering that deep hierarchical model has turned out to be more efficient than a shallow one. Motivated by previous research on constructing deep recurrent neural networks (RNNs), alternative deep LSTM architectures are proposed an...

A Heuristic Approach to Intra-Brain Communications Using Chaos in a Recurrent Neural Network Model

Science.gov (United States)

Soma, Ken-ichiro; Mori, Ryota; Sato, Ryuichi; Nara, Shigetoshi

2011-09-01

To approach functional roles of chaos in brain, a heuristic model to consider mechanisms of intra-brain communications is proposed. The key idea is to use chaos in firing pattern dynamics of a recurrent neural network consisting of birary state neurons, as propagation medium of pulse signals. Computer experiments and numerical methods are introduced to evaluate signal transport characteristics by calculating correlation functions between sending neurons and receiving neurons of pulse signals.

Modeling the dynamics of the lead bismuth eutectic experimental accelerator driven system by an infinite impulse response locally recurrent neural network

International Nuclear Information System (INIS)

Zio, Enrico; Pedroni, Nicola; Broggi, Matteo; Golea, Lucia Roxana

2009-01-01

In this paper, an infinite impulse response locally recurrent neural network (IIR-LRNN) is employed for modelling the dynamics of the Lead Bismuth Eutectic eXperimental Accelerator Driven System (LBE-XADS). The network is trained by recursive back-propagation (RBP) and its ability in estimating transients is tested under various conditions. The results demonstrate the robustness of the locally recurrent scheme in the reconstruction of complex nonlinear dynamic relationships

Improved delay-dependent globally asymptotic stability of delayed uncertain recurrent neural networks with Markovian jumping parameters

International Nuclear Information System (INIS)

Yan, Ji; Bao-Tong, Cui

2010-01-01

In this paper, we have improved delay-dependent stability criteria for recurrent neural networks with a delay varying over a range and Markovian jumping parameters. The criteria improve over some previous ones in that they have fewer matrix variables yet less conservatism. In addition, a numerical example is provided to illustrate the applicability of the result using the linear matrix inequality toolbox in MATLAB. (general)

Contemporary deep recurrent learning for recognition

Science.gov (United States)

Iftekharuddin, K. M.; Alam, M.; Vidyaratne, L.

2017-05-01

Large-scale feed-forward neural networks have seen intense application in many computer vision problems. However, these networks can get hefty and computationally intensive with increasing complexity of the task. Our work, for the first time in literature, introduces a Cellular Simultaneous Recurrent Network (CSRN) based hierarchical neural network for object detection. CSRN has shown to be more effective to solving complex tasks such as maze traversal and image processing when compared to generic feed forward networks. While deep neural networks (DNN) have exhibited excellent performance in object detection and recognition, such hierarchical structure has largely been absent in neural networks with recurrency. Further, our work introduces deep hierarchy in SRN for object recognition. The simultaneous recurrency results in an unfolding effect of the SRN through time, potentially enabling the design of an arbitrarily deep network. This paper shows experiments using face, facial expression and character recognition tasks using novel deep recurrent model and compares recognition performance with that of generic deep feed forward model. Finally, we demonstrate the flexibility of incorporating our proposed deep SRN based recognition framework in a humanoid robotic platform called NAO.

An Incremental Time-delay Neural Network for Dynamical Recurrent Associative Memory

Institute of Scientific and Technical Information of China (English)

无

2002-01-01

An incremental time-delay neural network based on synapse growth, which is suitable for dynamic control and learning of autonomous robots, is proposed to improve the learning and retrieving performance of dynamical recurrent associative memory architecture. The model allows steady and continuous establishment of associative memory for spatio-temporal regularities and time series in discrete sequence of inputs. The inserted hidden units can be taken as the long-term memories that expand the capacity of network and sometimes may fade away under certain condition. Preliminary experiment has shown that this incremental network may be a promising approach to endow autonomous robots with the ability of adapting to new data without destroying the learned patterns. The system also benefits from its potential chaos character for emergence.

Recurrent networks for wave forecasting

Digital Repository Service at National Institute of Oceanography (India)

Mandal, S.; Prabaharan, N.

, merchant vessel routing, nearshore construction, etc. more efficiently and safely. This paper presents an application of the Artificial Neural Network, namely Backpropagation Recurrent Neural Network (BRNN) with rprop update algorithm for wave forecasting...

Distributed Recurrent Neural Forward Models with Synaptic Adaptation and CPG-based control for Complex Behaviors of Walking Robots

Directory of Open Access Journals (Sweden)

Sakyasingha eDasgupta

2015-09-01

Full Text Available Walking animals, like stick insects, cockroaches or ants, demonstrate a fascinating range of locomotive abilities and complex behaviors. The locomotive behaviors can consist of a variety of walking patterns along with adaptation that allow the animals to deal with changes in environmental conditions, like uneven terrains, gaps, obstacles etc. Biological study has revealed that such complex behaviors are a result of a combination of biomechanics and neural mechanism thus representing the true nature of embodied interactions. While the biomechanics helps maintain flexibility and sustain a variety of movements, the neural mechanisms generate movements while making appropriate predictions crucial for achieving adaptation. Such predictions or planning ahead can be achieved by way of internal models that are grounded in the overall behavior of the animal. Inspired by these findings, we present here, an artificial bio-inspired walking system which effectively combines biomechanics (in terms of the body and leg structures with the underlying neural mechanisms. The neural mechanisms consist of 1 central pattern generator based control for generating basic rhythmic patterns and coordinated movements, 2 distributed (at each leg recurrent neural network based adaptive forward models with efference copies as internal models for sensory predictions and instantaneous state estimations, and 3 searching and elevation control for adapting the movement of an individual leg to deal with different environmental conditions. Using simulations we show that this bio-inspired approach with adaptive internal models allows the walking robot to perform complex locomotive behaviors as observed in insects, including walking on undulated terrains, crossing large gaps as well as climbing over high obstacles. Furthermore we demonstrate that the newly developed recurrent network based approach to sensorimotor prediction outperforms the previous state of the art adaptive neuron

Criticality meets learning: Criticality signatures in a self-organizing recurrent neural network.

Science.gov (United States)

Del Papa, Bruno; Priesemann, Viola; Triesch, Jochen

2017-01-01

Many experiments have suggested that the brain operates close to a critical state, based on signatures of criticality such as power-law distributed neuronal avalanches. In neural network models, criticality is a dynamical state that maximizes information processing capacities, e.g. sensitivity to input, dynamical range and storage capacity, which makes it a favorable candidate state for brain function. Although models that self-organize towards a critical state have been proposed, the relation between criticality signatures and learning is still unclear. Here, we investigate signatures of criticality in a self-organizing recurrent neural network (SORN). Investigating criticality in the SORN is of particular interest because it has not been developed to show criticality. Instead, the SORN has been shown to exhibit spatio-temporal pattern learning through a combination of neural plasticity mechanisms and it reproduces a number of biological findings on neural variability and the statistics and fluctuations of synaptic efficacies. We show that, after a transient, the SORN spontaneously self-organizes into a dynamical state that shows criticality signatures comparable to those found in experiments. The plasticity mechanisms are necessary to attain that dynamical state, but not to maintain it. Furthermore, onset of external input transiently changes the slope of the avalanche distributions - matching recent experimental findings. Interestingly, the membrane noise level necessary for the occurrence of the criticality signatures reduces the model's performance in simple learning tasks. Overall, our work shows that the biologically inspired plasticity and homeostasis mechanisms responsible for the SORN's spatio-temporal learning abilities can give rise to criticality signatures in its activity when driven by random input, but these break down under the structured input of short repeating sequences.

New baseline correction algorithm for text-line recognition with bidirectional recurrent neural networks

Science.gov (United States)

Morillot, Olivier; Likforman-Sulem, Laurence; Grosicki, Emmanuèle

2013-04-01

Many preprocessing techniques have been proposed for isolated word recognition. However, recently, recognition systems have dealt with text blocks and their compound text lines. In this paper, we propose a new preprocessing approach to efficiently correct baseline skew and fluctuations. Our approach is based on a sliding window within which the vertical position of the baseline is estimated. Segmentation of text lines into subparts is, thus, avoided. Experiments conducted on a large publicly available database (Rimes), with a BLSTM (bidirectional long short-term memory) recurrent neural network recognition system, show that our baseline correction approach highly improves performance.

A Velocity-Level Bi-Criteria Optimization Scheme for Coordinated Path Tracking of Dual Robot Manipulators Using Recurrent Neural Network.

Science.gov (United States)

Xiao, Lin; Zhang, Yongsheng; Liao, Bolin; Zhang, Zhijun; Ding, Lei; Jin, Long

2017-01-01

A dual-robot system is a robotic device composed of two robot arms. To eliminate the joint-angle drift and prevent the occurrence of high joint velocity, a velocity-level bi-criteria optimization scheme, which includes two criteria (i.e., the minimum velocity norm and the repetitive motion), is proposed and investigated for coordinated path tracking of dual robot manipulators. Specifically, to realize the coordinated path tracking of dual robot manipulators, two subschemes are first presented for the left and right robot manipulators. After that, such two subschemes are reformulated as two general quadratic programs (QPs), which can be formulated as one unified QP. A recurrent neural network (RNN) is thus presented to solve effectively the unified QP problem. At last, computer simulation results based on a dual three-link planar manipulator further validate the feasibility and the efficacy of the velocity-level optimization scheme for coordinated path tracking using the recurrent neural network.

Marginally Stable Triangular Recurrent Neural Network Architecture for Time Series Prediction.

Science.gov (United States)

Sivakumar, Seshadri; Sivakumar, Shyamala

2017-09-25

This paper introduces a discrete-time recurrent neural network architecture using triangular feedback weight matrices that allows a simplified approach to ensuring network and training stability. The triangular structure of the weight matrices is exploited to readily ensure that the eigenvalues of the feedback weight matrix represented by the block diagonal elements lie on the unit circle in the complex z-plane by updating these weights based on the differential of the angular error variable. Such placement of the eigenvalues together with the extended close interaction between state variables facilitated by the nondiagonal triangular elements, enhances the learning ability of the proposed architecture. Simulation results show that the proposed architecture is highly effective in time-series prediction tasks associated with nonlinear and chaotic dynamic systems with underlying oscillatory modes. This modular architecture with dual upper and lower triangular feedback weight matrices mimics fully recurrent network architectures, while maintaining learning stability with a simplified training process. While training, the block-diagonal weights (hence the eigenvalues) of the dual triangular matrices are constrained to the same values during weight updates aimed at minimizing the possibility of overfitting. The dual triangular architecture also exploits the benefit of parsing the input and selectively applying the parsed inputs to the two subnetworks to facilitate enhanced learning performance.

Deep Recurrent Neural Networks for seizure detection and early seizure detection systems

Energy Technology Data Exchange (ETDEWEB)

Talathi, S. S. [Lawrence Livermore National Lab. (LLNL), Livermore, CA (United States)

2017-06-05

Epilepsy is common neurological diseases, affecting about 0.6-0.8 % of world population. Epileptic patients suffer from chronic unprovoked seizures, which can result in broad spectrum of debilitating medical and social consequences. Since seizures, in general, occur infrequently and are unpredictable, automated seizure detection systems are recommended to screen for seizures during long-term electroencephalogram (EEG) recordings. In addition, systems for early seizure detection can lead to the development of new types of intervention systems that are designed to control or shorten the duration of seizure events. In this article, we investigate the utility of recurrent neural networks (RNNs) in designing seizure detection and early seizure detection systems. We propose a deep learning framework via the use of Gated Recurrent Unit (GRU) RNNs for seizure detection. We use publicly available data in order to evaluate our method and demonstrate very promising evaluation results with overall accuracy close to 100 %. We also systematically investigate the application of our method for early seizure warning systems. Our method can detect about 98% of seizure events within the first 5 seconds of the overall epileptic seizure duration.

An intelligent nuclear reactor core controller for load following operations, using recurrent neural networks and fuzzy systems

International Nuclear Information System (INIS)

Boroushaki, M.; Ghofrani, M.B.; Lucas, C.; Yazdanpanah, M.J.

2003-01-01

In the last decade, the intelligent control community has paid great attention to the topic of intelligent control systems for nuclear plants (core, steam generator...). Papers mostly used approximate and simple mathematical SISO (single-input-single-output) model of nuclear plants for testing and/or tuning of the control systems. They also tried to generalize theses models to a real MIMO (multi-input-multi-output) plant, while nuclear plants are typically of complex nonlinear and multivariable nature with high interactions between their state variables and therefore, many of these proposed intelligent control systems are not appropriate for real cases. In this paper, we designed an on-line intelligent core controller for load following operations, based on a heuristic control algorithm, using a valid and updatable recurrent neural network (RNN). We have used an accurate 3-dimensional core calculation code to represent the real plant and to train the RNN. The results of simulation show that this intelligent controller can control the reactor core during load following operations, using optimum control rod groups manoeuvre and variable overlapping strategy. This methodology represents a simple and reliable procedure for controlling other complex nonlinear MIMO plants, and may improve the responses, comparing to other control systems

Cascaded bidirectional recurrent neural networks for protein secondary structure prediction.

Science.gov (United States)

Chen, Jinmiao; Chaudhari, Narendra

2007-01-01

Protein secondary structure (PSS) prediction is an important topic in bioinformatics. Our study on a large set of non-homologous proteins shows that long-range interactions commonly exist and negatively affect PSS prediction. Besides, we also reveal strong correlations between secondary structure (SS) elements. In order to take into account the long-range interactions and SS-SS correlations, we propose a novel prediction system based on cascaded bidirectional recurrent neural network (BRNN). We compare the cascaded BRNN against another two BRNN architectures, namely the original BRNN architecture used for speech recognition as well as Pollastri's BRNN that was proposed for PSS prediction. Our cascaded BRNN achieves an overall three state accuracy Q3 of 74.38\\%, and reaches a high Segment OVerlap (SOV) of 66.0455. It outperforms the original BRNN and Pollastri's BRNN in both Q3 and SOV. Specifically, it improves the SOV score by 4-6%.

Bayesian Recurrent Neural Network for Language Modeling.

Science.gov (United States)

Chien, Jen-Tzung; Ku, Yuan-Chu

2016-02-01

A language model (LM) is calculated as the probability of a word sequence that provides the solution to word prediction for a variety of information systems. A recurrent neural network (RNN) is powerful to learn the large-span dynamics of a word sequence in the continuous space. However, the training of the RNN-LM is an ill-posed problem because of too many parameters from a large dictionary size and a high-dimensional hidden layer. This paper presents a Bayesian approach to regularize the RNN-LM and apply it for continuous speech recognition. We aim to penalize the too complicated RNN-LM by compensating for the uncertainty of the estimated model parameters, which is represented by a Gaussian prior. The objective function in a Bayesian classification network is formed as the regularized cross-entropy error function. The regularized model is constructed not only by calculating the regularized parameters according to the maximum a posteriori criterion but also by estimating the Gaussian hyperparameter by maximizing the marginal likelihood. A rapid approximation to a Hessian matrix is developed to implement the Bayesian RNN-LM (BRNN-LM) by selecting a small set of salient outer-products. The proposed BRNN-LM achieves a sparser model than the RNN-LM. Experiments on different corpora show the robustness of system performance by applying the rapid BRNN-LM under different conditions.

Adaptive complementary fuzzy self-recurrent wavelet neural network controller for the electric load simulator system

Directory of Open Access Journals (Sweden)

Wang Chao

2016-03-01

Full Text Available Due to the complexities existing in the electric load simulator, this article develops a high-performance nonlinear adaptive controller to improve the torque tracking performance of the electric load simulator, which mainly consists of an adaptive fuzzy self-recurrent wavelet neural network controller with variable structure (VSFSWC and a complementary controller. The VSFSWC is clearly and easily used for real-time systems and greatly improves the convergence rate and control precision. The complementary controller is designed to eliminate the effect of the approximation error between the proposed neural network controller and the ideal feedback controller without chattering phenomena. Moreover, adaptive learning laws are derived to guarantee the system stability in the sense of the Lyapunov theory. Finally, the hardware-in-the-loop simulations are carried out to verify the feasibility and effectiveness of the proposed algorithms in different working styles.

Recurrent Spatial Transformer Networks

DEFF Research Database (Denmark)

Sønderby, Søren Kaae; Sønderby, Casper Kaae; Maaløe, Lars

2015-01-01

We integrate the recently proposed spatial transformer network (SPN) [Jaderberg et. al 2015] into a recurrent neural network (RNN) to form an RNN-SPN model. We use the RNN-SPN to classify digits in cluttered MNIST sequences. The proposed model achieves a single digit error of 1.5% compared to 2.......9% for a convolutional networks and 2.0% for convolutional networks with SPN layers. The SPN outputs a zoomed, rotated and skewed version of the input image. We investigate different down-sampling factors (ratio of pixel in input and output) for the SPN and show that the RNN-SPN model is able to down-sample the input...

Single-Cell Memory Regulates a Neural Circuit for Sensory Behavior.

Science.gov (United States)

Kobayashi, Kyogo; Nakano, Shunji; Amano, Mutsuki; Tsuboi, Daisuke; Nishioka, Tomoki; Ikeda, Shingo; Yokoyama, Genta; Kaibuchi, Kozo; Mori, Ikue

2016-01-05

Unveiling the molecular and cellular mechanisms underlying memory has been a challenge for the past few decades. Although synaptic plasticity is proven to be essential for memory formation, the significance of "single-cell memory" still remains elusive. Here, we exploited a primary culture system for the analysis of C. elegans neurons and show that a single thermosensory neuron has an ability to form, retain, and reset a temperature memory. Genetic and proteomic analyses found that the expression of the single-cell memory exhibits inter-individual variability, which is controlled by the evolutionarily conserved CaMKI/IV and Raf pathway. The variable responses of a sensory neuron influenced the neural activity of downstream interneurons, suggesting that modulation of the sensory neurons ultimately determines the behavioral output in C. elegans. Our results provide proof of single-cell memory and suggest that the individual differences in neural responses at the single-cell level can confer individuality. Copyright © 2016 The Authors. Published by Elsevier Inc. All rights reserved.

Recurrent laughter-induced syncope.

Science.gov (United States)

Gaitatzis, Athanasios; Petzold, Axel

2012-07-01

Syncope is a common presenting complaint in Neurology clinics or Emergency departments, but its causes are sometimes difficult to diagnose. Apart from vasovagal attacks, other benign, neurally mediated syncopes include "situational" syncopes, which occur after urination, coughing, swallowing, or defecation. A healthy 42-year-old male patient presented to the neurology clinic with a long history of faints triggered by spontaneous laughter, especially after funny jokes. Physical and neurological examination, and electroencephalography and magnetic resonance imaging were unremarkable. There was no evidence to suggest cardiogenic causes, epilepsy, or cataplexy and a diagnosis of laughing syncope was made. Laughter-induced syncope is usually a single event in the majority of cases, but may present as recurrent attacks as in our case. Some cases occur in association with underlying neurological conditions. Prognosis is good in the case of neurally mediated attacks. Laughter may not be recognized by physicians as a cause of syncope, which may lead to unnecessary investigations or misdiagnosis, and affect patients' quality of life.

Multiplex visibility graphs to investigate recurrent neural network dynamics

Science.gov (United States)

Bianchi, Filippo Maria; Livi, Lorenzo; Alippi, Cesare; Jenssen, Robert

2017-03-01

A recurrent neural network (RNN) is a universal approximator of dynamical systems, whose performance often depends on sensitive hyperparameters. Tuning them properly may be difficult and, typically, based on a trial-and-error approach. In this work, we adopt a graph-based framework to interpret and characterize internal dynamics of a class of RNNs called echo state networks (ESNs). We design principled unsupervised methods to derive hyperparameters configurations yielding maximal ESN performance, expressed in terms of prediction error and memory capacity. In particular, we propose to model time series generated by each neuron activations with a horizontal visibility graph, whose topological properties have been shown to be related to the underlying system dynamics. Successively, horizontal visibility graphs associated with all neurons become layers of a larger structure called a multiplex. We show that topological properties of such a multiplex reflect important features of ESN dynamics that can be used to guide the tuning of its hyperparamers. Results obtained on several benchmarks and a real-world dataset of telephone call data records show the effectiveness of the proposed methods.

Neural networks and statistical learning

CERN Document Server

Du, Ke-Lin

2014-01-01

Providing a broad but in-depth introduction to neural network and machine learning in a statistical framework, this book provides a single, comprehensive resource for study and further research. All the major popular neural network models and statistical learning approaches are covered with examples and exercises in every chapter to develop a practical working understanding of the content. Each of the twenty-five chapters includes state-of-the-art descriptions and important research results on the respective topics. The broad coverage includes the multilayer perceptron, the Hopfield network, associative memory models, clustering models and algorithms, the radial basis function network, recurrent neural networks, principal component analysis, nonnegative matrix factorization, independent component analysis, discriminant analysis, support vector machines, kernel methods, reinforcement learning, probabilistic and Bayesian networks, data fusion and ensemble learning, fuzzy sets and logic, neurofuzzy models, hardw...

Kernel Function Tuning for Single-Layer Neural Networks

Czech Academy of Sciences Publication Activity Database

Vidnerová, Petra; Neruda, Roman

-, accepted 28.11. 2017 (2018) ISSN 2278-0149 R&D Projects: GA ČR GA15-18108S Institutional support: RVO:67985807 Keywords : single-layer neural networks * kernel methods * kernel function * optimisation Subject RIV: IN - Informatics, Computer Science http://www.ijmerr.com/

Recurrent neural network approach to quantum signal: coherent state restoration for continuous-variable quantum key distribution

Science.gov (United States)

Lu, Weizhao; Huang, Chunhui; Hou, Kun; Shi, Liting; Zhao, Huihui; Li, Zhengmei; Qiu, Jianfeng

2018-05-01

In continuous-variable quantum key distribution (CV-QKD), weak signal carrying information transmits from Alice to Bob; during this process it is easily influenced by unknown noise which reduces signal-to-noise ratio, and strongly impacts reliability and stability of the communication. Recurrent quantum neural network (RQNN) is an artificial neural network model which can perform stochastic filtering without any prior knowledge of the signal and noise. In this paper, a modified RQNN algorithm with expectation maximization algorithm is proposed to process the signal in CV-QKD, which follows the basic rule of quantum mechanics. After RQNN, noise power decreases about 15 dBm, coherent signal recognition rate of RQNN is 96%, quantum bit error rate (QBER) drops to 4%, which is 6.9% lower than original QBER, and channel capacity is notably enlarged.

EMG-Based Estimation of Limb Movement Using Deep Learning With Recurrent Convolutional Neural Networks.

Science.gov (United States)

Xia, Peng; Hu, Jie; Peng, Yinghong

2017-10-25

A novel model based on deep learning is proposed to estimate kinematic information for myoelectric control from multi-channel electromyogram (EMG) signals. The neural information of limb movement is embedded in EMG signals that are influenced by all kinds of factors. In order to overcome the negative effects of variability in signals, the proposed model employs the deep architecture combining convolutional neural networks (CNNs) and recurrent neural networks (RNNs). The EMG signals are transformed to time-frequency frames as the input to the model. The limb movement is estimated by the model that is trained with the gradient descent and backpropagation procedure. We tested the model for simultaneous and proportional estimation of limb movement in eight healthy subjects and compared it with support vector regression (SVR) and CNNs on the same data set. The experimental studies show that the proposed model has higher estimation accuracy and better robustness with respect to time. The combination of CNNs and RNNs can improve the model performance compared with using CNNs alone. The model of deep architecture is promising in EMG decoding and optimization of network structures can increase the accuracy and robustness. © 2017 International Center for Artificial Organs and Transplantation and Wiley Periodicals, Inc.

Simulating the dynamics of the neutron flux in a nuclear reactor by locally recurrent neural networks

International Nuclear Information System (INIS)

Cadini, F.; Zio, E.; Pedroni, N.

2007-01-01

In this paper, a locally recurrent neural network (LRNN) is employed for approximating the temporal evolution of a nonlinear dynamic system model of a simplified nuclear reactor. To this aim, an infinite impulse response multi-layer perceptron (IIR-MLP) is trained according to a recursive back-propagation (RBP) algorithm. The network nodes contain internal feedback paths and their connections are realized by means of IIR synaptic filters, which provide the LRNN with the necessary system state memory

New results on global exponential stability of recurrent neural networks with time-varying delays

International Nuclear Information System (INIS)

Xu Shengyuan; Chu Yuming; Lu Junwei

2006-01-01

This Letter provides new sufficient conditions for the existence, uniqueness and global exponential stability of the equilibrium point of recurrent neural networks with time-varying delays by employing Lyapunov functions and using the Halanay inequality. The time-varying delays are not necessarily differentiable. Both Lipschitz continuous activation functions and monotone nondecreasing activation functions are considered. The derived stability criteria are expressed in terms of linear matrix inequalities (LMIs), which can be checked easily by resorting to recently developed algorithms solving LMIs. Furthermore, the proposed stability results are less conservative than some previous ones in the literature, which is demonstrated via some numerical examples

New results on global exponential stability of recurrent neural networks with time-varying delays

Energy Technology Data Exchange (ETDEWEB)

Xu Shengyuan [Department of Automation, Nanjing University of Science and Technology, Nanjing 210094 (China)]. E-mail: syxu02@yahoo.com.cn; Chu Yuming [Department of Mathematics, Huzhou Teacher' s College, Huzhou, Zhejiang 313000 (China); Lu Junwei [School of Electrical and Automation Engineering, Nanjing Normal University, 78 Bancang Street, Nanjing, 210042 (China)

2006-04-03

This Letter provides new sufficient conditions for the existence, uniqueness and global exponential stability of the equilibrium point of recurrent neural networks with time-varying delays by employing Lyapunov functions and using the Halanay inequality. The time-varying delays are not necessarily differentiable. Both Lipschitz continuous activation functions and monotone nondecreasing activation functions are considered. The derived stability criteria are expressed in terms of linear matrix inequalities (LMIs), which can be checked easily by resorting to recently developed algorithms solving LMIs. Furthermore, the proposed stability results are less conservative than some previous ones in the literature, which is demonstrated via some numerical examples.

Sequence-specific bias correction for RNA-seq data using recurrent neural networks.

Science.gov (United States)

Zhang, Yao-Zhong; Yamaguchi, Rui; Imoto, Seiya; Miyano, Satoru

2017-01-25

The recent success of deep learning techniques in machine learning and artificial intelligence has stimulated a great deal of interest among bioinformaticians, who now wish to bring the power of deep learning to bare on a host of bioinformatical problems. Deep learning is ideally suited for biological problems that require automatic or hierarchical feature representation for biological data when prior knowledge is limited. In this work, we address the sequence-specific bias correction problem for RNA-seq data redusing Recurrent Neural Networks (RNNs) to model nucleotide sequences without pre-determining sequence structures. The sequence-specific bias of a read is then calculated based on the sequence probabilities estimated by RNNs, and used in the estimation of gene abundance. We explore the application of two popular RNN recurrent units for this task and demonstrate that RNN-based approaches provide a flexible way to model nucleotide sequences without knowledge of predetermined sequence structures. Our experiments show that training a RNN-based nucleotide sequence model is efficient and RNN-based bias correction methods compare well with the-state-of-the-art sequence-specific bias correction method on the commonly used MAQC-III data set. RNNs provides an alternative and flexible way to calculate sequence-specific bias without explicitly pre-determining sequence structures.

Fractional Hopfield Neural Networks: Fractional Dynamic Associative Recurrent Neural Networks.

Science.gov (United States)

Pu, Yi-Fei; Yi, Zhang; Zhou, Ji-Liu

2017-10-01

This paper mainly discusses a novel conceptual framework: fractional Hopfield neural networks (FHNN). As is commonly known, fractional calculus has been incorporated into artificial neural networks, mainly because of its long-term memory and nonlocality. Some researchers have made interesting attempts at fractional neural networks and gained competitive advantages over integer-order neural networks. Therefore, it is naturally makes one ponder how to generalize the first-order Hopfield neural networks to the fractional-order ones, and how to implement FHNN by means of fractional calculus. We propose to introduce a novel mathematical method: fractional calculus to implement FHNN. First, we implement fractor in the form of an analog circuit. Second, we implement FHNN by utilizing fractor and the fractional steepest descent approach, construct its Lyapunov function, and further analyze its attractors. Third, we perform experiments to analyze the stability and convergence of FHNN, and further discuss its applications to the defense against chip cloning attacks for anticounterfeiting. The main contribution of our work is to propose FHNN in the form of an analog circuit by utilizing a fractor and the fractional steepest descent approach, construct its Lyapunov function, prove its Lyapunov stability, analyze its attractors, and apply FHNN to the defense against chip cloning attacks for anticounterfeiting. A significant advantage of FHNN is that its attractors essentially relate to the neuron's fractional order. FHNN possesses the fractional-order-stability and fractional-order-sensitivity characteristics.

The synaptic properties of cells define the hallmarks of interval timing in a recurrent neural network.

Science.gov (United States)

Pérez, Oswaldo; Merchant, Hugo

2018-04-03

Extensive research has described two key features of interval timing. The bias property is associated with accuracy and implies that time is overestimated for short intervals and underestimated for long intervals. The scalar property is linked to precision and states that the variability of interval estimates increases as a function of interval duration. The neural mechanisms behind these properties are not well understood. Here we implemented a recurrent neural network that mimics a cortical ensemble and includes cells that show paired-pulse facilitation and slow inhibitory synaptic currents. The network produces interval selective responses and reproduces both bias and scalar properties when a Bayesian decoder reads its activity. Notably, the interval-selectivity, timing accuracy, and precision of the network showed complex changes as a function of the decay time constants of the modeled synaptic properties and the level of background activity of the cells. These findings suggest that physiological values of the time constants for paired-pulse facilitation and GABAb, as well as the internal state of the network, determine the bias and scalar properties of interval timing. Significant Statement Timing is a fundamental element of complex behavior, including music and language. Temporal processing in a wide variety of contexts shows two primary features: time estimates exhibit a shift towards the mean (the bias property) and are more variable for longer intervals (the scalar property). We implemented a recurrent neural network that includes long-lasting synaptic currents, which can not only produce interval selective responses but also follow the bias and scalar properties. Interestingly, only physiological values of the time constants for paired-pulse facilitation and GABAb, as well as intermediate background activity within the network can reproduce the two key features of interval timing. Copyright © 2018 the authors.

Automatic temporal segment detection via bilateral long short-term memory recurrent neural networks

Science.gov (United States)

Sun, Bo; Cao, Siming; He, Jun; Yu, Lejun; Li, Liandong

2017-03-01

Constrained by the physiology, the temporal factors associated with human behavior, irrespective of facial movement or body gesture, are described by four phases: neutral, onset, apex, and offset. Although they may benefit related recognition tasks, it is not easy to accurately detect such temporal segments. An automatic temporal segment detection framework using bilateral long short-term memory recurrent neural networks (BLSTM-RNN) to learn high-level temporal-spatial features, which synthesizes the local and global temporal-spatial information more efficiently, is presented. The framework is evaluated in detail over the face and body database (FABO). The comparison shows that the proposed framework outperforms state-of-the-art methods for solving the problem of temporal segment detection.

Nonlinear dynamics analysis of a self-organizing recurrent neural network: chaos waning.

Science.gov (United States)

Eser, Jürgen; Zheng, Pengsheng; Triesch, Jochen

2014-01-01

Self-organization is thought to play an important role in structuring nervous systems. It frequently arises as a consequence of plasticity mechanisms in neural networks: connectivity determines network dynamics which in turn feed back on network structure through various forms of plasticity. Recently, self-organizing recurrent neural network models (SORNs) have been shown to learn non-trivial structure in their inputs and to reproduce the experimentally observed statistics and fluctuations of synaptic connection strengths in cortex and hippocampus. However, the dynamics in these networks and how they change with network evolution are still poorly understood. Here we investigate the degree of chaos in SORNs by studying how the networks' self-organization changes their response to small perturbations. We study the effect of perturbations to the excitatory-to-excitatory weight matrix on connection strengths and on unit activities. We find that the network dynamics, characterized by an estimate of the maximum Lyapunov exponent, becomes less chaotic during its self-organization, developing into a regime where only few perturbations become amplified. We also find that due to the mixing of discrete and (quasi-)continuous variables in SORNs, small perturbations to the synaptic weights may become amplified only after a substantial delay, a phenomenon we propose to call deferred chaos.

Single-hidden-layer feed-forward quantum neural network based on Grover learning.

Science.gov (United States)

Liu, Cheng-Yi; Chen, Chein; Chang, Ching-Ter; Shih, Lun-Min

2013-09-01

In this paper, a novel single-hidden-layer feed-forward quantum neural network model is proposed based on some concepts and principles in the quantum theory. By combining the quantum mechanism with the feed-forward neural network, we defined quantum hidden neurons and connected quantum weights, and used them as the fundamental information processing unit in a single-hidden-layer feed-forward neural network. The quantum neurons make a wide range of nonlinear functions serve as the activation functions in the hidden layer of the network, and the Grover searching algorithm outstands the optimal parameter setting iteratively and thus makes very efficient neural network learning possible. The quantum neuron and weights, along with a Grover searching algorithm based learning, result in a novel and efficient neural network characteristic of reduced network, high efficient training and prospect application in future. Some simulations are taken to investigate the performance of the proposed quantum network and the result show that it can achieve accurate learning. Copyright © 2013 Elsevier Ltd. All rights reserved.

Using Long-Short-Term-Memory Recurrent Neural Networks to Predict Aviation Engine Vibrations

Science.gov (United States)

ElSaid, AbdElRahman Ahmed

This thesis examines building viable Recurrent Neural Networks (RNN) using Long Short Term Memory (LSTM) neurons to predict aircraft engine vibrations. The different networks are trained on a large database of flight data records obtained from an airline containing flights that suffered from excessive vibration. RNNs can provide a more generalizable and robust method for prediction over analytical calculations of engine vibration, as analytical calculations must be solved iteratively based on specific empirical engine parameters, and this database contains multiple types of engines. Further, LSTM RNNs provide a "memory" of the contribution of previous time series data which can further improve predictions of future vibration values. LSTM RNNs were used over traditional RNNs, as those suffer from vanishing/exploding gradients when trained with back propagation. The study managed to predict vibration values for 1, 5, 10, and 20 seconds in the future, with 2.84% 3.3%, 5.51% and 10.19% mean absolute error, respectively. These neural networks provide a promising means for the future development of warning systems so that suitable actions can be taken before the occurrence of excess vibration to avoid unfavorable situations during flight.

Fast computation with spikes in a recurrent neural network

International Nuclear Information System (INIS)

Jin, Dezhe Z.; Seung, H. Sebastian

2002-01-01

Neural networks with recurrent connections are sometimes regarded as too slow at computation to serve as models of the brain. Here we analytically study a counterexample, a network consisting of N integrate-and-fire neurons with self excitation, all-to-all inhibition, instantaneous synaptic coupling, and constant external driving inputs. When the inhibition and/or excitation are large enough, the network performs a winner-take-all computation for all possible external inputs and initial states of the network. The computation is done very quickly: As soon as the winner spikes once, the computation is completed since no other neurons will spike. For some initial states, the winner is the first neuron to spike, and the computation is done at the first spike of the network. In general, there are M potential winners, corresponding to the top M external inputs. When the external inputs are close in magnitude, M tends to be larger. If M>1, the selection of the actual winner is strongly influenced by the initial states. If a special relation between the excitation and inhibition is satisfied, the network always selects the neuron with the maximum external input as the winner

A delay-dependent LMI approach to dynamics analysis of discrete-time recurrent neural networks with time-varying delays

International Nuclear Information System (INIS)

Song, Qiankun; Wang, Zidong

2007-01-01

In this Letter, the analysis problem for the existence and stability of periodic solutions is investigated for a class of general discrete-time recurrent neural networks with time-varying delays. For the neural networks under study, a generalized activation function is considered, and the traditional assumptions on the boundedness, monotony and differentiability of the activation functions are removed. By employing the latest free-weighting matrix method, an appropriate Lyapunov-Krasovskii functional is constructed and several sufficient conditions are established to ensure the existence, uniqueness, and globally exponential stability of the periodic solution for the addressed neural network. The conditions are dependent on both the lower bound and upper bound of the time-varying time delays. Furthermore, the conditions are expressed in terms of the linear matrix inequalities (LMIs), which can be checked numerically using the effective LMI toolbox in MATLAB. Two simulation examples are given to show the effectiveness and less conservatism of the proposed criteria

Intelligent Noise Removal from EMG Signal Using Focused Time-Lagged Recurrent Neural Network

Directory of Open Access Journals (Sweden)

S. N. Kale

2009-01-01

Full Text Available Electromyography (EMG signals can be used for clinical/biomedical application and modern human computer interaction. EMG signals acquire noise while traveling through tissue, inherent noise in electronics equipment, ambient noise, and so forth. ANN approach is studied for reduction of noise in EMG signal. In this paper, it is shown that Focused Time-Lagged Recurrent Neural Network (FTLRNN can elegantly solve to reduce the noise from EMG signal. After rigorous computer simulations, authors developed an optimal FTLRNN model, which removes the noise from the EMG signal. Results show that the proposed optimal FTLRNN model has an MSE (Mean Square Error as low as 0.000067 and 0.000048, correlation coefficient as high as 0.99950 and 0.99939 for noise signal and EMG signal, respectively, when validated on the test dataset. It is also noticed that the output of the estimated FTLRNN model closely follows the real one. This network is indeed robust as EMG signal tolerates the noise variance from 0.1 to 0.4 for uniform noise and 0.30 for Gaussian noise. It is clear that the training of the network is independent of specific partitioning of dataset. It is seen that the performance of the proposed FTLRNN model clearly outperforms the best Multilayer perceptron (MLP and Radial Basis Function NN (RBF models. The simple NN model such as the FTLRNN with single-hidden layer can be employed to remove noise from EMG signal.

Design of a heart rate controller for treadmill exercise using a recurrent fuzzy neural network.

Science.gov (United States)

Lu, Chun-Hao; Wang, Wei-Cheng; Tai, Cheng-Chi; Chen, Tien-Chi

2016-05-01

In this study, we developed a computer controlled treadmill system using a recurrent fuzzy neural network heart rate controller (RFNNHRC). Treadmill speeds and inclines were controlled by corresponding control servo motors. The RFNNHRC was used to generate the control signals to automatically control treadmill speed and incline to minimize the user heart rate deviations from a preset profile. The RFNNHRC combines a fuzzy reasoning capability to accommodate uncertain information and an artificial recurrent neural network learning process that corrects for treadmill system nonlinearities and uncertainties. Treadmill speeds and inclines are controlled by the RFNNHRC to achieve minimal heart rate deviation from a pre-set profile using adjustable parameters and an on-line learning algorithm that provides robust performance against parameter variations. The on-line learning algorithm of RFNNHRC was developed and implemented using a dsPIC 30F4011 DSP. Application of the proposed control scheme to heart rate responses of runners resulted in smaller fluctuations than those produced by using proportional integra control, and treadmill speeds and inclines were smoother. The present experiments demonstrate improved heart rate tracking performance with the proposed control scheme. The RFNNHRC scheme with adjustable parameters and an on-line learning algorithm was applied to a computer controlled treadmill system with heart rate control during treadmill exercise. Novel RFNNHRC structure and controller stability analyses were introduced. The RFNNHRC were tuned using a Lyapunov function to ensure system stability. The superior heart rate control with the proposed RFNNHRC scheme was demonstrated with various pre-set heart rates. Copyright © 2016 Elsevier Ireland Ltd. All rights reserved.

Interpretation of Recurrent Neural Networks

DEFF Research Database (Denmark)

Pedersen, Morten With; Larsen, Jan

1997-01-01

This paper addresses techniques for interpretation and characterization of trained recurrent nets for time series problems. In particular, we focus on assessment of effective memory and suggest an operational definition of memory. Further we discuss the evaluation of learning curves. Various nume...

Application of recurrent neural networks for drought projections in California

Science.gov (United States)

Le, J. A.; El-Askary, H. M.; Allali, M.; Struppa, D. C.

2017-05-01

We use recurrent neural networks (RNNs) to investigate the complex interactions between the long-term trend in dryness and a projected, short but intense, period of wetness due to the 2015-2016 El Niño. Although it was forecasted that this El Niño season would bring significant rainfall to the region, our long-term projections of the Palmer Z Index (PZI) showed a continuing drought trend, contrasting with the 1998-1999 El Niño event. RNN training considered PZI data during 1896-2006 that was validated against the 2006-2015 period to evaluate the potential of extreme precipitation forecast. We achieved a statistically significant correlation of 0.610 between forecasted and observed PZI on the validation set for a lead time of 1 month. This gives strong confidence to the forecasted precipitation indicator. The 2015-2016 El Niño season proved to be relatively weak as compared with the 1997-1998, with a peak PZI anomaly of 0.242 standard deviations below historical averages, continuing drought conditions.

An adaptive PID like controller using mix locally recurrent neural network for robotic manipulator with variable payload.

Science.gov (United States)

Sharma, Richa; Kumar, Vikas; Gaur, Prerna; Mittal, A P

2016-05-01

Being complex, non-linear and coupled system, the robotic manipulator cannot be effectively controlled using classical proportional-integral-derivative (PID) controller. To enhance the effectiveness of the conventional PID controller for the nonlinear and uncertain systems, gains of the PID controller should be conservatively tuned and should adapt to the process parameter variations. In this work, a mix locally recurrent neural network (MLRNN) architecture is investigated to mimic a conventional PID controller which consists of at most three hidden nodes which act as proportional, integral and derivative node. The gains of the mix locally recurrent neural network based PID (MLRNNPID) controller scheme are initialized with a newly developed cuckoo search algorithm (CSA) based optimization method rather than assuming randomly. A sequential learning based least square algorithm is then investigated for the on-line adaptation of the gains of MLRNNPID controller. The performance of the proposed controller scheme is tested against the plant parameters uncertainties and external disturbances for both links of the two link robotic manipulator with variable payload (TL-RMWVP). The stability of the proposed controller is analyzed using Lyapunov stability criteria. A performance comparison is carried out among MLRNNPID controller, CSA optimized NNPID (OPTNNPID) controller and CSA optimized conventional PID (OPTPID) controller in order to establish the effectiveness of the MLRNNPID controller. Copyright © 2016 ISA. Published by Elsevier Ltd. All rights reserved.

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

Science.gov (United States)

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

Wind Turbine Driving a PM Synchronous Generator Using Novel Recurrent Chebyshev Neural Network Control with the Ideal Learning Rate

Directory of Open Access Journals (Sweden)

Chih-Hong Lin

2016-06-01

Full Text Available A permanent magnet (PM synchronous generator system driven by wind turbine (WT, connected with smart grid via AC-DC converter and DC-AC converter, are controlled by the novel recurrent Chebyshev neural network (NN and amended particle swarm optimization (PSO to regulate output power and output voltage in two power converters in this study. Because a PM synchronous generator system driven by WT is an unknown non-linear and time-varying dynamic system, the on-line training novel recurrent Chebyshev NN control system is developed to regulate DC voltage of the AC-DC converter and AC voltage of the DC-AC converter connected with smart grid. Furthermore, the variable learning rate of the novel recurrent Chebyshev NN is regulated according to discrete-type Lyapunov function for improving the control performance and enhancing convergent speed. Finally, some experimental results are shown to verify the effectiveness of the proposed control method for a WT driving a PM synchronous generator system in smart grid.

LFNet: A Novel Bidirectional Recurrent Convolutional Neural Network for Light-Field Image Super-Resolution.

Science.gov (United States)

Wang, Yunlong; Liu, Fei; Zhang, Kunbo; Hou, Guangqi; Sun, Zhenan; Tan, Tieniu

2018-09-01

The low spatial resolution of light-field image poses significant difficulties in exploiting its advantage. To mitigate the dependency of accurate depth or disparity information as priors for light-field image super-resolution, we propose an implicitly multi-scale fusion scheme to accumulate contextual information from multiple scales for super-resolution reconstruction. The implicitly multi-scale fusion scheme is then incorporated into bidirectional recurrent convolutional neural network, which aims to iteratively model spatial relations between horizontally or vertically adjacent sub-aperture images of light-field data. Within the network, the recurrent convolutions are modified to be more effective and flexible in modeling the spatial correlations between neighboring views. A horizontal sub-network and a vertical sub-network of the same network structure are ensembled for final outputs via stacked generalization. Experimental results on synthetic and real-world data sets demonstrate that the proposed method outperforms other state-of-the-art methods by a large margin in peak signal-to-noise ratio and gray-scale structural similarity indexes, which also achieves superior quality for human visual systems. Furthermore, the proposed method can enhance the performance of light field applications such as depth estimation.

Dynamic training algorithm for dynamic neural networks

International Nuclear Information System (INIS)

Tan, Y.; Van Cauwenberghe, A.; Liu, Z.

1996-01-01

The widely used backpropagation algorithm for training neural networks based on the gradient descent has a significant drawback of slow convergence. A Gauss-Newton method based recursive least squares (RLS) type algorithm with dynamic error backpropagation is presented to speed-up the learning procedure of neural networks with local recurrent terms. Finally, simulation examples concerning the applications of the RLS type algorithm to identification of nonlinear processes using a local recurrent neural network are also included in this paper

Clinical significance and predictive factors of early massive recurrence after radiofrequency ablation in patients with a single small hepatocellular carcinoma

Directory of Open Access Journals (Sweden)

Ju-Yeon Cho

2016-12-01

Full Text Available Background/Aims Radiofrequency ablation (RFA is one of the most frequently applied curative treatments in patients with a single small hepatocellular carcinoma (HCC. However, the clinical significance of and risk factors for early massive recurrence after RFA—a dreadful event limiting further curative treatment—have not been fully evaluated. Methods In total, 438 patients with a single HCC of size ≤3 cm who underwent percutaneous RFA as an initial treatment between 2006 and 2009 were included. Baseline patient characteristics, overall survival, predictive factors, and recurrence after RFA were evaluated. In addition, the incidence, impact on survival, and predictive factors of early massive recurrence, and initial recurrence beyond the Milan criteria within 2 years were also investigated. Results During the median follow-up of 68.4 months, recurrent HCC was confirmed in 302 (68.9% patients, with early massive recurrence in 27 patients (6.2%. The 1-, 3-, and 5-year overall survival rates were 95.4%, 84.7%, and 81.8%, respectively, in patients with no recurrence, 99.6%, 86.4%, and 70.1% in patients with recurrence within the Milan criteria or late recurrence, and 92.6%, 46.5%, and 0.05% in patients with early massive recurrence. Multivariable analysis identified older age, Child-Pugh score B or C, and early massive recurrence as predictive of poor overall survival. A tumor size of ≥2 cm and tumor location adjacent to the colon were independent risk factors predictive of early massive recurrence. Conclusions Early massive recurrence is independently predictive of poor overall survival after RFA in patients with a single small HCC. Tumors sized ≥2 cm and located adjacent to the colon appear to be independent risk factors for early massive recurrence.

Novel delay-distribution-dependent stability analysis for continuous-time recurrent neural networks with stochastic delay

International Nuclear Information System (INIS)

Wang Shen-Quan; Feng Jian; Zhao Qing

2012-01-01

In this paper, the problem of delay-distribution-dependent stability is investigated for continuous-time recurrent neural networks (CRNNs) with stochastic delay. Different from the common assumptions on time delays, it is assumed that the probability distribution of the delay taking values in some intervals is known a priori. By making full use of the information concerning the probability distribution of the delay and by using a tighter bounding technique (the reciprocally convex combination method), less conservative asymptotic mean-square stable sufficient conditions are derived in terms of linear matrix inequalities (LMIs). Two numerical examples show that our results are better than the existing ones. (general)

Training Excitatory-Inhibitory Recurrent Neural Networks for Cognitive Tasks: A Simple and Flexible Framework.

Directory of Open Access Journals (Sweden)

H Francis Song

2016-02-01

Full Text Available The ability to simultaneously record from large numbers of neurons in behaving animals has ushered in a new era for the study of the neural circuit mechanisms underlying cognitive functions. One promising approach to uncovering the dynamical and computational principles governing population responses is to analyze model recurrent neural networks (RNNs that have been optimized to perform the same tasks as behaving animals. Because the optimization of network parameters specifies the desired output but not the manner in which to achieve this output, "trained" networks serve as a source of mechanistic hypotheses and a testing ground for data analyses that link neural computation to behavior. Complete access to the activity and connectivity of the circuit, and the ability to manipulate them arbitrarily, make trained networks a convenient proxy for biological circuits and a valuable platform for theoretical investigation. However, existing RNNs lack basic biological features such as the distinction between excitatory and inhibitory units (Dale's principle, which are essential if RNNs are to provide insights into the operation of biological circuits. Moreover, trained networks can achieve the same behavioral performance but differ substantially in their structure and dynamics, highlighting the need for a simple and flexible framework for the exploratory training of RNNs. Here, we describe a framework for gradient descent-based training of excitatory-inhibitory RNNs that can incorporate a variety of biological knowledge. We provide an implementation based on the machine learning library Theano, whose automatic differentiation capabilities facilitate modifications and extensions. We validate this framework by applying it to well-known experimental paradigms such as perceptual decision-making, context-dependent integration, multisensory integration, parametric working memory, and motor sequence generation. Our results demonstrate the wide range of neural

Training Excitatory-Inhibitory Recurrent Neural Networks for Cognitive Tasks: A Simple and Flexible Framework

Science.gov (United States)

Wang, Xiao-Jing

2016-01-01

The ability to simultaneously record from large numbers of neurons in behaving animals has ushered in a new era for the study of the neural circuit mechanisms underlying cognitive functions. One promising approach to uncovering the dynamical and computational principles governing population responses is to analyze model recurrent neural networks (RNNs) that have been optimized to perform the same tasks as behaving animals. Because the optimization of network parameters specifies the desired output but not the manner in which to achieve this output, “trained” networks serve as a source of mechanistic hypotheses and a testing ground for data analyses that link neural computation to behavior. Complete access to the activity and connectivity of the circuit, and the ability to manipulate them arbitrarily, make trained networks a convenient proxy for biological circuits and a valuable platform for theoretical investigation. However, existing RNNs lack basic biological features such as the distinction between excitatory and inhibitory units (Dale’s principle), which are essential if RNNs are to provide insights into the operation of biological circuits. Moreover, trained networks can achieve the same behavioral performance but differ substantially in their structure and dynamics, highlighting the need for a simple and flexible framework for the exploratory training of RNNs. Here, we describe a framework for gradient descent-based training of excitatory-inhibitory RNNs that can incorporate a variety of biological knowledge. We provide an implementation based on the machine learning library Theano, whose automatic differentiation capabilities facilitate modifications and extensions. We validate this framework by applying it to well-known experimental paradigms such as perceptual decision-making, context-dependent integration, multisensory integration, parametric working memory, and motor sequence generation. Our results demonstrate the wide range of neural activity

PERAMALAN KONSUMSI LISTRIK JANGKA PENDEK DENGAN ARIMA MUSIMAN GANDA DAN ELMAN-RECURRENT NEURAL NETWORK

Directory of Open Access Journals (Sweden)

Suhartono Suhartono

2009-07-01

Full Text Available Neural network (NN is one of many method used to predict the electricity consumption per hour in many countries. NN method which is used in many previous studies is Feed-Forward Neural Network (FFNN or Autoregressive Neural Network(AR-NN. AR-NN model is not able to capture and explain the effect of moving average (MA order on a time series of data. This research was conducted with the purpose of reviewing the application of other types of NN, that is Elman-Recurrent Neural Network (Elman-RNN which could explain MA order effect and compare the result of prediction accuracy with multiple seasonal ARIMA (Autoregressive Integrated Moving Average models. As a case study, we used data electricity consumption per hour in Mengare Gresik. Result of analysis showed that the best of double seasonal Arima models suited to short-term forecasting in the case study data is ARIMA([1,2,3,4,6,7,9,10,14,21,33],1,8(0,1,124 (1,1,0168. This model produces a white noise residuals, but it does not have a normal distribution due to suspected outlier. Outlier detection in iterative produce 14 innovation outliers. There are 4 inputs of Elman-RNN network that were examined and tested for forecasting the data, the input according to lag Arima, input such as lag Arima plus 14 dummy outlier, inputs are the lag-multiples of 24 up to lag 480, and the inputs are lag 1 and lag multiples of 24+1. All of four network uses one hidden layer with tangent sigmoid activation function and one output with a linear function. The result of comparative forecast accuracy through value of MAPE out-sample showed that the fourth networks, namely Elman-RNN (22, 3, 1, is the best model for forecasting electricity consumption per hour in short term in Mengare Gresik.

Tracking Control Based on Recurrent Neural Networks for Nonlinear Systems with Multiple Inputs and Unknown Deadzone

Directory of Open Access Journals (Sweden)

J. Humberto Pérez-Cruz

2012-01-01

Full Text Available This paper deals with the problem of trajectory tracking for a broad class of uncertain nonlinear systems with multiple inputs each one subject to an unknown symmetric deadzone. On the basis of a model of the deadzone as a combination of a linear term and a disturbance-like term, a continuous-time recurrent neural network is directly employed in order to identify the uncertain dynamics. By using a Lyapunov analysis, the exponential convergence of the identification error to a bounded zone is demonstrated. Subsequently, by a proper control law, the state of the neural network is compelled to follow a bounded reference trajectory. This control law is designed in such a way that the singularity problem is conveniently avoided and the exponential convergence to a bounded zone of the difference between the state of the neural identifier and the reference trajectory can be proven. Thus, the exponential convergence of the tracking error to a bounded zone and the boundedness of all closed-loop signals can be guaranteed. One of the main advantages of the proposed strategy is that the controller can work satisfactorily without any specific knowledge of an upper bound for the unmodeled dynamics and/or the disturbance term.

Single-Iteration Learning Algorithm for Feed-Forward Neural Networks

Energy Technology Data Exchange (ETDEWEB)

Barhen, J.; Cogswell, R.; Protopopescu, V.

1999-07-31

A new methodology for neural learning is presented, whereby only a single iteration is required to train a feed-forward network with near-optimal results. To this aim, a virtual input layer is added to the multi-layer architecture. The virtual input layer is connected to the nominal input layer by a specird nonlinear transfer function, and to the fwst hidden layer by regular (linear) synapses. A sequence of alternating direction singular vrdue decompositions is then used to determine precisely the inter-layer synaptic weights. This algorithm exploits the known separability of the linear (inter-layer propagation) and nonlinear (neuron activation) aspects of information &ansfer within a neural network.

Adaptive Sliding Mode Control of Dynamic Systems Using Double Loop Recurrent Neural Network Structure.

Science.gov (United States)

Fei, Juntao; Lu, Cheng

2018-04-01

In this paper, an adaptive sliding mode control system using a double loop recurrent neural network (DLRNN) structure is proposed for a class of nonlinear dynamic systems. A new three-layer RNN is proposed to approximate unknown dynamics with two different kinds of feedback loops where the firing weights and output signal calculated in the last step are stored and used as the feedback signals in each feedback loop. Since the new structure has combined the advantages of internal feedback NN and external feedback NN, it can acquire the internal state information while the output signal is also captured, thus the new designed DLRNN can achieve better approximation performance compared with the regular NNs without feedback loops or the regular RNNs with a single feedback loop. The new proposed DLRNN structure is employed in an equivalent controller to approximate the unknown nonlinear system dynamics, and the parameters of the DLRNN are updated online by adaptive laws to get favorable approximation performance. To investigate the effectiveness of the proposed controller, the designed adaptive sliding mode controller with the DLRNN is applied to a -axis microelectromechanical system gyroscope to control the vibrating dynamics of the proof mass. Simulation results demonstrate that the proposed methodology can achieve good tracking property, and the comparisons of the approximation performance between radial basis function NN, RNN, and DLRNN show that the DLRNN can accurately estimate the unknown dynamics with a fast speed while the internal states of DLRNN are more stable.

A mathematical analysis of the effects of Hebbian learning rules on the dynamics and structure of discrete-time random recurrent neural networks.

Science.gov (United States)

Siri, Benoît; Berry, Hugues; Cessac, Bruno; Delord, Bruno; Quoy, Mathias

2008-12-01

We present a mathematical analysis of the effects of Hebbian learning in random recurrent neural networks, with a generic Hebbian learning rule, including passive forgetting and different timescales, for neuronal activity and learning dynamics. Previous numerical work has reported that Hebbian learning drives the system from chaos to a steady state through a sequence of bifurcations. Here, we interpret these results mathematically and show that these effects, involving a complex coupling between neuronal dynamics and synaptic graph structure, can be analyzed using Jacobian matrices, which introduce both a structural and a dynamical point of view on neural network evolution. Furthermore, we show that sensitivity to a learned pattern is maximal when the largest Lyapunov exponent is close to 0. We discuss how neural networks may take advantage of this regime of high functional interest.

Fast convergence of spike sequences to periodic patterns in recurrent networks

International Nuclear Information System (INIS)

Jin, Dezhe Z.

2002-01-01

The dynamical attractors are thought to underlie many biological functions of recurrent neural networks. Here we show that stable periodic spike sequences with precise timings are the attractors of the spiking dynamics of recurrent neural networks with global inhibition. Almost all spike sequences converge within a finite number of transient spikes to these attractors. The convergence is fast, especially when the global inhibition is strong. These results support the possibility that precise spatiotemporal sequences of spikes are useful for information encoding and processing in biological neural networks

Gender Differences in Risk Factors for Single and Recurrent Falls Among the Community-Dwelling Elderly

OpenAIRE

Yu Mei O; Fatima El Fakiri

2015-01-01

The purpose of this study was to identify gender differences in risk factors of fall accidents among older people, and whether these factors differ between single and recurrent fallers. A total of 4,426 individuals aged ≥65 years from two large-scale health surveys provided data. Logistic regression analyses were used to identify risk factors and to determine the risk model for falling and recurrent falling in men and ...

Emergence of unstable itinerant orbits in a recurrent neural network model

International Nuclear Information System (INIS)

Suemitsu, Yoshikazu; Nara, Shigetoshi

2005-01-01

A recurrent neural network model with time delay is investigated by numerical methods. The model functions as both conventional associative memory and also enables us to embed a new kind of memory attractor that cannot be realized in models without time delay, for example chain-ring attractors. This is attributed to the fact that the time delay extends the available state space dimension. The difference between the basin structures of chain-ring attractors and of isolated cycle attractors is investigated with respect to the two attractor pattern sets, random memory patterns and designed memory patterns with intended structures. Compared to isolated attractors with random memory patterns, the basins of chain-ring attractors are reduced considerably. Computer experiments confirm that the basin volume of each embedded chain-ring attractor shrinks and the emergence of unstable itinerant orbits in the outer state space of the memory attractor basins is discovered. The instability of such itinerant orbits is investigated. Results show that a 1-bit difference in initial conditions does not exceed 10% of a total dimension within 100 updating steps

Equivalence of Equilibrium Propagation and Recurrent Backpropagation

OpenAIRE

Scellier, Benjamin; Bengio, Yoshua

2017-01-01

Recurrent Backpropagation and Equilibrium Propagation are algorithms for fixed point recurrent neural networks which differ in their second phase. In the first phase, both algorithms converge to a fixed point which corresponds to the configuration where the prediction is made. In the second phase, Recurrent Backpropagation computes error derivatives whereas Equilibrium Propagation relaxes to another nearby fixed point. In this work we establish a close connection between these two algorithms....

Recurrent varicocele

Directory of Open Access Journals (Sweden)

Katherine Rotker

2016-01-01

Full Text Available Varicocele recurrence is one of the most common complications associated with varicocele repair. A systematic review was performed to evaluate varicocele recurrence rates, anatomic causes of recurrence, and methods of management of recurrent varicoceles. The PubMed database was evaluated using keywords "recurrent" and "varicocele" as well as MESH criteria "recurrent" and "varicocele." Articles were not included that were not in English, represented single case reports, focused solely on subclinical varicocele, or focused solely on a pediatric population (age <18. Rates of recurrence vary with the technique of varicocele repair from 0% to 35%. Anatomy of recurrence can be defined by venography. Management of varicocele recurrence can be surgical or via embolization.

Application of Recurrent Neural Networks on El Nino Impact on California Climate

Science.gov (United States)

Le, J.; El-Askary, H. M.; Allai, M.

2017-12-01

Following our successful paper on the application for the El Nino season of 2015-2016 over Southern California, we use recurrent neural networks (RNNs) to investigate the complex interactions between the long-term trend in dryness and a projected, short but intense, period of wetness due to the 2015-2016 El Niño. Although it was forecasted that this El Niño season would bring significant rainfall to the region, our long-term projections of the Palmer Z Index (PZI) showed a continuing drought trend. We achieved a statistically significant correlation of 0.610 between forecasted and observed PZI on the validation set for a lead time of 1 month. This gives strong confidence to the forecasted precipitation indicator. These predictions were bourne out in the resulting data. This paper details the expansion of our system to the climate of the entire California climate as a whole, dealing with inter-relationships and spatial variations within the state.

Discrete-time recurrent neural networks with time-varying delays: Exponential stability analysis

International Nuclear Information System (INIS)

Liu, Yurong; Wang, Zidong; Serrano, Alan; Liu, Xiaohui

2007-01-01

This Letter is concerned with the analysis problem of exponential stability for a class of discrete-time recurrent neural networks (DRNNs) with time delays. The delay is of the time-varying nature, and the activation functions are assumed to be neither differentiable nor strict monotonic. Furthermore, the description of the activation functions is more general than the recently commonly used Lipschitz conditions. Under such mild conditions, we first prove the existence of the equilibrium point. Then, by employing a Lyapunov-Krasovskii functional, a unified linear matrix inequality (LMI) approach is developed to establish sufficient conditions for the DRNNs to be globally exponentially stable. It is shown that the delayed DRNNs are globally exponentially stable if a certain LMI is solvable, where the feasibility of such an LMI can be easily checked by using the numerically efficient Matlab LMI Toolbox. A simulation example is presented to show the usefulness of the derived LMI-based stability condition

A recurrent neural model for proto-object based contour integration and figure-ground segregation.

Science.gov (United States)

Hu, Brian; Niebur, Ernst

2017-12-01

Visual processing of objects makes use of both feedforward and feedback streams of information. However, the nature of feedback signals is largely unknown, as is the identity of the neuronal populations in lower visual areas that receive them. Here, we develop a recurrent neural model to address these questions in the context of contour integration and figure-ground segregation. A key feature of our model is the use of grouping neurons whose activity represents tentative objects ("proto-objects") based on the integration of local feature information. Grouping neurons receive input from an organized set of local feature neurons, and project modulatory feedback to those same neurons. Additionally, inhibition at both the local feature level and the object representation level biases the interpretation of the visual scene in agreement with principles from Gestalt psychology. Our model explains several sets of neurophysiological results (Zhou et al. Journal of Neuroscience, 20(17), 6594-6611 2000; Qiu et al. Nature Neuroscience, 10(11), 1492-1499 2007; Chen et al. Neuron, 82(3), 682-694 2014), and makes testable predictions about the influence of neuronal feedback and attentional selection on neural responses across different visual areas. Our model also provides a framework for understanding how object-based attention is able to select both objects and the features associated with them.

Protein-Protein Interaction Article Classification Using a Convolutional Recurrent Neural Network with Pre-trained Word Embeddings.

Science.gov (United States)

Matos, Sérgio; Antunes, Rui

2017-12-13

Curation of protein interactions from scientific articles is an important task, since interaction networks are essential for the understanding of biological processes associated with disease or pharmacological action for example. However, the increase in the number of publications that potentially contain relevant information turns this into a very challenging and expensive task. In this work we used a convolutional recurrent neural network for identifying relevant articles for extracting information regarding protein interactions. Using the BioCreative III Article Classification Task dataset, we achieved an area under the precision-recall curve of 0.715 and a Matthew's correlation coefficient of 0.600, which represents an improvement over previous works.

Identification of Jets Containing $b$-Hadrons with Recurrent Neural Networks at the ATLAS Experiment

CERN Document Server

The ATLAS collaboration

2017-01-01

A novel $b$-jet identification algorithm is constructed with a Recurrent Neural Network (RNN) at the ATLAS experiment at the CERN Large Hadron Collider. The RNN based $b$-tagging algorithm processes charged particle tracks associated to jets without reliance on secondary vertex finding, and can augment existing secondary-vertex based taggers. In contrast to traditional impact-parameter-based $b$-tagging algorithms which assume that tracks associated to jets are independent from each other, the RNN based $b$-tagging algorithm can exploit the spatial and kinematic correlations between tracks which are initiated from the same $b$-hadrons. This new approach also accommodates an extended set of input variables. This note presents the expected performance of the RNN based $b$-tagging algorithm in simulated $t \\bar t$ events at $\\sqrt{s}=13$ TeV.

H∞ state estimation for discrete-time memristive recurrent neural networks with stochastic time-delays

Science.gov (United States)

Liu, Hongjian; Wang, Zidong; Shen, Bo; Alsaadi, Fuad E.

2016-07-01

This paper deals with the robust H∞ state estimation problem for a class of memristive recurrent neural networks with stochastic time-delays. The stochastic time-delays under consideration are governed by a Bernoulli-distributed stochastic sequence. The purpose of the addressed problem is to design the robust state estimator such that the dynamics of the estimation error is exponentially stable in the mean square, and the prescribed ? performance constraint is met. By utilizing the difference inclusion theory and choosing a proper Lyapunov-Krasovskii functional, the existence condition of the desired estimator is derived. Based on it, the explicit expression of the estimator gain is given in terms of the solution to a linear matrix inequality. Finally, a numerical example is employed to demonstrate the effectiveness and applicability of the proposed estimation approach.

Robust stability analysis of Takagi—Sugeno uncertain stochastic fuzzy recurrent neural networks with mixed time-varying delays

International Nuclear Information System (INIS)

Ali, M. Syed

2011-01-01

In this paper, the global stability of Takagi—Sugeno (TS) uncertain stochastic fuzzy recurrent neural networks with discrete and distributed time-varying delays (TSUSFRNNs) is considered. A novel LMI-based stability criterion is obtained by using Lyapunov functional theory to guarantee the asymptotic stability of TSUSFRNNs. The proposed stability conditions are demonstrated through numerical examples. Furthermore, the supplementary requirement that the time derivative of time-varying delays must be smaller than one is removed. Comparison results are demonstrated to show that the proposed method is more able to guarantee the widest stability region than the other methods available in the existing literature. (general)

A novel treatment modality for recurrent aphthous stomatitis – Single application of doxycycline hyclate

Directory of Open Access Journals (Sweden)

R Thriveni

2018-01-01

Full Text Available Background and Objectives: Recurrent aphthous ulcers are common painful mucosal conditions affecting the oral cavity. Despite of so many treatment modalities, there is no specific and definitive treatment. Hence a study was carried out to evaluate the clinical effects Single Application of Doxycycline Hyclate 100 mg for Recurrent apthous Stomatitis (RAS. Materials and Methods: Forty study subjects were included in the study. Patients were randomly assigned into two groups. There were 20 patients in each group; Group A patients received Doxycycline Hyclate 100 mg in the first visit, Group B patients received placebo. The results were analyzed with unpaired 't' test. Results: The data indicated a significant reduction in pain in group A (i.e., faster reduction in pain compared with group B. Interpretation and Conclusion: A single application of doxycycline hyclate decreased pain and speeded recovery.

Single-Nucleotide Polymorphism-Microarray Ploidy Analysis of Paraffin-Embedded Products of Conception in Recurrent Pregnancy Loss Evaluations.

Science.gov (United States)

Maslow, Bat-Sheva L; Budinetz, Tara; Sueldo, Carolina; Anspach, Erica; Engmann, Lawrence; Benadiva, Claudio; Nulsen, John C

2015-07-01

To compare the analysis of chromosome number from paraffin-embedded products of conception using single-nucleotide polymorphism (SNP) microarray with the recommended screening for the evaluation of couples presenting with recurrent pregnancy loss who do not have previous fetal cytogenetic data. We performed a retrospective cohort study including all women who presented for a new evaluation of recurrent pregnancy loss over a 2-year period (January 1, 2012, to December 31, 2013). All participants had at least two documented first-trimester losses and both the recommended screening tests and SNP microarray performed on at least one paraffin-embedded products of conception sample. Single-nucleotide polymorphism microarray identifies all 24 chromosomes (22 autosomes, X, and Y). Forty-two women with a total of 178 losses were included in the study. Paraffin-embedded products of conception from 62 losses were sent for SNP microarray. Single-nucleotide polymorphism microarray successfully diagnosed fetal chromosome number in 71% (44/62) of samples, of which 43% (19/44) were euploid and 57% (25/44) were noneuploid. Seven of 42 (17%) participants had abnormalities on recurrent pregnancy loss screening. The per-person detection rate for a cause of pregnancy loss was significantly higher in the SNP microarray (0.50; 95% confidence interval [CI] 0.36-0.64) compared with recurrent pregnancy loss evaluation (0.17; 95% CI 0.08-0.31) (P=.002). Participants with one or more euploid loss identified on paraffin-embedded products of conception were significantly more likely to have an abnormality on recurrent pregnancy loss screening than those with only noneuploid results (P=.028). The significance remained when controlling for age, number of losses, number of samples, and total pregnancies. These results suggest that SNP microarray testing of paraffin-embedded products of conception is a valuable tool for the evaluation of recurrent pregnancy loss in patients without prior fetal

Efficacy of a diazepam suppository at preventing febrile seizure recurrence during a single febrile illness.

Science.gov (United States)

Hirabayashi, Yu; Okumura, Akihisa; Kondo, Taiki; Magota, Miyuki; Kawabe, Shinji; Kando, Naoyuki; Yamaguchi, Hideaki; Natsume, Jun; Negoro, Tamiko; Watanabe, Kazuyoshi

2009-06-01

To assess the efficacy of diazepam suppositories at preventing febrile seizure recurrence during a single febrile illness to determine how to treat children with a febrile seizure on presentation at the hospital. We studied 203 children with febrile seizures from December 2004 through March 2006. On admission between December 2004 and May 2005, a diazepam suppository was administered to the patients. Patients seen between June 2005 and March 2006 were not treated with antiepileptic drugs on admission. We saw a significant difference in the rate of recurrence of febrile seizures between children treated with diazepam and those who were not. Recurrences were observed in 2 (2.1%) of 95 children treated with diazepam and in 16 (14.8%) of 108 untreated children. For the 108 untreated patients, the median age was 22.8 months in those with recurrences and 30.6 months in those without, confirming that a younger age was related to a recurrence. A diazepam suppository after a febrile seizure will reduce the incidence of recurrent febrile seizures during the same febrile illness. However, a diazepam suppository after a febrile seizure should be used after carefully considering the benefits and potential adverse effects.

Empirical modeling of nuclear power plants using neural networks

International Nuclear Information System (INIS)

Parlos, A.G.; Atiya, A.; Chong, K.T.

1991-01-01

A summary of a procedure for nonlinear identification of process dynamics encountered in nuclear power plant components is presented in this paper using artificial neural systems. A hybrid feedforward/feedback neural network, namely, a recurrent multilayer perceptron, is used as the nonlinear structure for system identification. In the overall identification process, the feedforward portion of the network architecture provides its well-known interpolation property, while through recurrency and cross-talk, the local information feedback enables representation of time-dependent system nonlinearities. The standard backpropagation learning algorithm is modified and is used to train the proposed hybrid network in a supervised manner. The performance of recurrent multilayer perceptron networks in identifying process dynamics is investigated via the case study of a U-tube steam generator. The nonlinear response of a representative steam generator is predicted using a neural network and is compared to the response obtained from a sophisticated physical model during both high- and low-power operation. The transient responses compare well, though further research is warranted for training and testing of recurrent neural networks during more severe operational transients and accident scenarios

A loop-based neural architecture for structured behavior encoding and decoding.

Science.gov (United States)

Gisiger, Thomas; Boukadoum, Mounir

2018-02-01

We present a new type of artificial neural network that generalizes on anatomical and dynamical aspects of the mammal brain. Its main novelty lies in its topological structure which is built as an array of interacting elementary motifs shaped like loops. These loops come in various types and can implement functions such as gating, inhibitory or executive control, or encoding of task elements to name a few. Each loop features two sets of neurons and a control region, linked together by non-recurrent projections. The two neural sets do the bulk of the loop's computations while the control unit specifies the timing and the conditions under which the computations implemented by the loop are to be performed. By functionally linking many such loops together, a neural network is obtained that may perform complex cognitive computations. To demonstrate the potential offered by such a system, we present two neural network simulations. The first illustrates the structure and dynamics of a single loop implementing a simple gating mechanism. The second simulation shows how connecting four loops in series can produce neural activity patterns that are sufficient to pass a simplified delayed-response task. We also show that this network reproduces electrophysiological measurements gathered in various regions of the brain of monkeys performing similar tasks. We also demonstrate connections between this type of neural network and recurrent or long short-term memory network models, and suggest ways to generalize them for future artificial intelligence research. Copyright © 2017 Elsevier Ltd. All rights reserved.

Synchronization of chaotic systems and identification of nonlinear systems by using recurrent hierarchical type-2 fuzzy neural networks.

Science.gov (United States)

Mohammadzadeh, Ardashir; Ghaemi, Sehraneh

2015-09-01

This paper proposes a novel approach for training of proposed recurrent hierarchical interval type-2 fuzzy neural networks (RHT2FNN) based on the square-root cubature Kalman filters (SCKF). The SCKF algorithm is used to adjust the premise part of the type-2 FNN and the weights of defuzzification and the feedback weights. The recurrence property in the proposed network is the output feeding of each membership function to itself. The proposed RHT2FNN is employed in the sliding mode control scheme for the synchronization of chaotic systems. Unknown functions in the sliding mode control approach are estimated by RHT2FNN. Another application of the proposed RHT2FNN is the identification of dynamic nonlinear systems. The effectiveness of the proposed network and its learning algorithm is verified by several simulation examples. Furthermore, the universal approximation of RHT2FNNs is also shown. Copyright © 2015 ISA. Published by Elsevier Ltd. All rights reserved.

Recurrent neural network based hybrid model for reconstructing gene regulatory network.

Science.gov (United States)

Raza, Khalid; Alam, Mansaf

2016-10-01

One of the exciting problems in systems biology research is to decipher how genome controls the development of complex biological system. The gene regulatory networks (GRNs) help in the identification of regulatory interactions between genes and offer fruitful information related to functional role of individual gene in a cellular system. Discovering GRNs lead to a wide range of applications, including identification of disease related pathways providing novel tentative drug targets, helps to predict disease response, and also assists in diagnosing various diseases including cancer. Reconstruction of GRNs from available biological data is still an open problem. This paper proposes a recurrent neural network (RNN) based model of GRN, hybridized with generalized extended Kalman filter for weight update in backpropagation through time training algorithm. The RNN is a complex neural network that gives a better settlement between biological closeness and mathematical flexibility to model GRN; and is also able to capture complex, non-linear and dynamic relationships among variables. Gene expression data are inherently noisy and Kalman filter performs well for estimation problem even in noisy data. Hence, we applied non-linear version of Kalman filter, known as generalized extended Kalman filter, for weight update during RNN training. The developed model has been tested on four benchmark networks such as DNA SOS repair network, IRMA network, and two synthetic networks from DREAM Challenge. We performed a comparison of our results with other state-of-the-art techniques which shows superiority of our proposed model. Further, 5% Gaussian noise has been induced in the dataset and result of the proposed model shows negligible effect of noise on results, demonstrating the noise tolerance capability of the model. Copyright © 2016 Elsevier Ltd. All rights reserved.

Single versus recurrent depression history: differentiating risk factors among current US smokers.

Science.gov (United States)

Strong, David R; Cameron, Amy; Feuer, Shelley; Cohn, Amy; Abrantes, Ana M; Brown, Richard A

2010-06-01

The strong relationship between persistent tobacco use and Major Depressive Disorder (MDD) has motivated clinical trials of specialized treatments targeting smokers with a history of MDD. Meta-analyses suggest positive responses to specialized treatments have been observed consistently among smokers with history of recurrent rather than a single episode of MDD. Approximately 15% of current US smokers have a history of recurrent MDD. Little is known about the risk factors that contribute to persistent smoking and differentiate these at-risk smokers, US. The National Comorbidity Survey - Replication (NCS-R) included a survey of 1560 smokers participants aged 18 and older in the United States. Lifetime history of MDD was categorized according to chronicity: no history (No MDD), single episode (MDD-S) and recurrent depression (MDD-R). The relationship between the chronicity of MDD, smoking characteristics, cessation history, nicotine dependence, comorbidity with psychiatric disorders, and current functional impairments were examined. MDD-R smokers reported fewer lifetime cessation efforts, smoked more cigarettes, had higher levels of nicotine dependence, had higher rates of comorbid psychiatric disorders and greater functional impairment than smokers with No MDD. MDD-S smokers were not consistently distinguished from No MDD smokers on cessation attempts, level of daily smoking, nicotine dependence or functional impairment indices. The study highlights the importance of chronicity when characterizing depression-related risk of persistent smoking behavior. Although, clinical trials suggest MDD-R smokers specifically benefit from specialized behavioral treatments, these services are not widely available and more efforts are needed to engage MDD-R smokers in efficacious treatments. Copyright (c) 2010 Elsevier Ireland Ltd. All rights reserved.

Video Super-Resolution via Bidirectional Recurrent Convolutional Networks.

Science.gov (United States)

Huang, Yan; Wang, Wei; Wang, Liang

2018-04-01

Super resolving a low-resolution video, namely video super-resolution (SR), is usually handled by either single-image SR or multi-frame SR. Single-Image SR deals with each video frame independently, and ignores intrinsic temporal dependency of video frames which actually plays a very important role in video SR. Multi-Frame SR generally extracts motion information, e.g., optical flow, to model the temporal dependency, but often shows high computational cost. Considering that recurrent neural networks (RNNs) can model long-term temporal dependency of video sequences well, we propose a fully convolutional RNN named bidirectional recurrent convolutional network for efficient multi-frame SR. Different from vanilla RNNs, 1) the commonly-used full feedforward and recurrent connections are replaced with weight-sharing convolutional connections. So they can greatly reduce the large number of network parameters and well model the temporal dependency in a finer level, i.e., patch-based rather than frame-based, and 2) connections from input layers at previous timesteps to the current hidden layer are added by 3D feedforward convolutions, which aim to capture discriminate spatio-temporal patterns for short-term fast-varying motions in local adjacent frames. Due to the cheap convolutional operations, our model has a low computational complexity and runs orders of magnitude faster than other multi-frame SR methods. With the powerful temporal dependency modeling, our model can super resolve videos with complex motions and achieve well performance.

Neural Circuits via Which Single Prolonged Stress Exposure Leads to Fear Extinction Retention Deficits

Science.gov (United States)

Knox, Dayan; Stanfield, Briana R.; Staib, Jennifer M.; David, Nina P.; Keller, Samantha M.; DePietro, Thomas

2016-01-01

Single prolonged stress (SPS) has been used to examine mechanisms via which stress exposure leads to post-traumatic stress disorder symptoms. SPS induces fear extinction retention deficits, but neural circuits critical for mediating these deficits are unknown. To address this gap, we examined the effect of SPS on neural activity in brain regions…

Fundamentals of computational intelligence neural networks, fuzzy systems, and evolutionary computation

CERN Document Server

Keller, James M; Fogel, David B

2016-01-01

This book covers the three fundamental topics that form the basis of computational intelligence: neural networks, fuzzy systems, and evolutionary computation. The text focuses on inspiration, design, theory, and practical aspects of implementing procedures to solve real-world problems. While other books in the three fields that comprise computational intelligence are written by specialists in one discipline, this book is co-written by current former Editor-in-Chief of IEEE Transactions on Neural Networks and Learning Systems, a former Editor-in-Chief of IEEE Transactions on Fuzzy Systems, and the founding Editor-in-Chief of IEEE Transactions on Evolutionary Computation. The coverage across the three topics is both uniform and consistent in style and notation. Discusses single-layer and multilayer neural networks, radial-basi function networks, and recurrent neural networks Covers fuzzy set theory, fuzzy relations, fuzzy logic interference, fuzzy clustering and classification, fuzzy measures and fuzz...

Using LSTM recurrent neural networks for monitoring the LHC superconducting magnets

Science.gov (United States)

Wielgosz, Maciej; Skoczeń, Andrzej; Mertik, Matej

2017-09-01

The superconducting LHC magnets are coupled with an electronic monitoring system which records and analyzes voltage time series reflecting their performance. A currently used system is based on a range of preprogrammed triggers which launches protection procedures when a misbehavior of the magnets is detected. All the procedures used in the protection equipment were designed and implemented according to known working scenarios of the system and are updated and monitored by human operators. This paper proposes a novel approach to monitoring and fault protection of the Large Hadron Collider (LHC) superconducting magnets which employs state-of-the-art Deep Learning algorithms. Consequently, the authors of the paper decided to examine the performance of LSTM recurrent neural networks for modeling of voltage time series of the magnets. In order to address this challenging task different network architectures and hyper-parameters were used to achieve the best possible performance of the solution. The regression results were measured in terms of RMSE for different number of future steps and history length taken into account for the prediction. The best result of RMSE = 0 . 00104 was obtained for a network of 128 LSTM cells within the internal layer and 16 steps history buffer.

A recurrent neural network for classification of unevenly sampled variable stars

Science.gov (United States)

Naul, Brett; Bloom, Joshua S.; Pérez, Fernando; van der Walt, Stéfan

2018-02-01

Astronomical surveys of celestial sources produce streams of noisy time series measuring flux versus time (`light curves'). Unlike in many other physical domains, however, large (and source-specific) temporal gaps in data arise naturally due to intranight cadence choices as well as diurnal and seasonal constraints1-5. With nightly observations of millions of variable stars and transients from upcoming surveys4,6, efficient and accurate discovery and classification techniques on noisy, irregularly sampled data must be employed with minimal human-in-the-loop involvement. Machine learning for inference tasks on such data traditionally requires the laborious hand-coding of domain-specific numerical summaries of raw data (`features')7. Here, we present a novel unsupervised autoencoding recurrent neural network8 that makes explicit use of sampling times and known heteroskedastic noise properties. When trained on optical variable star catalogues, this network produces supervised classification models that rival other best-in-class approaches. We find that autoencoded features learned in one time-domain survey perform nearly as well when applied to another survey. These networks can continue to learn from new unlabelled observations and may be used in other unsupervised tasks, such as forecasting and anomaly detection.

Physiological modules for generating discrete and rhythmic movements: action identification by a dynamic recurrent neural network.

Science.gov (United States)

Bengoetxea, Ana; Leurs, Françoise; Hoellinger, Thomas; Cebolla, Ana M; Dan, Bernard; McIntyre, Joseph; Cheron, Guy

2014-01-01

In this study we employed a dynamic recurrent neural network (DRNN) in a novel fashion to reveal characteristics of control modules underlying the generation of muscle activations when drawing figures with the outstretched arm. We asked healthy human subjects to perform four different figure-eight movements in each of two workspaces (frontal plane and sagittal plane). We then trained a DRNN to predict the movement of the wrist from information in the EMG signals from seven different muscles. We trained different instances of the same network on a single movement direction, on all four movement directions in a single movement plane, or on all eight possible movement patterns and looked at the ability of the DRNN to generalize and predict movements for trials that were not included in the training set. Within a single movement plane, a DRNN trained on one movement direction was not able to predict movements of the hand for trials in the other three directions, but a DRNN trained simultaneously on all four movement directions could generalize across movement directions within the same plane. Similarly, the DRNN was able to reproduce the kinematics of the hand for both movement planes, but only if it was trained on examples performed in each one. As we will discuss, these results indicate that there are important dynamical constraints on the mapping of EMG to hand movement that depend on both the time sequence of the movement and on the anatomical constraints of the musculoskeletal system. In a second step, we injected EMG signals constructed from different synergies derived by the PCA in order to identify the mechanical significance of each of these components. From these results, one can surmise that discrete-rhythmic movements may be constructed from three different fundamental modules, one regulating the co-activation of all muscles over the time span of the movement and two others elliciting patterns of reciprocal activation operating in orthogonal directions.

Exploring multiple feature combination strategies with a recurrent neural network architecture for off-line handwriting recognition

Science.gov (United States)

Mioulet, L.; Bideault, G.; Chatelain, C.; Paquet, T.; Brunessaux, S.

2015-01-01

The BLSTM-CTC is a novel recurrent neural network architecture that has outperformed previous state of the art algorithms in tasks such as speech recognition or handwriting recognition. It has the ability to process long term dependencies in temporal signals in order to label unsegmented data. This paper describes different ways of combining features using a BLSTM-CTC architecture. Not only do we explore the low level combination (feature space combination) but we also explore high level combination (decoding combination) and mid-level (internal system representation combination). The results are compared on the RIMES word database. Our results show that the low level combination works best, thanks to the powerful data modeling of the LSTM neurons.

Distributed representations of action sequences in anterior cingulate cortex: A recurrent neural network approach.

Science.gov (United States)

Shahnazian, Danesh; Holroyd, Clay B

2018-02-01

Anterior cingulate cortex (ACC) has been the subject of intense debate over the past 2 decades, but its specific computational function remains controversial. Here we present a simple computational model of ACC that incorporates distributed representations across a network of interconnected processing units. Based on the proposal that ACC is concerned with the execution of extended, goal-directed action sequences, we trained a recurrent neural network to predict each successive step of several sequences associated with multiple tasks. In keeping with neurophysiological observations from nonhuman animals, the network yields distributed patterns of activity across ACC neurons that track the progression of each sequence, and in keeping with human neuroimaging data, the network produces discrepancy signals when any step of the sequence deviates from the predicted step. These simulations illustrate a novel approach for investigating ACC function.

Stability switches, oscillatory multistability, and spatio-temporal patterns of nonlinear oscillations in recurrently delay coupled neural networks.

Science.gov (United States)

Song, Yongli; Makarov, Valeri A; Velarde, Manuel G

2009-08-01

A model of time-delay recurrently coupled spatially segregated neural assemblies is here proposed. We show that it operates like some of the hierarchical architectures of the brain. Each assembly is a neural network with no delay in the local couplings between the units. The delay appears in the long range feedforward and feedback inter-assemblies communications. Bifurcation analysis of a simple four-units system in the autonomous case shows the richness of the dynamical behaviors in a biophysically plausible parameter region. We find oscillatory multistability, hysteresis, and stability switches of the rest state provoked by the time delay. Then we investigate the spatio-temporal patterns of bifurcating periodic solutions by using the symmetric local Hopf bifurcation theory of delay differential equations and derive the equation describing the flow on the center manifold that enables us determining the direction of Hopf bifurcations and stability of the bifurcating periodic orbits. We also discuss computational properties of the system due to the delay when an external drive of the network mimicks external sensory input.

Study of GABAergic extra-synaptic tonic inhibition in single neurons and neural populations by traversing neural scales: application to propofol-induced anaesthesia.

Science.gov (United States)

Hutt, Axel; Buhry, Laure

2014-12-01

Anaesthetic agents are known to affect extra-synaptic GABAergic receptors, which induce tonic inhibitory currents. Since these receptors are very sensitive to small concentrations of agents, they are supposed to play an important role in the underlying neural mechanism of general anaesthesia. Moreover anaesthetic agents modulate the encephalographic activity (EEG) of subjects and hence show an effect on neural populations. To understand better the tonic inhibition effect in single neurons on neural populations and hence how it affects the EEG, the work considers single neurons and neural populations in a steady-state and studies numerically and analytically the modulation of their firing rate and nonlinear gain with respect to different levels of tonic inhibition. We consider populations of both type-I (Leaky Integrate-and-Fire model) and type-II (Morris-Lecar model) neurons. To bridge the single neuron description to the population description analytically, a recently proposed statistical approach is employed which allows to derive new analytical expressions for the population firing rate for type-I neurons. In addition, the work shows the derivation of a novel transfer function for type-I neurons as considered in neural mass models and studies briefly the interaction of synaptic and extra-synaptic inhibition. We reveal a strong subtractive and divisive effect of tonic inhibition in type-I neurons, i.e. a shift of the firing rate to higher excitation levels accompanied by a change of the nonlinear gain. Tonic inhibition shortens the excitation window of type-II neurons and their populations while maintaining the nonlinear gain. The gained results are interpreted in the context of recent experimental findings under propofol-induced anaesthesia.

On the approximation by single hidden layer feedforward neural networks with fixed weights

OpenAIRE

Guliyev, Namig J.; Ismailov, Vugar E.

2017-01-01

International audience; Feedforward neural networks have wide applicability in various disciplines of science due to their universal approximation property. Some authors have shown that single hidden layer feedforward neural networks (SLFNs) with fixed weights still possess the universal approximation property provided that approximated functions are univariate. But this phenomenon does not lay any restrictions on the number of neurons in the hidden layer. The more this number, the more the p...

Artificial neural network and falls in community-dwellers: a new approach to identify the risk of recurrent falling?

Science.gov (United States)

Kabeshova, Anastasiia; Launay, Cyrille P; Gromov, Vasilii A; Annweiler, Cédric; Fantino, Bruno; Beauchet, Olivier

2015-04-01

Identification of the risk of recurrent falls is complex in older adults. The aim of this study was to examine the efficiency of 3 artificial neural networks (ANNs: multilayer perceptron [MLP], modified MLP, and neuroevolution of augmenting topologies [NEAT]) for the classification of recurrent fallers and nonrecurrent fallers using a set of clinical characteristics corresponding to risk factors of falls measured among community-dwelling older adults. Based on a cross-sectional design, 3289 community-dwelling volunteers aged 65 and older were recruited. Age, gender, body mass index (BMI), number of drugs daily taken, use of psychoactive drugs, diphosphonate, calcium, vitamin D supplements and walking aid, fear of falling, distance vision score, Timed Up and Go (TUG) score, lower-limb proprioception, handgrip strength, depressive symptoms, cognitive disorders, and history of falls were recorded. Participants were separated into 2 groups based on the number of falls that occurred over the past year: 0 or 1 fall and 2 or more falls. In addition, total population was separated into training and testing subgroups for ANN analysis. Among 3289 participants, 18.9% (n = 622) were recurrent fallers. NEAT, using 15 clinical characteristics (ie, use of walking aid, fear of falling, use of calcium, depression, use of vitamin D supplements, female, cognitive disorders, BMI 4, vision score 9 seconds, handgrip strength score ≤29 (N), and age ≥75 years), showed the best efficiency for identification of recurrent fallers, sensitivity (80.42%), specificity (92.54%), positive predictive value (84.38), negative predictive value (90.34), accuracy (88.39), and Cohen κ (0.74), compared with MLP and modified MLP. NEAT, using a set of 15 clinical characteristics, was an efficient ANN for the identification of recurrent fallers in older community-dwellers. Copyright © 2015 AMDA – The Society for Post-Acute and Long-Term Care Medicine. Published by Elsevier Inc. All rights reserved.

Energy Complexity of Recurrent Neural Networks

Czech Academy of Sciences Publication Activity Database

Šíma, Jiří

2014-01-01

Roč. 26, č. 5 (2014), s. 953-973 ISSN 0899-7667 R&D Projects: GA ČR GAP202/10/1333 Institutional support: RVO:67985807 Keywords : neural network * finite automaton * energy complexity * optimal size Subject RIV: IN - Informatics, Computer Science Impact factor: 2.207, year: 2014

A novel flow diverter(Tubridge) for the treatment of recurrent aneurysms: A single-center experience

International Nuclear Information System (INIS)

Zhang, Yong Xin; Huang, Qing Hai; Fang, Yibin; Yang, Peng Fei; Xu, Yi; Hong Bo; Liu, Jian Min

2017-01-01

The Tubridge flow diverter (FD) is a novel device aimed at reconstructing the parent artery and occluding complex aneurysms. Retreatment of recurrent aneurysms using the FD is challenging. We report our initial experience in the repair of aneurysm recurrence with the FD. A database was reviewed prospectively, and 8 patients with 8 recurrent aneurysms (mean size, 16.7 mm) were identified. Four aneurysms had previously ruptured. The previous aneurysm treatment consisted of coiling in 1 aneurysm and single-stent-assisted coiling in 7 aneurysms. The procedural complications and clinical and angiographic outcomes were analyzed. Six aneurysms were treated by using a single Tubridge FD alone, while the remaining 2 were treated with FD + coiling. The immediate results of the 8 aneurysms were that they all showed incomplete occlusion. Neither major ischemic nor hemorrhagic complications occurred; however, 1 patient experienced a vasospasm. Follow-up angiographies were available for 7 aneurysms; the mean follow-up was 16.9 months (7–36 months). Five aneurysms were completely occluded, whereas 2 had a residual neck. Severe asymptomatic stenosis of 1 parent artery of a vertebral artery dissecting aneurysm was found. All visible branches covered by the FD were patent. All patients were clinically assessed as having attained a favorable outcome (modified Rankin Scale score ≤ 2) at discharge and follow-up. In selected patients, the Tubridge FD can provide a safe and efficient option for the retreatment of recurrent aneurysms. Nevertheless, attention should be paid to several technical points

A novel flow diverter(Tubridge) for the treatment of recurrent aneurysms: A single-center experience

Energy Technology Data Exchange (ETDEWEB)

Zhang, Yong Xin; Huang, Qing Hai; Fang, Yibin; Yang, Peng Fei; Xu, Yi; Hong Bo; Liu, Jian Min [Dept. of Neurosurgery, Changhai Hospital, Second Military Medical University, Shanghai (China)

2017-09-15

The Tubridge flow diverter (FD) is a novel device aimed at reconstructing the parent artery and occluding complex aneurysms. Retreatment of recurrent aneurysms using the FD is challenging. We report our initial experience in the repair of aneurysm recurrence with the FD. A database was reviewed prospectively, and 8 patients with 8 recurrent aneurysms (mean size, 16.7 mm) were identified. Four aneurysms had previously ruptured. The previous aneurysm treatment consisted of coiling in 1 aneurysm and single-stent-assisted coiling in 7 aneurysms. The procedural complications and clinical and angiographic outcomes were analyzed. Six aneurysms were treated by using a single Tubridge FD alone, while the remaining 2 were treated with FD + coiling. The immediate results of the 8 aneurysms were that they all showed incomplete occlusion. Neither major ischemic nor hemorrhagic complications occurred; however, 1 patient experienced a vasospasm. Follow-up angiographies were available for 7 aneurysms; the mean follow-up was 16.9 months (7–36 months). Five aneurysms were completely occluded, whereas 2 had a residual neck. Severe asymptomatic stenosis of 1 parent artery of a vertebral artery dissecting aneurysm was found. All visible branches covered by the FD were patent. All patients were clinically assessed as having attained a favorable outcome (modified Rankin Scale score ≤ 2) at discharge and follow-up. In selected patients, the Tubridge FD can provide a safe and efficient option for the retreatment of recurrent aneurysms. Nevertheless, attention should be paid to several technical points.

Biological oscillations for learning walking coordination: dynamic recurrent neural network functionally models physiological central pattern generator.

Science.gov (United States)

Hoellinger, Thomas; Petieau, Mathieu; Duvinage, Matthieu; Castermans, Thierry; Seetharaman, Karthik; Cebolla, Ana-Maria; Bengoetxea, Ana; Ivanenko, Yuri; Dan, Bernard; Cheron, Guy

2013-01-01

The existence of dedicated neuronal modules such as those organized in the cerebral cortex, thalamus, basal ganglia, cerebellum, or spinal cord raises the question of how these functional modules are coordinated for appropriate motor behavior. Study of human locomotion offers an interesting field for addressing this central question. The coordination of the elevation of the 3 leg segments under a planar covariation rule (Borghese et al., 1996) was recently modeled (Barliya et al., 2009) by phase-adjusted simple oscillators shedding new light on the understanding of the central pattern generator (CPG) processing relevant oscillation signals. We describe the use of a dynamic recurrent neural network (DRNN) mimicking the natural oscillatory behavior of human locomotion for reproducing the planar covariation rule in both legs at different walking speeds. Neural network learning was based on sinusoid signals integrating frequency and amplitude features of the first three harmonics of the sagittal elevation angles of the thigh, shank, and foot of each lower limb. We verified the biological plausibility of the neural networks. Best results were obtained with oscillations extracted from the first three harmonics in comparison to oscillations outside the harmonic frequency peaks. Physiological replication steadily increased with the number of neuronal units from 1 to 80, where similarity index reached 0.99. Analysis of synaptic weighting showed that the proportion of inhibitory connections consistently increased with the number of neuronal units in the DRNN. This emerging property in the artificial neural networks resonates with recent advances in neurophysiology of inhibitory neurons that are involved in central nervous system oscillatory activities. The main message of this study is that this type of DRNN may offer a useful model of physiological central pattern generator for gaining insights in basic research and developing clinical applications.

Learning and retrieval behavior in recurrent neural networks with pre-synaptic dependent homeostatic plasticity

Science.gov (United States)

Mizusaki, Beatriz E. P.; Agnes, Everton J.; Erichsen, Rubem; Brunnet, Leonardo G.

2017-08-01

The plastic character of brain synapses is considered to be one of the foundations for the formation of memories. There are numerous kinds of such phenomenon currently described in the literature, but their role in the development of information pathways in neural networks with recurrent architectures is still not completely clear. In this paper we study the role of an activity-based process, called pre-synaptic dependent homeostatic scaling, in the organization of networks that yield precise-timed spiking patterns. It encodes spatio-temporal information in the synaptic weights as it associates a learned input with a specific response. We introduce a correlation measure to evaluate the precision of the spiking patterns and explore the effects of different inhibitory interactions and learning parameters. We find that large learning periods are important in order to improve the network learning capacity and discuss this ability in the presence of distinct inhibitory currents.

The attractor recurrent neural network based on fuzzy functions: An effective model for the classification of lung abnormalities.

Science.gov (United States)

Khodabakhshi, Mohammad Bagher; Moradi, Mohammad Hassan

2017-05-01

The respiratory system dynamic is of high significance when it comes to the detection of lung abnormalities, which highlights the importance of presenting a reliable model for it. In this paper, we introduce a novel dynamic modelling method for the characterization of the lung sounds (LS), based on the attractor recurrent neural network (ARNN). The ARNN structure allows the development of an effective LS model. Additionally, it has the capability to reproduce the distinctive features of the lung sounds using its formed attractors. Furthermore, a novel ARNN topology based on fuzzy functions (FFs-ARNN) is developed. Given the utility of the recurrent quantification analysis (RQA) as a tool to assess the nature of complex systems, it was used to evaluate the performance of both the ARNN and the FFs-ARNN models. The experimental results demonstrate the effectiveness of the proposed approaches for multichannel LS analysis. In particular, a classification accuracy of 91% was achieved using FFs-ARNN with sequences of RQA features. Copyright © 2017 Elsevier Ltd. All rights reserved.

Stochastic resonance in an ensemble of single-electron neuromorphic devices and its application to competitive neural networks

International Nuclear Information System (INIS)

Oya, Takahide; Asai, Tetsuya; Amemiya, Yoshihito

2007-01-01

Neuromorphic computing based on single-electron circuit technology is gaining prominence because of its massively increased computational efficiency and the increasing relevance of computer technology and nanotechnology [Likharev K, Mayr A, Muckra I, Tuerel O. CrossNets: High-performance neuromorphic architectures for CMOL circuits. Molec Electron III: Ann NY Acad Sci 1006;2003:146-63; Oya T, Schmid A, Asai T, Leblebici Y, Amemiya Y. On the fault tolerance of a clustered single-electron neural network for differential enhancement. IEICE Electron Expr 2;2005:76-80]. The maximum impact of these technologies will be strongly felt when single-electron circuits based on fault- and noise-tolerant neural structures can operate at room temperature. In this paper, inspired by stochastic resonance (SR) in an ensemble of spiking neurons [Collins JJ, Chow CC, Imhoff TT. Stochastic resonance without tuning. Nature 1995;376:236-8], we propose our design of a basic single-electron neural component and report how we examined its statistical results on a network

Interactive natural language acquisition in a multi-modal recurrent neural architecture

Science.gov (United States)

Heinrich, Stefan; Wermter, Stefan

2018-01-01

For the complex human brain that enables us to communicate in natural language, we gathered good understandings of principles underlying language acquisition and processing, knowledge about sociocultural conditions, and insights into activity patterns in the brain. However, we were not yet able to understand the behavioural and mechanistic characteristics for natural language and how mechanisms in the brain allow to acquire and process language. In bridging the insights from behavioural psychology and neuroscience, the goal of this paper is to contribute a computational understanding of appropriate characteristics that favour language acquisition. Accordingly, we provide concepts and refinements in cognitive modelling regarding principles and mechanisms in the brain and propose a neurocognitively plausible model for embodied language acquisition from real-world interaction of a humanoid robot with its environment. In particular, the architecture consists of a continuous time recurrent neural network, where parts have different leakage characteristics and thus operate on multiple timescales for every modality and the association of the higher level nodes of all modalities into cell assemblies. The model is capable of learning language production grounded in both, temporal dynamic somatosensation and vision, and features hierarchical concept abstraction, concept decomposition, multi-modal integration, and self-organisation of latent representations.

Single Layer Recurrent Neural Network for detection of swarm-like earthquakes in W-Bohemia/Vogtland - the method

Czech Academy of Sciences Publication Activity Database

Doubravová, Jana; Wiszniowski, J.; Horálek, Josef

2016-01-01

Roč. 93, August (2016), s. 138-149 ISSN 0098-3004 R&D Projects: GA ČR GAP210/12/2336; GA MŠk LM2010008 Institutional support: RVO:67985530 Keywords : event detection * artificial neural network * West Bohemia/Vogtland Subject RIV: DC - Siesmology, Volcanology, Earth Structure Impact factor: 2.533, year: 2016

Nonlinear dynamic systems identification using recurrent interval type-2 TSK fuzzy neural network - A novel structure.

Science.gov (United States)

El-Nagar, Ahmad M

2018-01-01

In this study, a novel structure of a recurrent interval type-2 Takagi-Sugeno-Kang (TSK) fuzzy neural network (FNN) is introduced for nonlinear dynamic and time-varying systems identification. It combines the type-2 fuzzy sets (T2FSs) and a recurrent FNN to avoid the data uncertainties. The fuzzy firing strengths in the proposed structure are returned to the network input as internal variables. The interval type-2 fuzzy sets (IT2FSs) is used to describe the antecedent part for each rule while the consequent part is a TSK-type, which is a linear function of the internal variables and the external inputs with interval weights. All the type-2 fuzzy rules for the proposed RIT2TSKFNN are learned on-line based on structure and parameter learning, which are performed using the type-2 fuzzy clustering. The antecedent and consequent parameters of the proposed RIT2TSKFNN are updated based on the Lyapunov function to achieve network stability. The obtained results indicate that our proposed network has a small root mean square error (RMSE) and a small integral of square error (ISE) with a small number of rules and a small computation time compared with other type-2 FNNs. Copyright © 2017 ISA. Published by Elsevier Ltd. All rights reserved.

Modeling Belt-Servomechanism by Chebyshev Functional Recurrent Neuro-Fuzzy Network

Science.gov (United States)

Huang, Yuan-Ruey; Kang, Yuan; Chu, Ming-Hui; Chang, Yeon-Pun

A novel Chebyshev functional recurrent neuro-fuzzy (CFRNF) network is developed from a combination of the Takagi-Sugeno-Kang (TSK) fuzzy model and the Chebyshev recurrent neural network (CRNN). The CFRNF network can emulate the nonlinear dynamics of a servomechanism system. The system nonlinearity is addressed by enhancing the input dimensions of the consequent parts in the fuzzy rules due to functional expansion of a Chebyshev polynomial. The back propagation algorithm is used to adjust the parameters of the antecedent membership functions as well as those of consequent functions. To verify the performance of the proposed CFRNF, the experiment of the belt servomechanism is presented in this paper. Both of identification methods of adaptive neural fuzzy inference system (ANFIS) and recurrent neural network (RNN) are also studied for modeling of the belt servomechanism. The analysis and comparison results indicate that CFRNF makes identification of complex nonlinear dynamic systems easier. It is verified that the accuracy and convergence of the CFRNF are superior to those of ANFIS and RNN by the identification results of a belt servomechanism.

Application of a Self-recurrent Wavelet Neural Network in the Modeling and Control of an AC Servo System

Directory of Open Access Journals (Sweden)

Run Min HOU

2014-05-01

Full Text Available To control the nonlinearity, widespread variations in loads and time varying characteristic of the high power ac servo system, the modeling and control techniques are studied here. A self-recurrent wavelet neural network (SRWNN modeling scheme is proposed, which successfully addresses the issue of the traditional wavelet neural network easily falling into local optimum, and significantly improves the network approximation capability and convergence rate. The control scheme of a SRWNN based on fuzzy compensation is expected. Gradient information is provided in real time for the controller by using a SRWNN identifier, so as to ensure that the learning and adjusting function of the controller of the SRWNN operate well, and fuzzy compensation control is applied to improve rapidity and accuracy of the entire system. Then the Lyapunov function is utilized to judge the stability of the system. The experimental analysis and comparisons with other modeling and control methods, it is clearly shown that the validities of the proposed modeling scheme and control scheme are effective.

Using Elman recurrent neural networks with conjugate gradient algorithm in determining the anesthetic the amount of anesthetic medicine to be applied.

Science.gov (United States)

Güntürkün, Rüştü

2010-08-01

In this study, Elman recurrent neural networks have been defined by using conjugate gradient algorithm in order to determine the depth of anesthesia in the continuation stage of the anesthesia and to estimate the amount of medicine to be applied at that moment. The feed forward neural networks are also used for comparison. The conjugate gradient algorithm is compared with back propagation (BP) for training of the neural Networks. The applied artificial neural network is composed of three layers, namely the input layer, the hidden layer and the output layer. The nonlinear activation function sigmoid (sigmoid function) has been used in the hidden layer and the output layer. EEG data has been recorded with Nihon Kohden 9200 brand 22-channel EEG device. The international 8-channel bipolar 10-20 montage system (8 TB-b system) has been used in assembling the recording electrodes. EEG data have been recorded by being sampled once in every 2 milliseconds. The artificial neural network has been designed so as to have 60 neurons in the input layer, 30 neurons in the hidden layer and 1 neuron in the output layer. The values of the power spectral density (PSD) of 10-second EEG segments which correspond to the 1-50 Hz frequency range; the ratio of the total power of PSD values of the EEG segment at that moment in the same range to the total of PSD values of EEG segment taken prior to the anesthesia.

Construction of Gene Regulatory Networks Using Recurrent Neural Networks and Swarm Intelligence.

Science.gov (United States)

Khan, Abhinandan; Mandal, Sudip; Pal, Rajat Kumar; Saha, Goutam

2016-01-01

We have proposed a methodology for the reverse engineering of biologically plausible gene regulatory networks from temporal genetic expression data. We have used established information and the fundamental mathematical theory for this purpose. We have employed the Recurrent Neural Network formalism to extract the underlying dynamics present in the time series expression data accurately. We have introduced a new hybrid swarm intelligence framework for the accurate training of the model parameters. The proposed methodology has been first applied to a small artificial network, and the results obtained suggest that it can produce the best results available in the contemporary literature, to the best of our knowledge. Subsequently, we have implemented our proposed framework on experimental (in vivo) datasets. Finally, we have investigated two medium sized genetic networks (in silico) extracted from GeneNetWeaver, to understand how the proposed algorithm scales up with network size. Additionally, we have implemented our proposed algorithm with half the number of time points. The results indicate that a reduction of 50% in the number of time points does not have an effect on the accuracy of the proposed methodology significantly, with a maximum of just over 15% deterioration in the worst case.

Different cognitive profiles for single compared with recurrent fallers without dementia.

Science.gov (United States)

Anstey, Kaarin J; Wood, Joanne; Kerr, Graham; Caldwell, Haley; Lord, Stephen R

2009-07-01

Relationships between self-reported retrospective falls and cognitive measures (executive function, reaction time [RT], processing speed, working memory, visual attention) were examined in a population based sample of older adults (n = 658). Two of the choice RT tests involved inhibiting responses to either targets of a specific color or location with hand and foot responses. Potentially confounding demographic variables, medical conditions, and postural sway were controlled for in logistic regression models, excluding participants with possible cognitive impairment. A factor analysis of cognitive measures extracted factors measuring RT, accuracy and inhibition, and visual search. Single fallers did not differ from nonfallers in terms of health, sway or cognitive function, except that they performed worse on accuracy and inhibition. In contrast, recurrent fallers performed worse than nonfallers on all measures. Results suggest that occasional falls in late life may be associated with subtle age-related changes in the prefrontal cortex leading to failures of executive control, whereas recurrent falling may result from more advanced brain ageing that is associated with generalized cognitive decline. 2009 American Psychological Association

A Recurrent Neural Network Approach to Rear Vehicle Detection Which Considered State Dependency

Directory of Open Access Journals (Sweden)

Kayichirou Inagaki

2003-08-01

Full Text Available Experimental vision-based detection often fails in cases when the acquired image quality is reduced by changing optical environments. In addition, the shape of vehicles in images that are taken from vision sensors change due to approaches by vehicle. Vehicle detection methods are required to perform successfully under these conditions. However, the conventional methods do not consider especially in rapidly varying by brightness conditions. We suggest a new detection method that compensates for those conditions in monocular vision-based vehicle detection. The suggested method employs a Recurrent Neural Network (RNN, which has been applied for spatiotemporal processing. The RNN is able to respond to consecutive scenes involving the target vehicle and can track the movements of the target by the effect of the past network states. The suggested method has a particularly beneficial effect in environments with sudden, extreme variations such as bright sunlight and shield. Finally, we demonstrate effectiveness by state-dependent of the RNN-based method by comparing its detection results with those of a Multi Layered Perceptron (MLP.

An interpretable LSTM neural network for autoregressive exogenous model

OpenAIRE

Guo, Tian; Lin, Tao; Lu, Yao

2018-01-01

In this paper, we propose an interpretable LSTM recurrent neural network, i.e., multi-variable LSTM for time series with exogenous variables. Currently, widely used attention mechanism in recurrent neural networks mostly focuses on the temporal aspect of data and falls short of characterizing variable importance. To this end, our multi-variable LSTM equipped with tensorized hidden states is developed to learn variable specific representations, which give rise to both temporal and variable lev...

Auto-Associative Recurrent Neural Networks and Long Term Dependencies in Novelty Detection for Audio Surveillance Applications

Science.gov (United States)

Rossi, A.; Montefoschi, F.; Rizzo, A.; Diligenti, M.; Festucci, C.

2017-10-01

Machine Learning applied to Automatic Audio Surveillance has been attracting increasing attention in recent years. In spite of several investigations based on a large number of different approaches, little attention had been paid to the environmental temporal evolution of the input signal. In this work, we propose an exploration in this direction comparing the temporal correlations extracted at the feature level with the one learned by a representational structure. To this aim we analysed the prediction performances of a Recurrent Neural Network architecture varying the length of the processed input sequence and the size of the time window used in the feature extraction. Results corroborated the hypothesis that sequential models work better when dealing with data characterized by temporal order. However, so far the optimization of the temporal dimension remains an open issue.

A Discrete-Time Recurrent Neural Network for Solving Rank-Deficient Matrix Equations With an Application to Output Regulation of Linear Systems.

Science.gov (United States)

Liu, Tao; Huang, Jie

2017-04-17

This paper presents a discrete-time recurrent neural network approach to solving systems of linear equations with two features. First, the system of linear equations may not have a unique solution. Second, the system matrix is not known precisely, but a sequence of matrices that converges to the unknown system matrix exponentially is known. The problem is motivated from solving the output regulation problem for linear systems. Thus, an application of our main result leads to an online solution to the output regulation problem for linear systems.

Distributed Recurrent Neural Forward Models with Neural Control for Complex Locomotion in Walking Robots

DEFF Research Database (Denmark)

Dasgupta, Sakyasingha; Goldschmidt, Dennis; Wörgötter, Florentin

2015-01-01

here, an artificial bio-inspired walking system which effectively combines biomechanics (in terms of the body and leg structures) with the underlying neural mechanisms. The neural mechanisms consist of (1) central pattern generator based control for generating basic rhythmic patterns and coordinated......Walking animals, like stick insects, cockroaches or ants, demonstrate a fascinating range of locomotive abilities and complex behaviors. The locomotive behaviors can consist of a variety of walking patterns along with adaptation that allow the animals to deal with changes in environmental...... conditions, like uneven terrains, gaps, obstacles etc. Biological study has revealed that such complex behaviors are a result of a combination of biomechanics and neural mechanism thus representing the true nature of embodied interactions. While the biomechanics helps maintain flexibility and sustain...

End-to-End Neural Optical Music Recognition of Monophonic Scores

Directory of Open Access Journals (Sweden)

Jorge Calvo-Zaragoza

2018-04-01

Full Text Available Optical Music Recognition is a field of research that investigates how to computationally decode music notation from images. Despite the efforts made so far, there are hardly any complete solutions to the problem. In this work, we study the use of neural networks that work in an end-to-end manner. This is achieved by using a neural model that combines the capabilities of convolutional neural networks, which work on the input image, and recurrent neural networks, which deal with the sequential nature of the problem. Thanks to the use of the the so-called Connectionist Temporal Classification loss function, these models can be directly trained from input images accompanied by their corresponding transcripts into music symbol sequences. We also present the Printed Music Scores dataset, containing more than 80,000 monodic single-staff real scores in common western notation, that is used to train and evaluate the neural approach. In our experiments, it is demonstrated that this formulation can be carried out successfully. Additionally, we study several considerations about the codification of the output musical sequences, the convergence and scalability of the neural models, as well as the ability of this approach to locate symbols in the input score.

Modeling and control of magnetorheological fluid dampers using neural networks

Science.gov (United States)

Wang, D. H.; Liao, W. H.

2005-02-01

Due to the inherent nonlinear nature of magnetorheological (MR) fluid dampers, one of the challenging aspects for utilizing these devices to achieve high system performance is the development of accurate models and control algorithms that can take advantage of their unique characteristics. In this paper, the direct identification and inverse dynamic modeling for MR fluid dampers using feedforward and recurrent neural networks are studied. The trained direct identification neural network model can be used to predict the damping force of the MR fluid damper on line, on the basis of the dynamic responses across the MR fluid damper and the command voltage, and the inverse dynamic neural network model can be used to generate the command voltage according to the desired damping force through supervised learning. The architectures and the learning methods of the dynamic neural network models and inverse neural network models for MR fluid dampers are presented, and some simulation results are discussed. Finally, the trained neural network models are applied to predict and control the damping force of the MR fluid damper. Moreover, validation methods for the neural network models developed are proposed and used to evaluate their performance. Validation results with different data sets indicate that the proposed direct identification dynamic model using the recurrent neural network can be used to predict the damping force accurately and the inverse identification dynamic model using the recurrent neural network can act as a damper controller to generate the command voltage when the MR fluid damper is used in a semi-active mode.

Combination of Deep Recurrent Neural Networks and Conditional Random Fields for Extracting Adverse Drug Reactions from User Reviews.

Science.gov (United States)

Tutubalina, Elena; Nikolenko, Sergey

2017-01-01

Adverse drug reactions (ADRs) are an essential part of the analysis of drug use, measuring drug use benefits, and making policy decisions. Traditional channels for identifying ADRs are reliable but very slow and only produce a small amount of data. Text reviews, either on specialized web sites or in general-purpose social networks, may lead to a data source of unprecedented size, but identifying ADRs in free-form text is a challenging natural language processing problem. In this work, we propose a novel model for this problem, uniting recurrent neural architectures and conditional random fields. We evaluate our model with a comprehensive experimental study, showing improvements over state-of-the-art methods of ADR extraction.

Combination of Deep Recurrent Neural Networks and Conditional Random Fields for Extracting Adverse Drug Reactions from User Reviews

Directory of Open Access Journals (Sweden)

Elena Tutubalina

2017-01-01

Full Text Available Adverse drug reactions (ADRs are an essential part of the analysis of drug use, measuring drug use benefits, and making policy decisions. Traditional channels for identifying ADRs are reliable but very slow and only produce a small amount of data. Text reviews, either on specialized web sites or in general-purpose social networks, may lead to a data source of unprecedented size, but identifying ADRs in free-form text is a challenging natural language processing problem. In this work, we propose a novel model for this problem, uniting recurrent neural architectures and conditional random fields. We evaluate our model with a comprehensive experimental study, showing improvements over state-of-the-art methods of ADR extraction.

Applying long short-term memory recurrent neural networks to intrusion detection

Directory of Open Access Journals (Sweden)

Ralf C. Staudemeyer

2015-07-01

Full Text Available We claim that modelling network traffic as a time series with a supervised learning approach, using known genuine and malicious behaviour, improves intrusion detection. To substantiate this, we trained long short-term memory (LSTM recurrent neural networks with the training data provided by the DARPA / KDD Cup ’99 challenge. To identify suitable LSTM-RNN network parameters and structure we experimented with various network topologies. We found networks with four memory blocks containing two cells each offer a good compromise between computational cost and detection performance. We applied forget gates and shortcut connections respectively. A learning rate of 0.1 and up to 1,000 epochs showed good results. We tested the performance on all features and on extracted minimal feature sets respectively. We evaluated different feature sets for the detection of all attacks within one network and also to train networks specialised on individual attack classes. Our results show that the LSTM classifier provides superior performance in comparison to results previously published results of strong static classifiers. With 93.82% accuracy and 22.13 cost, LSTM outperforms the winning entries of the KDD Cup ’99 challenge by far. This is due to the fact that LSTM learns to look back in time and correlate consecutive connection records. For the first time ever, we have demonstrated the usefulness of LSTM networks to intrusion detection.

Relation Classification via Recurrent Neural Network

OpenAIRE

Zhang, Dongxu; Wang, Dong

2015-01-01

Deep learning has gained much success in sentence-level relation classification. For example, convolutional neural networks (CNN) have delivered competitive performance without much effort on feature engineering as the conventional pattern-based methods. Thus a lot of works have been produced based on CNN structures. However, a key issue that has not been well addressed by the CNN-based method is the lack of capability to learn temporal features, especially long-distance dependency between no...

Ridge Polynomial Neural Network with Error Feedback for Time Series Forecasting.

Science.gov (United States)

Waheeb, Waddah; Ghazali, Rozaida; Herawan, Tutut

2016-01-01

Time series forecasting has gained much attention due to its many practical applications. Higher-order neural network with recurrent feedback is a powerful technique that has been used successfully for time series forecasting. It maintains fast learning and the ability to learn the dynamics of the time series over time. Network output feedback is the most common recurrent feedback for many recurrent neural network models. However, not much attention has been paid to the use of network error feedback instead of network output feedback. In this study, we propose a novel model, called Ridge Polynomial Neural Network with Error Feedback (RPNN-EF) that incorporates higher order terms, recurrence and error feedback. To evaluate the performance of RPNN-EF, we used four univariate time series with different forecasting horizons, namely star brightness, monthly smoothed sunspot numbers, daily Euro/Dollar exchange rate, and Mackey-Glass time-delay differential equation. We compared the forecasting performance of RPNN-EF with the ordinary Ridge Polynomial Neural Network (RPNN) and the Dynamic Ridge Polynomial Neural Network (DRPNN). Simulation results showed an average 23.34% improvement in Root Mean Square Error (RMSE) with respect to RPNN and an average 10.74% improvement with respect to DRPNN. That means that using network errors during training helps enhance the overall forecasting performance for the network.

Ridge Polynomial Neural Network with Error Feedback for Time Series Forecasting.

Directory of Open Access Journals (Sweden)

Waddah Waheeb

Full Text Available Time series forecasting has gained much attention due to its many practical applications. Higher-order neural network with recurrent feedback is a powerful technique that has been used successfully for time series forecasting. It maintains fast learning and the ability to learn the dynamics of the time series over time. Network output feedback is the most common recurrent feedback for many recurrent neural network models. However, not much attention has been paid to the use of network error feedback instead of network output feedback. In this study, we propose a novel model, called Ridge Polynomial Neural Network with Error Feedback (RPNN-EF that incorporates higher order terms, recurrence and error feedback. To evaluate the performance of RPNN-EF, we used four univariate time series with different forecasting horizons, namely star brightness, monthly smoothed sunspot numbers, daily Euro/Dollar exchange rate, and Mackey-Glass time-delay differential equation. We compared the forecasting performance of RPNN-EF with the ordinary Ridge Polynomial Neural Network (RPNN and the Dynamic Ridge Polynomial Neural Network (DRPNN. Simulation results showed an average 23.34% improvement in Root Mean Square Error (RMSE with respect to RPNN and an average 10.74% improvement with respect to DRPNN. That means that using network errors during training helps enhance the overall forecasting performance for the network.

Retrieving Single Scattering Albedos and Temperatures from CRISM Hyperspectral Data Using Neural Networks

Science.gov (United States)

He, L.; Arvidson, R. E.; O'Sullivan, J. A.

2018-04-01

We use a neural network (NN) approach to simultaneously retrieve surface single scattering albedos and temperature maps for CRISM data from 1.40 to 3.85 µm. It approximates the inverse of DISORT which simulates solar and emission radiative streams.

Place cell rate remapping by CA3 recurrent collaterals.

Directory of Open Access Journals (Sweden)

Trygve Solstad

2014-06-01

Full Text Available Episodic-like memory is thought to be supported by attractor dynamics in the hippocampus. A possible neural substrate for this memory mechanism is rate remapping, in which the spatial map of place cells encodes contextual information through firing rate variability. To test whether memories are stored as multimodal attractors in populations of place cells, recent experiments morphed one familiar context into another while observing the responses of CA3 cell ensembles. Average population activity in CA3 was reported to transition gradually rather than abruptly from one familiar context to the next, suggesting a lack of attractive forces associated with the two stored representations. On the other hand, individual CA3 cells showed a mix of gradual and abrupt transitions at different points along the morph sequence, and some displayed hysteresis which is a signature of attractor dynamics. To understand whether these seemingly conflicting results are commensurate with attractor network theory, we developed a neural network model of the CA3 with attractors for both position and discrete contexts. We found that for memories stored in overlapping neural ensembles within a single spatial map, position-dependent context attractors made transitions at different points along the morph sequence. Smooth transition curves arose from averaging across the population, while a heterogeneous set of responses was observed on the single unit level. In contrast, orthogonal memories led to abrupt and coherent transitions on both population and single unit levels as experimentally observed when remapping between two independent spatial maps. Strong recurrent feedback entailed a hysteretic effect on the network which diminished with the amount of overlap in the stored memories. These results suggest that context-dependent memory can be supported by overlapping local attractors within a spatial map of CA3 place cells. Similar mechanisms for context-dependent memory may

Boolean Factor Analysis by Attractor Neural Network

Czech Academy of Sciences Publication Activity Database

Frolov, A. A.; Húsek, Dušan; Muraviev, I. P.; Polyakov, P.Y.

2007-01-01

Roč. 18, č. 3 (2007), s. 698-707 ISSN 1045-9227 R&D Projects: GA AV ČR 1ET100300419; GA ČR GA201/05/0079 Institutional research plan: CEZ:AV0Z10300504 Keywords : recurrent neural network * Hopfield-like neural network * associative memory * unsupervised learning * neural network architecture * neural network application * statistics * Boolean factor analysis * dimensionality reduction * features clustering * concepts search * information retrieval Subject RIV: BB - Applied Statistics, Operational Research Impact factor: 2.769, year: 2007

Recurrent fuzzy neural network backstepping control for the prescribed output tracking performance of nonlinear dynamic systems.

Science.gov (United States)

Han, Seong-Ik; Lee, Jang-Myung

2014-01-01

This paper proposes a backstepping control system that uses a tracking error constraint and recurrent fuzzy neural networks (RFNNs) to achieve a prescribed tracking performance for a strict-feedback nonlinear dynamic system. A new constraint variable was defined to generate the virtual control that forces the tracking error to fall within prescribed boundaries. An adaptive RFNN was also used to obtain the required improvement on the approximation performances in order to avoid calculating the explosive number of terms generated by the recursive steps of traditional backstepping control. The boundedness and convergence of the closed-loop system was confirmed based on the Lyapunov stability theory. The prescribed performance of the proposed control scheme was validated by using it to control the prescribed error of a nonlinear system and a robot manipulator. © 2013 ISA. Published by Elsevier Ltd. All rights reserved.

Recurrent fuzzy neural network by using feedback error learning approaches for LFC in interconnected power system

International Nuclear Information System (INIS)

Sabahi, Kamel; Teshnehlab, Mohammad; Shoorhedeli, Mahdi Aliyari

2009-01-01

In this study, a new adaptive controller based on modified feedback error learning (FEL) approaches is proposed for load frequency control (LFC) problem. The FEL strategy consists of intelligent and conventional controllers in feedforward and feedback paths, respectively. In this strategy, a conventional feedback controller (CFC), i.e. proportional, integral and derivative (PID) controller, is essential to guarantee global asymptotic stability of the overall system; and an intelligent feedforward controller (INFC) is adopted to learn the inverse of the controlled system. Therefore, when the INFC learns the inverse of controlled system, the tracking of reference signal is done properly. Generally, the CFC is designed at nominal operating conditions of the system and, therefore, fails to provide the best control performance as well as global stability over a wide range of changes in the operating conditions of the system. So, in this study a supervised controller (SC), a lookup table based controller, is addressed for tuning of the CFC. During abrupt changes of the power system parameters, the SC adjusts the PID parameters according to these operating conditions. Moreover, for improving the performance of overall system, a recurrent fuzzy neural network (RFNN) is adopted in INFC instead of the conventional neural network, which was used in past studies. The proposed FEL controller has been compared with the conventional feedback error learning controller (CFEL) and the PID controller through some performance indices

Recurrent hamburger thyrotoxicosis

Science.gov (United States)

Parmar, Malvinder S.; Sturge, Cecil

2003-01-01

RECURRENT EPISODES OF SPONTANEOUSLY RESOLVING HYPERTHYROIDISM may be caused by release of preformed hormone from the thyroid gland after it has been damaged by inflammation (recurrent silent thyroiditis) or by exogenous administration of thyroid hormone, which might be intentional or surreptitious (thyrotoxicosis factitia). Community-wide outbreaks of “hamburger thyrotoxicosis” resulting from inadvertent consumption of beef contaminated with bovine thyroid gland have been previously reported. Here we describe a single patient who experienced recurrent episodes of this phenomenon over an 11-year period and present an approach to systematically evaluating patients with recurrent hyperthyroidism. PMID:12952802

Mining e-cigarette adverse events in social media using Bi-LSTM recurrent neural network with word embedding representation.

Science.gov (United States)

Xie, Jiaheng; Liu, Xiao; Dajun Zeng, Daniel

2018-01-01

Recent years have seen increased worldwide popularity of e-cigarette use. However, the risks of e-cigarettes are underexamined. Most e-cigarette adverse event studies have achieved low detection rates due to limited subject sample sizes in the experiments and surveys. Social media provides a large data repository of consumers' e-cigarette feedback and experiences, which are useful for e-cigarette safety surveillance. However, it is difficult to automatically interpret the informal and nontechnical consumer vocabulary about e-cigarettes in social media. This issue hinders the use of social media content for e-cigarette safety surveillance. Recent developments in deep neural network methods have shown promise for named entity extraction from noisy text. Motivated by these observations, we aimed to design a deep neural network approach to extract e-cigarette safety information in social media. Our deep neural language model utilizes word embedding as the representation of text input and recognizes named entity types with the state-of-the-art Bidirectional Long Short-Term Memory (Bi-LSTM) Recurrent Neural Network. Our Bi-LSTM model achieved the best performance compared to 3 baseline models, with a precision of 94.10%, a recall of 91.80%, and an F-measure of 92.94%. We identified 1591 unique adverse events and 9930 unique e-cigarette components (ie, chemicals, flavors, and devices) from our research testbed. Although the conditional random field baseline model had slightly better precision than our approach, our Bi-LSTM model achieved much higher recall, resulting in the best F-measure. Our method can be generalized to extract medical concepts from social media for other medical applications. © The Author 2017. Published by Oxford University Press on behalf of the American Medical Informatics Association. All rights reserved. For Permissions, please email: journals.permissions@oup.com

Stimulus-dependent suppression of chaos in recurrent neural networks

International Nuclear Information System (INIS)

Rajan, Kanaka; Abbott, L. F.; Sompolinsky, Haim

2010-01-01

Neuronal activity arises from an interaction between ongoing firing generated spontaneously by neural circuits and responses driven by external stimuli. Using mean-field analysis, we ask how a neural network that intrinsically generates chaotic patterns of activity can remain sensitive to extrinsic input. We find that inputs not only drive network responses, but they also actively suppress ongoing activity, ultimately leading to a phase transition in which chaos is completely eliminated. The critical input intensity at the phase transition is a nonmonotonic function of stimulus frequency, revealing a 'resonant' frequency at which the input is most effective at suppressing chaos even though the power spectrum of the spontaneous activity peaks at zero and falls exponentially. A prediction of our analysis is that the variance of neural responses should be most strongly suppressed at frequencies matching the range over which many sensory systems operate.

Recurrent and Dynamic Models for Predicting Streaming Video Quality of Experience.

Science.gov (United States)

Bampis, Christos G; Li, Zhi; Katsavounidis, Ioannis; Bovik, Alan C

2018-07-01

Streaming video services represent a very large fraction of global bandwidth consumption. Due to the exploding demands of mobile video streaming services, coupled with limited bandwidth availability, video streams are often transmitted through unreliable, low-bandwidth networks. This unavoidably leads to two types of major streaming-related impairments: compression artifacts and/or rebuffering events. In streaming video applications, the end-user is a human observer; hence being able to predict the subjective Quality of Experience (QoE) associated with streamed videos could lead to the creation of perceptually optimized resource allocation strategies driving higher quality video streaming services. We propose a variety of recurrent dynamic neural networks that conduct continuous-time subjective QoE prediction. By formulating the problem as one of time-series forecasting, we train a variety of recurrent neural networks and non-linear autoregressive models to predict QoE using several recently developed subjective QoE databases. These models combine multiple, diverse neural network inputs, such as predicted video quality scores, rebuffering measurements, and data related to memory and its effects on human behavioral responses, using them to predict QoE on video streams impaired by both compression artifacts and rebuffering events. Instead of finding a single time-series prediction model, we propose and evaluate ways of aggregating different models into a forecasting ensemble that delivers improved results with reduced forecasting variance. We also deploy appropriate new evaluation metrics for comparing time-series predictions in streaming applications. Our experimental results demonstrate improved prediction performance that approaches human performance. An implementation of this work can be found at https://github.com/christosbampis/NARX_QoE_release.

Gender Differences in Risk Factors for Single and Recurrent Falls Among the Community-Dwelling Elderly

Directory of Open Access Journals (Sweden)

Yu Mei O

2015-08-01

Full Text Available The purpose of this study was to identify gender differences in risk factors of fall accidents among older people, and whether these factors differ between single and recurrent fallers. A total of 4,426 individuals aged ≥65 years from two large-scale health surveys provided data. Logistic regression analyses were used to identify risk factors and to determine the risk model for falling and recurrent falling in men and women separately. Three major risk factors for falling regardless of gender or fall history are fear of falling, limitations in activities of daily living (ADL, and age ≥75 years. Fear of falling remains one of the common modifiable risk factors. Among those without a fall history, the use of sedatives or tranquilizers increases the risk of falling. Regarding gender differences, ADL limitations and fear of falling appear to be stronger fall risk factors for men than for women. Among women, alcohol use and educational level are significant risk factors for falling, while loneliness is associated with recurrent falling. Men with fear of falling or ADL limitations are at higher risk to have a recurrent fall accident than women with these conditions. Having a visual impairment or living with someone is associated with recurrent falling among men. Our findings emphasize the importance of multifactorial fall interventions, taking into account a variety of subgroup characteristics such as gender and fall history.

Precision position control of servo systems using adaptive back-stepping and recurrent fuzzy neural networks

International Nuclear Information System (INIS)

Kim, Han Me; Kim, Jong Shik; Han, Seong Ik

2009-01-01

To improve position tracking performance of servo systems, a position tracking control using adaptive back-stepping control(ABSC) scheme and recurrent fuzzy neural networks(RFNN) is proposed. An adaptive rule of the ABSC based on system dynamics and dynamic friction model is also suggested to compensate nonlinear dynamic friction characteristics. However, it is difficult to reduce the position tracking error of servo systems by using only the ABSC scheme because of the system uncertainties which cannot be exactly identified during the modeling of servo systems. Therefore, in order to overcome system uncertainties and then to improve position tracking performance of servo systems, the RFNN technique is additionally applied to the servo system. The feasibility of the proposed control scheme for a servo system is validated through experiments. Experimental results show that the servo system with ABS controller based on the dual friction observer and RFNN including the reconstruction error estimator can achieve desired tracking performance and robustness

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

Science.gov (United States)

1994-06-09

PROBLEM BASED ON LEARNING IN THE RECURRENT RANDOM NEURAL NETWORK Jose AGUILAR EHEI. UFR de Mathematiques et d’Informatique. Universiti Rene Descartes 45...parallelisme optimal". PHD thesis. Rene Descartes University, Paris, France, 1992. 9. GELENBE, E. "Learning in the recurrent Random Neural Network", Neural

Modeling long-term human activeness using recurrent neural networks for biometric data.

Science.gov (United States)

Kim, Zae Myung; Oh, Hyungrai; Kim, Han-Gyu; Lim, Chae-Gyun; Oh, Kyo-Joong; Choi, Ho-Jin

2017-05-18

With the invention of fitness trackers, it has been possible to continuously monitor a user's biometric data such as heart rates, number of footsteps taken, and amount of calories burned. This paper names the time series of these three types of biometric data, the user's "activeness", and investigates the feasibility in modeling and predicting the long-term activeness of the user. The dataset used in this study consisted of several months of biometric time-series data gathered by seven users independently. Four recurrent neural network (RNN) architectures-as well as a deep neural network and a simple regression model-were proposed to investigate the performance on predicting the activeness of the user under various length-related hyper-parameter settings. In addition, the learned model was tested to predict the time period when the user's activeness falls below a certain threshold. A preliminary experimental result shows that each type of activeness data exhibited a short-term autocorrelation; and among the three types of data, the consumed calories and the number of footsteps were positively correlated, while the heart rate data showed almost no correlation with neither of them. It is probably due to this characteristic of the dataset that although the RNN models produced the best results on modeling the user's activeness, the difference was marginal; and other baseline models, especially the linear regression model, performed quite admirably as well. Further experimental results show that it is feasible to predict a user's future activeness with precision, for example, a trained RNN model could predict-with the precision of 84%-when the user would be less active within the next hour given the latest 15 min of his activeness data. This paper defines and investigates the notion of a user's "activeness", and shows that forecasting the long-term activeness of the user is indeed possible. Such information can be utilized by a health-related application to proactively

Nonlinear identification of process dynamics using neural networks

International Nuclear Information System (INIS)

Parlos, A.G.; Atiya, A.F.; Chong, K.T.

1992-01-01

In this paper the nonlinear identification of process dynamics encountered in nuclear power plant components is addressed, in an input-output sense, using artificial neural systems. A hybrid feedforward/feedback neural network, namely, a recurrent multilayer perceptron, is used as the model structure to be identified. The feedforward portion of the network architecture provides its well-known interpolation property, while through recurrency and cross-talk, the local information feedback enables representation of temporal variations in the system nonlinearities. The standard backpropagation learning algorithm is modified, and it is used for the supervised training of the proposed hybrid network. The performance of recurrent multilayer perceptron networks in identifying process dynamics is investigated via the case study of a U-tube steam generator. The response of representative steam generator is predicted using a neural network, and it is compared to the response obtained from a sophisticated computer model based on first principles. The transient responses compare well, although further research is warranted to determine the predictive capabilities of these networks during more severe operational transients and accident scenarios

Optimal multiple-information integration inherent in a ring neural network

International Nuclear Information System (INIS)

Takiyama, Ken

2017-01-01

Although several behavioral experiments have suggested that our neural system integrates multiple sources of information based on the certainty of each type of information in the manner of maximum-likelihood estimation, it is unclear how the maximum-likelihood estimation is implemented in our neural system. Here, I investigate the relationship between maximum-likelihood estimation and a widely used ring-type neural network model that is used as a model of visual, motor, or prefrontal cortices. Without any approximation or ansatz, I analytically demonstrate that the equilibrium of an order parameter in the neural network model exactly corresponds to the maximum-likelihood estimation when the strength of the symmetrical recurrent synaptic connectivity within a neural population is appropriately stronger than that of asymmetrical connectivity, that of local and external inputs, and that of symmetrical or asymmetrical connectivity between different neural populations. In this case, strengths of local and external inputs or those of symmetrical connectivity between different neural populations exactly correspond to the input certainty in maximum-likelihood estimation. Thus, my analysis suggests appropriately strong symmetrical recurrent connectivity as a possible candidate for implementing the maximum-likelihood estimation within our neural system. (paper)

A new neural observer for an anaerobic bioreactor.

Science.gov (United States)

Belmonte-Izquierdo, R; Carlos-Hernandez, S; Sanchez, E N

2010-02-01

In this paper, a recurrent high order neural observer (RHONO) for anaerobic processes is proposed. The main objective is to estimate variables of methanogenesis: biomass, substrate and inorganic carbon in a completely stirred tank reactor (CSTR). The recurrent high order neural network (RHONN) structure is based on the hyperbolic tangent as activation function. The learning algorithm is based on an extended Kalman filter (EKF). The applicability of the proposed scheme is illustrated via simulation. A validation using real data from a lab scale process is included. Thus, this observer can be successfully implemented for control purposes.

Signal Processing and Neural Network Simulator

Science.gov (United States)

Tebbe, Dennis L.; Billhartz, Thomas J.; Doner, John R.; Kraft, Timothy T.

1995-04-01

The signal processing and neural network simulator (SPANNS) is a digital signal processing simulator with the capability to invoke neural networks into signal processing chains. This is a generic tool which will greatly facilitate the design and simulation of systems with embedded neural networks. The SPANNS is based on the Signal Processing WorkSystemTM (SPWTM), a commercial-off-the-shelf signal processing simulator. SPW provides a block diagram approach to constructing signal processing simulations. Neural network paradigms implemented in the SPANNS include Backpropagation, Kohonen Feature Map, Outstar, Fully Recurrent, Adaptive Resonance Theory 1, 2, & 3, and Brain State in a Box. The SPANNS was developed by integrating SAIC's Industrial Strength Neural Networks (ISNN) Software into SPW.

Spatiotemporal discrimination in neural networks with short-term synaptic plasticity

Science.gov (United States)

Shlaer, Benjamin; Miller, Paul

2015-03-01

Cells in recurrently connected neural networks exhibit bistability, which allows for stimulus information to persist in a circuit even after stimulus offset, i.e. short-term memory. However, such a system does not have enough hysteresis to encode temporal information about the stimuli. The biophysically described phenomenon of synaptic depression decreases synaptic transmission strengths due to increased presynaptic activity. This short-term reduction in synaptic strengths can destabilize attractor states in excitatory recurrent neural networks, causing the network to move along stimulus dependent dynamical trajectories. Such a network can successfully separate amplitudes and durations of stimuli from the number of successive stimuli. Stimulus number, duration and intensity encoding in randomly connected attractor networks with synaptic depression. Front. Comput. Neurosci. 7:59., and so provides a strong candidate network for the encoding of spatiotemporal information. Here we explicitly demonstrate the capability of a recurrent neural network with short-term synaptic depression to discriminate between the temporal sequences in which spatial stimuli are presented.

DanQ: a hybrid convolutional and recurrent deep neural network for quantifying the function of DNA sequences.

Science.gov (United States)

Quang, Daniel; Xie, Xiaohui

2016-06-20

Modeling the properties and functions of DNA sequences is an important, but challenging task in the broad field of genomics. This task is particularly difficult for non-coding DNA, the vast majority of which is still poorly understood in terms of function. A powerful predictive model for the function of non-coding DNA can have enormous benefit for both basic science and translational research because over 98% of the human genome is non-coding and 93% of disease-associated variants lie in these regions. To address this need, we propose DanQ, a novel hybrid convolutional and bi-directional long short-term memory recurrent neural network framework for predicting non-coding function de novo from sequence. In the DanQ model, the convolution layer captures regulatory motifs, while the recurrent layer captures long-term dependencies between the motifs in order to learn a regulatory 'grammar' to improve predictions. DanQ improves considerably upon other models across several metrics. For some regulatory markers, DanQ can achieve over a 50% relative improvement in the area under the precision-recall curve metric compared to related models. We have made the source code available at the github repository http://github.com/uci-cbcl/DanQ. © The Author(s) 2016. Published by Oxford University Press on behalf of Nucleic Acids Research.

Personality in remitted major depressive disorder with single and recurrent episodes assessed with the Temperament and Character Inventory.

Science.gov (United States)

Teraishi, Toshiya; Hori, Hiroaki; Sasayama, Daimei; Matsuo, Junko; Ogawa, Shintaro; Ishida, Ikki; Nagashima, Anna; Kinoshita, Yukiko; Ota, Miho; Hattori, Kotaro; Higuchi, Teruhiko; Kunugi, Hiroshi

2015-01-01

Previous studies consistently reported increased harm avoidance (HA) assessed with the Temperament and Character Inventory (TCI) in patients with major depressive disorder (MDD). However, such findings may have been related with depression severity and number of depressive episodes. The aims of the present study were twofold: to examine TCI personality profile in remitted MDD (DSM-IV) patients and to compare TCI personality between MDD patients with single episode (SGL-MDD) and those with recurrent episodes (REC-MDD) in order to elucidate personality profile associated with recurrence. TCI was administered to 86 outpatients with remitted SGL-MDD (12 male and 17 female patients; mean age 43.2 ± 12.1 years) and REC-MDD (26 male and 31 female patients; 40.3 ± 11.6 years), and 529 healthy controls (225 men and 304 women; 43.4 ± 15.5 years), matched for age, sex and education years. Logistic regression analyses were performed in which single/recurrent episodes of depression were the dependent variable and age, sex, age of onset, family history of psychiatric disease and TCI scores were entered as possible predictors. The remitted MDD patients had significantly higher scores on HA (P differences in personality profile between remitted MDD patients and controls, and between remitted REC-MDD and SGL-MDD patients, suggesting that they are trait markers. HA and fatigability might be useful to assess risk for recurrence of depression. © 2014 The Authors. Psychiatry and Clinical Neurosciences © 2014 Japanese Society of Psychiatry and Neurology.

Risk of recurrence after a single manic or mixed episode - a systematic review and meta-analysis

DEFF Research Database (Denmark)

Kessing, Lars Vedel; Andersen, Per Kragh; Vinberg, Maj

2017-01-01

OBJECTIVES: For the first time to estimate the risk of recurrence among patients with a single manic/mixed episode by systematically reviewing prior studies on cohorts of adults, and cohorts of children and adolescents, respectively. METHODS: A systematic literature search up to August 2017...... was carried out including studies in which mixed episode at inclusion. RESULTS: Three studies including a total of 293 adult patients with a single manic or mixed episode...... as children and adolescents. It is important that clinicians and patients as well as relatives are well informed about these high risks when deciding to start maintenance treatment or not following onset of a single manic or mixed episode....

Protein Solvent-Accessibility Prediction by a Stacked Deep Bidirectional Recurrent Neural Network

Directory of Open Access Journals (Sweden)

Buzhong Zhang

2018-05-01

Full Text Available Residue solvent accessibility is closely related to the spatial arrangement and packing of residues. Predicting the solvent accessibility of a protein is an important step to understand its structure and function. In this work, we present a deep learning method to predict residue solvent accessibility, which is based on a stacked deep bidirectional recurrent neural network applied to sequence profiles. To capture more long-range sequence information, a merging operator was proposed when bidirectional information from hidden nodes was merged for outputs. Three types of merging operators were used in our improved model, with a long short-term memory network performing as a hidden computing node. The trained database was constructed from 7361 proteins extracted from the PISCES server using a cut-off of 25% sequence identity. Sequence-derived features including position-specific scoring matrix, physical properties, physicochemical characteristics, conservation score and protein coding were used to represent a residue. Using this method, predictive values of continuous relative solvent-accessible area were obtained, and then, these values were transformed into binary states with predefined thresholds. Our experimental results showed that our deep learning method improved prediction quality relative to current methods, with mean absolute error and Pearson’s correlation coefficient values of 8.8% and 74.8%, respectively, on the CB502 dataset and 8.2% and 78%, respectively, on the Manesh215 dataset.

Protein Solvent-Accessibility Prediction by a Stacked Deep Bidirectional Recurrent Neural Network.

Science.gov (United States)

Zhang, Buzhong; Li, Linqing; Lü, Qiang

2018-05-25

Residue solvent accessibility is closely related to the spatial arrangement and packing of residues. Predicting the solvent accessibility of a protein is an important step to understand its structure and function. In this work, we present a deep learning method to predict residue solvent accessibility, which is based on a stacked deep bidirectional recurrent neural network applied to sequence profiles. To capture more long-range sequence information, a merging operator was proposed when bidirectional information from hidden nodes was merged for outputs. Three types of merging operators were used in our improved model, with a long short-term memory network performing as a hidden computing node. The trained database was constructed from 7361 proteins extracted from the PISCES server using a cut-off of 25% sequence identity. Sequence-derived features including position-specific scoring matrix, physical properties, physicochemical characteristics, conservation score and protein coding were used to represent a residue. Using this method, predictive values of continuous relative solvent-accessible area were obtained, and then, these values were transformed into binary states with predefined thresholds. Our experimental results showed that our deep learning method improved prediction quality relative to current methods, with mean absolute error and Pearson's correlation coefficient values of 8.8% and 74.8%, respectively, on the CB502 dataset and 8.2% and 78%, respectively, on the Manesh215 dataset.

Recurrent Syncope due to Esophageal Squamous Cell Carcinoma

OpenAIRE

Casini, Alessandro; Tschanz, Elisabeth; Dietrich, Pierre-Yves; Nendaz, Mathieu

2011-01-01

Syncope is caused by a wide variety of disorders. Recurrent syncope as a complication of malignancy is uncommon and may be difficult to diagnose and to treat. Primary neck carcinoma or metastases spreading in parapharyngeal and carotid spaces can involve the internal carotid artery and cause neurally mediated syncope with a clinical presentation like carotid sinus syndrome. We report the case of a 76-year-old man who suffered from recurrent syncope due to invasion of the right carotid sinus b...

The diagnostic accuracy of a single CEA blood test in detecting colorectal cancer recurrence: Results from the FACS trial.

Directory of Open Access Journals (Sweden)

Bethany Shinkins

Full Text Available To evaluate the diagnostic accuracy of a single CEA (carcinoembryonic antigen blood test in detecting colorectal cancer recurrence.Patients who have undergone curative resection for primary colorectal cancer are typically followed up with scheduled CEA testing for 5 years. Decisions to investigate further (usually by CT imaging are based on single test results, reflecting international guidelines.A secondary analysis was undertaken of data from the FACS trial (two arms included CEA testing. The composite reference standard applied included CT-CAP imaging, clinical assessment and colonoscopy. Accuracy in detecting recurrence was evaluated in terms of sensitivity, specificity, likelihood ratios, predictive values, time-dependent area under the ROC curves, and operational performance when used prospectively in clinical practice are reported.Of 582 patients, 104 (17.9% developed recurrence during the 5 year follow-up period. Applying the recommended threshold of 5μg/L achieves at best 50.0% sensitivity (95% CI: 40.1-59.9%; in prospective use in clinical practice it would lead to 56 missed recurrences (53.8%; 95% CI: 44.2-64.4% and 89 false alarms (56.7% of 157 patients referred for investigation. Applying a lower threshold of 2.5μg/L would reduce the number of missed recurrences to 36.5% (95% CI: 26.5-46.5% but would increase the false alarms to 84.2% (924/1097 referred. Some patients are more prone to false alarms than others-at the 5μg/L threshold, the 89 episodes of unnecessary investigation were clustered in 29 individuals.Our results demonstrated very low sensitivity for CEA, bringing to question whether it could ever be used as an independent triage test. It is not feasible to improve the diagnostic performance of a single test result by reducing the recommended action threshold because of the workload and false alarms generated. Current national and international guidelines merit re-evaluation and options to improve performance, such as

Neural Machine Translation with Recurrent Attention Modeling

OpenAIRE

Yang, Zichao; Hu, Zhiting; Deng, Yuntian; Dyer, Chris; Smola, Alex

2016-01-01

Knowing which words have been attended to in previous time steps while generating a translation is a rich source of information for predicting what words will be attended to in the future. We improve upon the attention model of Bahdanau et al. (2014) by explicitly modeling the relationship between previous and subsequent attention levels for each word using one recurrent network per input word. This architecture easily captures informative features, such as fertility and regularities in relat...

Classification of behavior using unsupervised temporal neural networks

International Nuclear Information System (INIS)

Adair, K.L.

1998-03-01

Adding recurrent connections to unsupervised neural networks used for clustering creates a temporal neural network which clusters a sequence of inputs as they appear over time. The model presented combines the Jordan architecture with the unsupervised learning technique Adaptive Resonance Theory, Fuzzy ART. The combination yields a neural network capable of quickly clustering sequential pattern sequences as the sequences are generated. The applicability of the architecture is illustrated through a facility monitoring problem

Confused or not Confused?: Disentangling Brain Activity from EEG Data Using Bidirectional LSTM Recurrent Neural Networks.

Science.gov (United States)

Ni, Zhaoheng; Yuksel, Ahmet Cem; Ni, Xiuyan; Mandel, Michael I; Xie, Lei

2017-08-01

Brain fog, also known as confusion, is one of the main reasons for low performance in the learning process or any kind of daily task that involves and requires thinking. Detecting confusion in a human's mind in real time is a challenging and important task that can be applied to online education, driver fatigue detection and so on. In this paper, we apply Bidirectional LSTM Recurrent Neural Networks to classify students' confusion in watching online course videos from EEG data. The results show that Bidirectional LSTM model achieves the state-of-the-art performance compared with other machine learning approaches, and shows strong robustness as evaluated by cross-validation. We can predict whether or not a student is confused in the accuracy of 73.3%. Furthermore, we find the most important feature to detecting the brain confusion is the gamma 1 wave of EEG signal. Our results suggest that machine learning is a potentially powerful tool to model and understand brain activity.

Estimates for Genetic Variance Components in Reciprocal Recurrent Selection in Populations Derived from Maize Single-Cross Hybrids

Directory of Open Access Journals (Sweden)

Matheus Costa dos Reis

2014-01-01

Full Text Available This study was carried out to obtain the estimates of genetic variance and covariance components related to intra- and interpopulation in the original populations (C0 and in the third cycle (C3 of reciprocal recurrent selection (RRS which allows breeders to define the best breeding strategy. For that purpose, the half-sib progenies of intrapopulation (P11 and P22 and interpopulation (P12 and P21 from populations 1 and 2 derived from single-cross hybrids in the 0 and 3 cycles of the reciprocal recurrent selection program were used. The intra- and interpopulation progenies were evaluated in a 10×10 triple lattice design in two separate locations. The data for unhusked ear weight (ear weight without husk and plant height were collected. All genetic variance and covariance components were estimated from the expected mean squares. The breakdown of additive variance into intrapopulation and interpopulation additive deviations (στ2 and the covariance between these and their intrapopulation additive effects (CovAτ found predominance of the dominance effect for unhusked ear weight. Plant height for these components shows that the intrapopulation additive effect explains most of the variation. Estimates for intrapopulation and interpopulation additive genetic variances confirm that populations derived from single-cross hybrids have potential for recurrent selection programs.

Feature Set Evaluation for Offline Handwriting Recognition Systems: Application to the Recurrent Neural Network Model.

Science.gov (United States)

Chherawala, Youssouf; Roy, Partha Pratim; Cheriet, Mohamed

2016-12-01

The performance of handwriting recognition systems is dependent on the features extracted from the word image. A large body of features exists in the literature, but no method has yet been proposed to identify the most promising of these, other than a straightforward comparison based on the recognition rate. In this paper, we propose a framework for feature set evaluation based on a collaborative setting. We use a weighted vote combination of recurrent neural network (RNN) classifiers, each trained with a particular feature set. This combination is modeled in a probabilistic framework as a mixture model and two methods for weight estimation are described. The main contribution of this paper is to quantify the importance of feature sets through the combination weights, which reflect their strength and complementarity. We chose the RNN classifier because of its state-of-the-art performance. Also, we provide the first feature set benchmark for this classifier. We evaluated several feature sets on the IFN/ENIT and RIMES databases of Arabic and Latin script, respectively. The resulting combination model is competitive with state-of-the-art systems.

Neural Network-Based Resistance Spot Welding Control and Quality Prediction

Energy Technology Data Exchange (ETDEWEB)

Allen, J.D., Jr.; Ivezic, N.D.; Zacharia, T.

1999-07-10

This paper describes the development and evaluation of neural network-based systems for industrial resistance spot welding process control and weld quality assessment. The developed systems utilize recurrent neural networks for process control and both recurrent networks and static networks for quality prediction. The first section describes a system capable of both welding process control and real-time weld quality assessment, The second describes the development and evaluation of a static neural network-based weld quality assessment system that relied on experimental design to limit the influence of environmental variability. Relevant data analysis methods are also discussed. The weld classifier resulting from the analysis successfldly balances predictive power and simplicity of interpretation. The results presented for both systems demonstrate clearly that neural networks can be employed to address two significant problems common to the resistance spot welding industry, control of the process itself, and non-destructive determination of resulting weld quality.

Tutorial on neural network applications in high energy physics: A 1992 perspective

International Nuclear Information System (INIS)

Denby, B.

1992-04-01

Feed forward and recurrent neural networks are introduced and related to standard data analysis tools. Tips are given on applications of neural nets to various areas of high energy physics. A review of applications within high energy physics and a summary of neural net hardware status are given

Monitoring tool usage in surgery videos using boosted convolutional and recurrent neural networks.

Science.gov (United States)

Al Hajj, Hassan; Lamard, Mathieu; Conze, Pierre-Henri; Cochener, Béatrice; Quellec, Gwenolé

2018-05-09

This paper investigates the automatic monitoring of tool usage during a surgery, with potential applications in report generation, surgical training and real-time decision support. Two surgeries are considered: cataract surgery, the most common surgical procedure, and cholecystectomy, one of the most common digestive surgeries. Tool usage is monitored in videos recorded either through a microscope (cataract surgery) or an endoscope (cholecystectomy). Following state-of-the-art video analysis solutions, each frame of the video is analyzed by convolutional neural networks (CNNs) whose outputs are fed to recurrent neural networks (RNNs) in order to take temporal relationships between events into account. Novelty lies in the way those CNNs and RNNs are trained. Computational complexity prevents the end-to-end training of "CNN+RNN" systems. Therefore, CNNs are usually trained first, independently from the RNNs. This approach is clearly suboptimal for surgical tool analysis: many tools are very similar to one another, but they can generally be differentiated based on past events. CNNs should be trained to extract the most useful visual features in combination with the temporal context. A novel boosting strategy is proposed to achieve this goal: the CNN and RNN parts of the system are simultaneously enriched by progressively adding weak classifiers (either CNNs or RNNs) trained to improve the overall classification accuracy. Experiments were performed in a dataset of 50 cataract surgery videos, where the usage of 21 surgical tools was manually annotated, and a dataset of 80 cholecystectomy videos, where the usage of 7 tools was manually annotated. Very good classification performance are achieved in both datasets: tool usage could be labeled with an average area under the ROC curve of A z =0.9961 and A z =0.9939, respectively, in offline mode (using past, present and future information), and A z =0.9957 and A z =0.9936, respectively, in online mode (using past and present

Deep Neural Network for Structural Prediction and Lane Detection in Traffic Scene.

Science.gov (United States)

Li, Jun; Mei, Xue; Prokhorov, Danil; Tao, Dacheng

2017-03-01

Hierarchical neural networks have been shown to be effective in learning representative image features and recognizing object classes. However, most existing networks combine the low/middle level cues for classification without accounting for any spatial structures. For applications such as understanding a scene, how the visual cues are spatially distributed in an image becomes essential for successful analysis. This paper extends the framework of deep neural networks by accounting for the structural cues in the visual signals. In particular, two kinds of neural networks have been proposed. First, we develop a multitask deep convolutional network, which simultaneously detects the presence of the target and the geometric attributes (location and orientation) of the target with respect to the region of interest. Second, a recurrent neuron layer is adopted for structured visual detection. The recurrent neurons can deal with the spatial distribution of visible cues belonging to an object whose shape or structure is difficult to explicitly define. Both the networks are demonstrated by the practical task of detecting lane boundaries in traffic scenes. The multitask convolutional neural network provides auxiliary geometric information to help the subsequent modeling of the given lane structures. The recurrent neural network automatically detects lane boundaries, including those areas containing no marks, without any explicit prior knowledge or secondary modeling.

The default mode network and recurrent depression: a neurobiological model of cognitive risk factors.

Science.gov (United States)

Marchetti, Igor; Koster, Ernst H W; Sonuga-Barke, Edmund J; De Raedt, Rudi

2012-09-01

A neurobiological account of cognitive vulnerability for recurrent depression is presented based on recent developments of resting state neural networks. We propose that alterations in the interplay between task positive (TP) and task negative (TN) elements of the Default Mode Network (DMN) act as a neurobiological risk factor for recurrent depression mediated by cognitive mechanisms. In the framework, depression is characterized by an imbalance between TN-TP components leading to an overpowering of TP by TN activity. The TN-TP imbalance is associated with a dysfunctional internally-focused cognitive style as well as a failure to attenuate TN activity in the transition from rest to task. Thus we propose the TN-TP imbalance as overarching neural mechanism involved in crucial cognitive risk factors for recurrent depression, namely rumination, impaired attentional control, and cognitive reactivity. During remission the TN-TP imbalance persists predisposing to vulnerability of recurrent depression. Empirical data to support this model is reviewed. Finally, we specify how this framework can guide future research efforts.

Homeostatic scaling of excitability in recurrent neural networks.

NARCIS (Netherlands)

Remme, M.W.H.; Wadman, W.J.

2012-01-01

Neurons adjust their intrinsic excitability when experiencing a persistent change in synaptic drive. This process can prevent neural activity from moving into either a quiescent state or a saturated state in the face of ongoing plasticity, and is thought to promote stability of the network in which

Financial Time Series Prediction Using Elman Recurrent Random Neural Networks

Directory of Open Access Journals (Sweden)

Jie Wang

2016-01-01

(ERNN, the empirical results show that the proposed neural network displays the best performance among these neural networks in financial time series forecasting. Further, the empirical research is performed in testing the predictive effects of SSE, TWSE, KOSPI, and Nikkei225 with the established model, and the corresponding statistical comparisons of the above market indices are also exhibited. The experimental results show that this approach gives good performance in predicting the values from the stock market indices.

RM-SORN: a reward-modulated self-organizing recurrent neural network.

Science.gov (United States)

Aswolinskiy, Witali; Pipa, Gordon

2015-01-01

Neural plasticity plays an important role in learning and memory. Reward-modulation of plasticity offers an explanation for the ability of the brain to adapt its neural activity to achieve a rewarded goal. Here, we define a neural network model that learns through the interaction of Intrinsic Plasticity (IP) and reward-modulated Spike-Timing-Dependent Plasticity (STDP). IP enables the network to explore possible output sequences and STDP, modulated by reward, reinforces the creation of the rewarded output sequences. The model is tested on tasks for prediction, recall, non-linear computation, pattern recognition, and sequence generation. It achieves performance comparable to networks trained with supervised learning, while using simple, biologically motivated plasticity rules, and rewarding strategies. The results confirm the importance of investigating the interaction of several plasticity rules in the context of reward-modulated learning and whether reward-modulated self-organization can explain the amazing capabilities of the brain.

A Neural Network Approach to Fluid Level Measurement in Dynamic Environments Using a Single Capacitive Sensor

Directory of Open Access Journals (Sweden)

Edin TERZIC

2010-03-01

Full Text Available A measurement system has been developed using a single tube capacitive sensor to accurately determine the fluid level in vehicular fuel tanks. A novel approach based on artificial neural networks based signal pre-processing and classification has been described in this article. A broad investigation on the Backpropagation neural network and some selected signal pre-processing filters, namely, Moving Mean, Moving Median, and Wavelet Filter has also been presented. An on field drive trial was conducted under normal driving conditions at various fuel volumes ranging from 5 L to 50 L to acquire training samples from the capacitive sensor. A second field trial was conducted to obtain test samples to verify the performance of the neural network. The neural network was trained and verified with 50 % of the training and test samples. The results obtained using the neural network approach having different filtration methods are compared with the results obtained using simple Moving Mean and Moving Median functions. It is demonstrated that the Backpropagation neural network with Moving Median filter produced the most accurate outcome compared with the other signal filtration methods.

Modeling Markov Switching ARMA-GARCH Neural Networks Models and an Application to Forecasting Stock Returns

Directory of Open Access Journals (Sweden)

Melike Bildirici

2014-01-01

Full Text Available The study has two aims. The first aim is to propose a family of nonlinear GARCH models that incorporate fractional integration and asymmetric power properties to MS-GARCH processes. The second purpose of the study is to augment the MS-GARCH type models with artificial neural networks to benefit from the universal approximation properties to achieve improved forecasting accuracy. Therefore, the proposed Markov-switching MS-ARMA-FIGARCH, APGARCH, and FIAPGARCH processes are further augmented with MLP, Recurrent NN, and Hybrid NN type neural networks. The MS-ARMA-GARCH family and MS-ARMA-GARCH-NN family are utilized for modeling the daily stock returns in an emerging market, the Istanbul Stock Index (ISE100. Forecast accuracy is evaluated in terms of MAE, MSE, and RMSE error criteria and Diebold-Mariano equal forecast accuracy tests. The results suggest that the fractionally integrated and asymmetric power counterparts of Gray’s MS-GARCH model provided promising results, while the best results are obtained for their neural network based counterparts. Further, among the models analyzed, the models based on the Hybrid-MLP and Recurrent-NN, the MS-ARMA-FIAPGARCH-HybridMLP, and MS-ARMA-FIAPGARCH-RNN provided the best forecast performances over the baseline single regime GARCH models and further, over the Gray’s MS-GARCH model. Therefore, the models are promising for various economic applications.

Attention-based Memory Selection Recurrent Network for Language Modeling

OpenAIRE

Liu, Da-Rong; Chuang, Shun-Po; Lee, Hung-yi

2016-01-01

Recurrent neural networks (RNNs) have achieved great success in language modeling. However, since the RNNs have fixed size of memory, their memory cannot store all the information about the words it have seen before in the sentence, and thus the useful long-term information may be ignored when predicting the next words. In this paper, we propose Attention-based Memory Selection Recurrent Network (AMSRN), in which the model can review the information stored in the memory at each previous time ...

Single image super-resolution based on convolutional neural networks

Science.gov (United States)

Zou, Lamei; Luo, Ming; Yang, Weidong; Li, Peng; Jin, Liujia

2018-03-01

We present a deep learning method for single image super-resolution (SISR). The proposed approach learns end-to-end mapping between low-resolution (LR) images and high-resolution (HR) images. The mapping is represented as a deep convolutional neural network which inputs the LR image and outputs the HR image. Our network uses 5 convolution layers, which kernels size include 5×5, 3×3 and 1×1. In our proposed network, we use residual-learning and combine different sizes of convolution kernels at the same layer. The experiment results show that our proposed method performs better than the existing methods in reconstructing quality index and human visual effects on benchmarked images.

A novel method for extraction of neural response from single channel cochlear implant auditory evoked potentials.

Science.gov (United States)

Sinkiewicz, Daniel; Friesen, Lendra; Ghoraani, Behnaz

2017-02-01

Cortical auditory evoked potentials (CAEP) are used to evaluate cochlear implant (CI) patient auditory pathways, but the CI device produces an electrical artifact, which obscures the relevant information in the neural response. Currently there are multiple methods, which attempt to recover the neural response from the contaminated CAEP, but there is no gold standard, which can quantitatively confirm the effectiveness of these methods. To address this crucial shortcoming, we develop a wavelet-based method to quantify the amount of artifact energy in the neural response. In addition, a novel technique for extracting the neural response from single channel CAEPs is proposed. The new method uses matching pursuit (MP) based feature extraction to represent the contaminated CAEP in a feature space, and support vector machines (SVM) to classify the components as normal hearing (NH) or artifact. The NH components are combined to recover the neural response without artifact energy, as verified using the evaluation tool. Although it needs some further evaluation, this approach is a promising method of electrical artifact removal from CAEPs. Copyright © 2016 IPEM. Published by Elsevier Ltd. All rights reserved.

Distinct neural control of intrinsic and extrinsic muscles of the hand during single finger pressing

NARCIS (Netherlands)

Dupan, Sigrid S.G.; Stegeman, Dick F.; Maas, Huub

2018-01-01

Single finger force tasks lead to unintended activation of the non-instructed fingers, commonly referred to as enslaving. Both neural and mechanical factors have been associated with this absence of finger individuality. This study investigates the amplitude modulation of both intrinsic and

Modeling Broadband Microwave Structures by Artificial Neural Networks

Directory of Open Access Journals (Sweden)

V. Otevrel

2004-06-01

Full Text Available The paper describes the exploitation of feed-forward neural networksand recurrent neural networks for replacing full-wave numerical modelsof microwave structures in complex microwave design tools. Building aneural model, attention is turned to the modeling accuracy and to theefficiency of building a model. Dealing with the accuracy, we describea method of increasing it by successive completing a training set.Neural models are mutually compared in order to highlight theiradvantages and disadvantages. As a reference model for comparisons,approximations based on standard cubic splines are used. Neural modelsare used to replace both the time-domain numeric models and thefrequency-domain ones.

Quasi-projective synchronization of fractional-order complex-valued recurrent neural networks.

Science.gov (United States)

Yang, Shuai; Yu, Juan; Hu, Cheng; Jiang, Haijun

2018-08-01

In this paper, without separating the complex-valued neural networks into two real-valued systems, the quasi-projective synchronization of fractional-order complex-valued neural networks is investigated. First, two new fractional-order inequalities are established by using the theory of complex functions, Laplace transform and Mittag-Leffler functions, which generalize traditional inequalities with the first-order derivative in the real domain. Additionally, different from hybrid control schemes given in the previous work concerning the projective synchronization, a simple and linear control strategy is designed in this paper and several criteria are derived to ensure quasi-projective synchronization of the complex-valued neural networks with fractional-order based on the established fractional-order inequalities and the theory of complex functions. Moreover, the error bounds of quasi-projective synchronization are estimated. Especially, some conditions are also presented for the Mittag-Leffler synchronization of the addressed neural networks. Finally, some numerical examples with simulations are provided to show the effectiveness of the derived theoretical results. Copyright © 2018 Elsevier Ltd. All rights reserved.

Local community detection as pattern restoration by attractor dynamics of recurrent neural networks.

Science.gov (United States)

Okamoto, Hiroshi

2016-08-01

Densely connected parts in networks are referred to as "communities". Community structure is a hallmark of a variety of real-world networks. Individual communities in networks form functional modules of complex systems described by networks. Therefore, finding communities in networks is essential to approaching and understanding complex systems described by networks. In fact, network science has made a great deal of effort to develop effective and efficient methods for detecting communities in networks. Here we put forward a type of community detection, which has been little examined so far but will be practically useful. Suppose that we are given a set of source nodes that includes some (but not all) of "true" members of a particular community; suppose also that the set includes some nodes that are not the members of this community (i.e., "false" members of the community). We propose to detect the community from this "imperfect" and "inaccurate" set of source nodes using attractor dynamics of recurrent neural networks. Community detection by the proposed method can be viewed as restoration of the original pattern from a deteriorated pattern, which is analogous to cue-triggered recall of short-term memory in the brain. We demonstrate the effectiveness of the proposed method using synthetic networks and real social networks for which correct communities are known. Copyright © 2016 Elsevier Ireland Ltd. All rights reserved.

Coupled Heuristic Prediction of Long Lead-Time Accumulated Total Inflow of a Reservoir during Typhoons Using Deterministic Recurrent and Fuzzy Inference-Based Neural Network

Directory of Open Access Journals (Sweden)

Chien-Lin Huang

2015-11-01

Full Text Available This study applies Real-Time Recurrent Learning Neural Network (RTRLNN and Adaptive Network-based Fuzzy Inference System (ANFIS with novel heuristic techniques to develop an advanced prediction model of accumulated total inflow of a reservoir in order to solve the difficulties of future long lead-time highly varied uncertainty during typhoon attacks while using a real-time forecast. For promoting the temporal-spatial forecasted precision, the following original specialized heuristic inputs were coupled: observed-predicted inflow increase/decrease (OPIID rate, total precipitation, and duration from current time to the time of maximum precipitation and direct runoff ending (DRE. This study also investigated the temporal-spatial forecasted error feature to assess the feasibility of the developed models, and analyzed the output sensitivity of both single and combined heuristic inputs to determine whether the heuristic model is susceptible to the impact of future forecasted uncertainty/errors. Validation results showed that the long lead-time–predicted accuracy and stability of the RTRLNN-based accumulated total inflow model are better than that of the ANFIS-based model because of the real-time recurrent deterministic routing mechanism of RTRLNN. Simulations show that the RTRLNN-based model with coupled heuristic inputs (RTRLNN-CHI, average error percentage (AEP/average forecast lead-time (AFLT: 6.3%/49 h can achieve better prediction than the model with non-heuristic inputs (AEP of RTRLNN-NHI and ANFIS-NHI: 15.2%/31.8% because of the full consideration of real-time hydrological initial/boundary conditions. Besides, the RTRLNN-CHI model can promote the forecasted lead-time above 49 h with less than 10% of AEP which can overcome the previous forecasted limits of 6-h AFLT with above 20%–40% of AEP.

Retrieval of Sentence Sequences for an Image Stream via Coherence Recurrent Convolutional Networks.

Science.gov (United States)

Park, Cesc Chunseong; Kim, Youngjin; Kim, Gunhee

2018-04-01

We propose an approach for retrieving a sequence of natural sentences for an image stream. Since general users often take a series of pictures on their experiences, much online visual information exists in the form of image streams, for which it would better take into consideration of the whole image stream to produce natural language descriptions. While almost all previous studies have dealt with the relation between a single image and a single natural sentence, our work extends both input and output dimension to a sequence of images and a sequence of sentences. For retrieving a coherent flow of multiple sentences for a photo stream, we propose a multimodal neural architecture called coherence recurrent convolutional network (CRCN), which consists of convolutional neural networks, bidirectional long short-term memory (LSTM) networks, and an entity-based local coherence model. Our approach directly learns from vast user-generated resource of blog posts as text-image parallel training data. We collect more than 22 K unique blog posts with 170 K associated images for the travel topics of NYC, Disneyland , Australia, and Hawaii. We demonstrate that our approach outperforms other state-of-the-art image captioning methods for text sequence generation, using both quantitative measures and user studies via Amazon Mechanical Turk.

A visual sense of number emerges from the dynamics of a recurrent on-center off-surround neural network.

Science.gov (United States)

Sengupta, Rakesh; Surampudi, Bapi Raju; Melcher, David

2014-09-25

It has been proposed that the ability of humans to quickly perceive numerosity involves a visual sense of number. Different paradigms of enumeration and numerosity comparison have produced a gamut of behavioral and neuroimaging data, but there has been no unified conceptual framework that can explain results across the entire range of numerosity. The current work tries to address the ongoing debate concerning whether the same mechanism operates for enumeration of small and large numbers, through a computational approach. We describe the workings of a single-layered, fully connected network characterized by self-excitation and recurrent inhibition that operates at both subitizing and estimation ranges. We show that such a network can account for classic numerical cognition effects (the distance effect, Fechner׳s law, Weber fraction for numerosity comparison) through the network steady state activation response across different recurrent inhibition values. The model also accounts for fMRI data previously reported for different enumeration related tasks. The model also allows us to generate an estimate of the pattern of reaction times in enumeration tasks. Overall, these findings suggest that a single network architecture can account for both small and large number processing. Copyright © 2014. Published by Elsevier B.V.

Investigation of Prognostic Factors and Survival without Recurrence in Patients with Breast Cancer

Directory of Open Access Journals (Sweden)

Ahmad Abdollahi

2017-01-01

Full Text Available Background: One of the major consequences of breast cancer is the recurrence of the disease. The objective of present study was to estimate the 7-year survival without recurrence as well as the effective prognostic factors in recurrence. Materials and Methods: This historical cohort survival analysis was conducted on 1329 patients diagnosed with breast cancer in Motahari Breast Clinic, Shiraz, Iran between 2004 and 2011. We estimated the rate of survival without recurrence through the Kaplan–Meier method and the difference between the survival curves was investigated using the log-rank test. Furthermore, Cox regression model was used to model the effective factors in local recurrence as well as metastasis. Results: The mean age of the patients was 54.8 ± 11.4 years. Estrogen receptor positive, progesterone receptor positive, and human epidermal growth factor receptor-2 positive were observed in 70.6%, 66.6%, and 34.4% of the cases, respectively. The mean of the follow-up period was 3.7 ± 1.8 years in all patients. The results of the Kaplan–Meier method revealed 1-, 3-, 5-, and 7-year rate of survival without recurrence as 96.4%, 78.4%, 66.3%, and 54.8%, respectively. There was a significant relationship between survival without recurrence and histology grade (hazard ratio [HR] = 1.66, P = 0.009, neural invasion (HR = 1.74, P = 0.006, and progesterone receptors (HR = 0.69, P = 0.031. Conclusion: In this study, the rate of survival without recurrence in breast cancer was 54.8%. Among factors, histology grade and neural involvement at the time of diagnosis increased the chance of recurrence and progesterone receptors caused a longer interval between diagnosis and recurrence.

Predictors of recurrence in pheochromocytoma.

Science.gov (United States)

Press, Danielle; Akyuz, Muhammet; Dural, Cem; Aliyev, Shamil; Monteiro, Rosebel; Mino, Jeff; Mitchell, Jamie; Hamrahian, Amir; Siperstein, Allan; Berber, Eren

2014-12-01

The recurrence rate of pheochromocytoma after adrenalectomy is 6.5-16.5%. This study aims to identify predictors of recurrence and optimal biochemical testing and imaging for detecting the recurrence of pheochromocytoma. In this retrospective study we reviewed all patients who underwent adrenalectomy for pheochromocytoma during a 14-year period at a single institution. One hundred thirty-five patients had adrenalectomy for pheochromocytoma. Eight patients (6%) developed recurrent disease. The median time from initial operation to diagnosis of recurrence was 35 months. On multivariate analysis, tumor size >5 cm was an independent predictor of recurrence. One patient with recurrence died, 4 had stable disease, 2 had progression of disease, and 1 was cured. Recurrence was diagnosed by increases in plasma and/or urinary metanephrines and positive imaging in 6 patients (75%), and by positive imaging and normal biochemical levels in 2 patients (25%). Patients with large tumors (>5 cm) should be followed vigilantly for recurrence. Because 25% of patients with recurrence had normal biochemical levels, we recommend routine imaging and testing of plasma or urinary metanephrines for prompt diagnosis of recurrence. Copyright © 2014 Elsevier Inc. All rights reserved.

Recurrent squamous cell carcinoma of the skin treated successfully with single agent cetuximab therapy

Directory of Open Access Journals (Sweden)

Seber S

2016-02-01

Full Text Available Selcuk Seber,1 Aylin Gonultas,2 Ozlem Ozturk,2 Tarkan Yetisyigit1 1Department of Medical Oncology, Faculty of Medicine, Namik Kemal University, 2Pathology Department, Tekirdag State Hospital, Tekirdag, Turkey Abstract: Recurrent squamous cell carcinoma of the skin is a rare but difficult to treat condition. Frequently, the disease presents itself in elderly patients with poor performance status and bearing many comorbidities, thus the decision to administer systemic chemotherapy becomes difficult to make. In addition, current chemotherapeutic protocols response rates are far from satisfactory. Recently cetuximab, a chimeric antibody against epidermal growth factor receptor, is increasingly being reported as an alternative treatment. We therefore report this case of a recurrent squamous cell carcinoma of the skin in an elderly woman with poor performance status and who had an excellent clinical response to single agent cetuximab therapy with complete resolution of the disease and minimal toxicity during the course of the treatment to provide evidence for future prospective clinical trials. Keywords: cetuximab, EGFR inhibiton, squamous cell carcinoma of the skin

Hypofractionated stereotactic radiation therapy for recurrent glioblastoma: single institutional experience

International Nuclear Information System (INIS)

Ciammella, Patrizia; Podgornii, Ala; Galeandro, Maria; D’Abbiero, Nunziata; Pisanello, Anna; Botti, Andrea; Cagni, Elisabetta; Iori, Mauro; Iotti, Cinzia

2013-01-01

Glioblastoma (GBM) is the most common malignant primary brain tumor in adults. Tumor control and survival have improved with the use of radiotherapy (RT) plus concomitant and adjuvant chemotherapy, but the prognosis remain poor. In most cases the recurrence occurs within 7–9 months after primary treatment. Currently, many approaches are available for the salvage treatment of patients with recurrent GBM, including resection, re-irradiation or systemic agents, but no standard of care exists. We analysed a cohort of patients with recurrent GBM treated with frame-less hypofractionated stereotactic radiation therapy with a total dose of 25 Gy in 5 fractions. Of 91 consecutive patients with newly diagnosed GBM treated between 2007 and 2012 with conventional adjuvant chemo-radiation therapy, 15 underwent salvage RT at recurrence. The median time interval between primary RT and salvage RT was 10.8 months (range, 6–54 months). Overall, patients undergoing salvage RT showed a longer survival, with a median survival of 33 vs. 9.9 months (p= 0.00149). Median overall survival (OS) from salvage RT was 9.5 months. No patients demonstrated clinically significant acute morbidity, and all patients were able to complete the prescribed radiation therapy without interruption. Our results suggest that hypofractionated stereotactic radiation therapy is effective and safe in recurrent GBM. However, until prospective randomized trials will confirm these results, the decision for salvage treatment should remain individual and based on a multidisciplinary evaluation of each patient

Entity recognition from clinical texts via recurrent neural network.

Science.gov (United States)

Liu, Zengjian; Yang, Ming; Wang, Xiaolong; Chen, Qingcai; Tang, Buzhou; Wang, Zhe; Xu, Hua

2017-07-05

Entity recognition is one of the most primary steps for text analysis and has long attracted considerable attention from researchers. In the clinical domain, various types of entities, such as clinical entities and protected health information (PHI), widely exist in clinical texts. Recognizing these entities has become a hot topic in clinical natural language processing (NLP), and a large number of traditional machine learning methods, such as support vector machine and conditional random field, have been deployed to recognize entities from clinical texts in the past few years. In recent years, recurrent neural network (RNN), one of deep learning methods that has shown great potential on many problems including named entity recognition, also has been gradually used for entity recognition from clinical texts. In this paper, we comprehensively investigate the performance of LSTM (long-short term memory), a representative variant of RNN, on clinical entity recognition and protected health information recognition. The LSTM model consists of three layers: input layer - generates representation of each word of a sentence; LSTM layer - outputs another word representation sequence that captures the context information of each word in this sentence; Inference layer - makes tagging decisions according to the output of LSTM layer, that is, outputting a label sequence. Experiments conducted on corpora of the 2010, 2012 and 2014 i2b2 NLP challenges show that LSTM achieves highest micro-average F1-scores of 85.81% on the 2010 i2b2 medical concept extraction, 92.29% on the 2012 i2b2 clinical event detection, and 94.37% on the 2014 i2b2 de-identification, which is considerably competitive with other state-of-the-art systems. LSTM that requires no hand-crafted feature has great potential on entity recognition from clinical texts. It outperforms traditional machine learning methods that suffer from fussy feature engineering. A possible future direction is how to integrate knowledge

An efficient automated parameter tuning framework for spiking neural networks.

Science.gov (United States)

Carlson, Kristofor D; Nageswaran, Jayram Moorkanikara; Dutt, Nikil; Krichmar, Jeffrey L

2014-01-01

As the desire for biologically realistic spiking neural networks (SNNs) increases, tuning the enormous number of open parameters in these models becomes a difficult challenge. SNNs have been used to successfully model complex neural circuits that explore various neural phenomena such as neural plasticity, vision systems, auditory systems, neural oscillations, and many other important topics of neural function. Additionally, SNNs are particularly well-adapted to run on neuromorphic hardware that will support biological brain-scale architectures. Although the inclusion of realistic plasticity equations, neural dynamics, and recurrent topologies has increased the descriptive power of SNNs, it has also made the task of tuning these biologically realistic SNNs difficult. To meet this challenge, we present an automated parameter tuning framework capable of tuning SNNs quickly and efficiently using evolutionary algorithms (EA) and inexpensive, readily accessible graphics processing units (GPUs). A sample SNN with 4104 neurons was tuned to give V1 simple cell-like tuning curve responses and produce self-organizing receptive fields (SORFs) when presented with a random sequence of counterphase sinusoidal grating stimuli. A performance analysis comparing the GPU-accelerated implementation to a single-threaded central processing unit (CPU) implementation was carried out and showed a speedup of 65× of the GPU implementation over the CPU implementation, or 0.35 h per generation for GPU vs. 23.5 h per generation for CPU. Additionally, the parameter value solutions found in the tuned SNN were studied and found to be stable and repeatable. The automated parameter tuning framework presented here will be of use to both the computational neuroscience and neuromorphic engineering communities, making the process of constructing and tuning large-scale SNNs much quicker and easier.

Pacemaker Therapy in Patients With Neurally Mediated Syncope and Documented Asystole Third International Study on Syncope of Uncertain Etiology (ISSUE-3) A Randomized Trial

NARCIS (Netherlands)

Brignole, Michele; Menozzi, Carlo; Moya, Angel; Andresen, Dietrich; Blanc, Jean Jacques; Krahn, Andrew D.; Wieling, Wouter; Beiras, Xulio; Deharo, Jean Claude; Russo, Vitantonio; Tomaino, Marco; Sutton, Richard; Tomaino, M.; Pescoller, F.; Donateo, P.; Oddone, D.; Russo, V.; Pierri, F.; Matino, M. G.; Vitale, E.; Massa, R.; Piccinni, G.; Melissano, D.; Menozzi, C.; Lolli, G.; Gulizia, M.; Francese, M.; Iorfida, M.; Golzio, P.; Gaggioli, G.; Laffi, M.; Rabjoli, F.; Cecchinato, C.; Ungar, A.; Rafanelli, M.; Chisciotti, V.; Morrione, A.; del Rosso, A.; Guernaccia, V.; Palella, M.; D'Agostino, C.; Campana, A.; Brigante, M.; Miracapillo, G.; Addonisio, L.; Proclemer, A.; Facchin, D.; Vado, A.; Knops, R. E.; Dekker, L. R. C.

2012-01-01

Background-The efficacy of cardiac pacing for prevention of syncopal recurrences in patients with neurally mediated syncope is controversial. We wanted to determine whether pacing therapy reduces syncopal recurrences in patients with severe asystolic neurally mediated syncope. Methods and

Single-stage anterior high sacrectomy for locally recurrent rectal cancer.

Science.gov (United States)

Fawaz, Khaled; Khaled, Fawaz; Smith, Myles J; Moises, Cukier; Smith, Andrew J; Yee, Albert J M

2014-03-01

A review of prospectively collected data on a consecutive series of patients undergoing single-stage anterior high sacrectomy for locally recurrent rectal carcinoma (LRRC). To determine the clinical outcome of patients who underwent anterior high sacrectomy for LRRC. High sacrectomy for oncological resection remains technically challenging. Surgery has the potential to achieve cure in carefully selected patients. Complete (R0) tumor excision in LRRC may require sacrectomy. High sacral resections (S3 and above) typically require a combined anterior/supine and posterior/prone procedure. We investigated our experience performing single-stage anterior high sacrectomy for LRRC. A consecutive series of patients with LRRC without systemic metastases who underwent resection with curative intent requiring high sacrectomy were identified. A review of a prospectively maintained colorectal and spine cancer database data was performed. An oblique dome high sacral osteotomy was performed during a single-stage anterior procedure. Outcome measures included surgical resection margin status, hospital length of stay, postoperative complications, physical functioning status, and overall survival. Nineteen consecutive patients were treated between 2002 and 2011. High sacrectomy was performed at sacral level S1-S2 in 4 patients, S2-S3 in 9 patients, and through S3 in 6 patients. An R0 resection margin was achieved histologically in all 19 cases. There was 1 early (<30 d) postoperative death (1/19, 5%). At median follow-up of 38 months, 13 patients had no evidence of residual disease, 1 was alive with disease, and 4 had died of disease. Morbidities occurred in 15 of the 19 patients (79%). Although high sacrectomy may require a combined anterior and posterior surgical approach, our series demonstrates the feasibility of performing single-stage anterior high sacrectomy in LRRC, with acceptable risks and outcomes compared with the literature. The procedure described by us for LRRC lessens

Hardware implementation of stochastic spiking neural networks.

Science.gov (United States)

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

2012-08-01

Spiking Neural Networks, the last generation of Artificial Neural Networks, are characterized by its bio-inspired nature and by a higher computational capacity with respect to other neural models. In real biological neurons, stochastic processes represent an important mechanism of neural behavior and are responsible of its special arithmetic capabilities. In this work we present a simple hardware implementation of spiking neurons that considers this probabilistic nature. The advantage of the proposed implementation is that it is fully digital and therefore can be massively implemented in Field Programmable Gate Arrays. The high computational capabilities of the proposed model are demonstrated by the study of both feed-forward and recurrent networks that are able to implement high-speed signal filtering and to solve complex systems of linear equations.

Tuning Recurrent Neural Networks for Recognizing Handwritten Arabic Words

KAUST Repository

Qaralleh, Esam; Abandah, Gheith; Jamour, Fuad Tarek

2013-01-01

and sizes of the hidden layers. Large sizes are slow and small sizes are generally not accurate. Tuning the neural network size is a hard task because the design space is often large and training is often a long process. We use design of experiments

Criticality predicts maximum irregularity in recurrent networks of excitatory nodes.

Directory of Open Access Journals (Sweden)

Yahya Karimipanah

Full Text Available A rigorous understanding of brain dynamics and function requires a conceptual bridge between multiple levels of organization, including neural spiking and network-level population activity. Mounting evidence suggests that neural networks of cerebral cortex operate at a critical regime, which is defined as a transition point between two phases of short lasting and chaotic activity. However, despite the fact that criticality brings about certain functional advantages for information processing, its supporting evidence is still far from conclusive, as it has been mostly based on power law scaling of size and durations of cascades of activity. Moreover, to what degree such hypothesis could explain some fundamental features of neural activity is still largely unknown. One of the most prevalent features of cortical activity in vivo is known to be spike irregularity of spike trains, which is measured in terms of the coefficient of variation (CV larger than one. Here, using a minimal computational model of excitatory nodes, we show that irregular spiking (CV > 1 naturally emerges in a recurrent network operating at criticality. More importantly, we show that even at the presence of other sources of spike irregularity, being at criticality maximizes the mean coefficient of variation of neurons, thereby maximizing their spike irregularity. Furthermore, we also show that such a maximized irregularity results in maximum correlation between neuronal firing rates and their corresponding spike irregularity (measured in terms of CV. On the one hand, using a model in the universality class of directed percolation, we propose new hallmarks of criticality at single-unit level, which could be applicable to any network of excitable nodes. On the other hand, given the controversy of the neural criticality hypothesis, we discuss the limitation of this approach to neural systems and to what degree they support the criticality hypothesis in real neural networks. Finally

An Implantable Wireless Neural Interface System for Simultaneous Recording and Stimulation of Peripheral Nerve with a Single Cuff Electrode.

Science.gov (United States)

Shon, Ahnsei; Chu, Jun-Uk; Jung, Jiuk; Kim, Hyungmin; Youn, Inchan

2017-12-21

Recently, implantable devices have become widely used in neural prostheses because they eliminate endemic drawbacks of conventional percutaneous neural interface systems. However, there are still several issues to be considered: low-efficiency wireless power transmission; wireless data communication over restricted operating distance with high power consumption; and limited functionality, working either as a neural signal recorder or as a stimulator. To overcome these issues, we suggest a novel implantable wireless neural interface system for simultaneous neural signal recording and stimulation using a single cuff electrode. By using widely available commercial off-the-shelf (COTS) components, an easily reconfigurable implantable wireless neural interface system was implemented into one compact module. The implantable device includes a wireless power consortium (WPC)-compliant power transmission circuit, a medical implant communication service (MICS)-band-based radio link and a cuff-electrode path controller for simultaneous neural signal recording and stimulation. During in vivo experiments with rabbit models, the implantable device successfully recorded and stimulated the tibial and peroneal nerves while communicating with the external device. The proposed system can be modified for various implantable medical devices, especially such as closed-loop control based implantable neural prostheses requiring neural signal recording and stimulation at the same time.

An Implantable Wireless Neural Interface System for Simultaneous Recording and Stimulation of Peripheral Nerve with a Single Cuff Electrode

Directory of Open Access Journals (Sweden)

Ahnsei Shon

2017-12-01

Full Text Available Recently, implantable devices have become widely used in neural prostheses because they eliminate endemic drawbacks of conventional percutaneous neural interface systems. However, there are still several issues to be considered: low-efficiency wireless power transmission; wireless data communication over restricted operating distance with high power consumption; and limited functionality, working either as a neural signal recorder or as a stimulator. To overcome these issues, we suggest a novel implantable wireless neural interface system for simultaneous neural signal recording and stimulation using a single cuff electrode. By using widely available commercial off-the-shelf (COTS components, an easily reconfigurable implantable wireless neural interface system was implemented into one compact module. The implantable device includes a wireless power consortium (WPC-compliant power transmission circuit, a medical implant communication service (MICS-band-based radio link and a cuff-electrode path controller for simultaneous neural signal recording and stimulation. During in vivo experiments with rabbit models, the implantable device successfully recorded and stimulated the tibial and peroneal nerves while communicating with the external device. The proposed system can be modified for various implantable medical devices, especially such as closed-loop control based implantable neural prostheses requiring neural signal recording and stimulation at the same time.

Bezlotoxumab: A Review in Preventing Clostridium difficile Infection Recurrence.

Science.gov (United States)

Deeks, Emma D

2017-10-01

Bezlotoxumab (Zinplava™) is a fully human monoclonal antibody against Clostridium difficile toxin B indicated for the prevention of C. difficile infection (CDI) recurrence in patients with a high recurrence risk. It is the first agent approved for recurrence prevention and is administered as a single intravenous infusion in conjunction with standard-of-care (SoC) antibacterial treatment for CDI. In well-designed, placebo-controlled, phase 3 trials (MODIFY 1 and 2), a single infusion of bezlotoxumab, given in combination with SoC antibacterial therapy for CDI in adults, was effective in reducing CDI recurrence in the 12 weeks post-treatment, with this benefit being seen mainly in the patients at high recurrence risk. Bezlotoxumab did not impact the efficacy of the antibacterials being used to treat the CDI and, consistent with its benefits on CDI recurrence, appeared to reduce the need for subsequent antibacterials, thus minimizing further gut microbiota disruption. Longer term, there were no further CDI recurrences over 12 months' follow-up among patients who had received bezlotoxumab in MODIFY 2 and entered an extension substudy. Bezlotoxumab has low immunogenicity and is generally well tolerated, although the potential for heart failure in some patients requires consideration; cost-effectiveness data for bezlotoxumab are awaited with interest. Thus, a single intravenous infusion of bezlotoxumab during SoC antibacterial treatment for CDI is an emerging option for reducing CDI recurrence in adults at high risk of recurrence.

Integrated built-in-test false and missed alarms reduction based on forward infinite impulse response & recurrent finite impulse response dynamic neural networks

Science.gov (United States)

Cui, Yiqian; Shi, Junyou; Wang, Zili

2017-11-01

Built-in tests (BITs) are widely used in mechanical systems to perform state identification, whereas the BIT false and missed alarms cause trouble to the operators or beneficiaries to make correct judgments. Artificial neural networks (ANN) are previously used for false and missed alarms identification, which has the features such as self-organizing and self-study. However, these ANN models generally do not incorporate the temporal effect of the bottom-level threshold comparison outputs and the historical temporal features are not fully considered. To improve the situation, this paper proposes a new integrated BIT design methodology by incorporating a novel type of dynamic neural networks (DNN) model. The new DNN model is termed as Forward IIR & Recurrent FIR DNN (FIRF-DNN), where its component neurons, network structures, and input/output relationships are discussed. The condition monitoring false and missed alarms reduction implementation scheme based on FIRF-DNN model is also illustrated, which is composed of three stages including model training, false and missed alarms detection, and false and missed alarms suppression. Finally, the proposed methodology is demonstrated in the application study and the experimental results are analyzed.

Dynamic stability analysis of fractional order leaky integrator echo state neural networks

Science.gov (United States)

Pahnehkolaei, Seyed Mehdi Abedi; Alfi, Alireza; Tenreiro Machado, J. A.

2017-06-01

The Leaky integrator echo state neural network (Leaky-ESN) is an improved model of the recurrent neural network (RNN) and adopts an interconnected recurrent grid of processing neurons. This paper presents a new proof for the convergence of a Lyapunov candidate function to zero when time tends to infinity by means of the Caputo fractional derivative with order lying in the range (0, 1). The stability of Fractional-Order Leaky-ESN (FO Leaky-ESN) is then analyzed, and the existence, uniqueness and stability of the equilibrium point are provided. A numerical example demonstrates the feasibility of the proposed method.

Drosophila olfactory memory: single genes to complex neural circuits.

Science.gov (United States)

Keene, Alex C; Waddell, Scott

2007-05-01

A central goal of neuroscience is to understand how neural circuits encode memory and guide behaviour. Studying simple, genetically tractable organisms, such as Drosophila melanogaster, can illuminate principles of neural circuit organization and function. Early genetic dissection of D. melanogaster olfactory memory focused on individual genes and molecules. These molecular tags subsequently revealed key neural circuits for memory. Recent advances in genetic technology have allowed us to manipulate and observe activity in these circuits, and even individual neurons, in live animals. The studies have transformed D. melanogaster from a useful organism for gene discovery to an ideal model to understand neural circuit function in memory.

A study of reactor monitoring method with neural network

Energy Technology Data Exchange (ETDEWEB)

Nabeshima, Kunihiko [Japan Atomic Energy Research Inst., Tokai, Ibaraki (Japan). Tokai Research Establishment

2001-03-01

The purpose of this study is to investigate the methodology of Nuclear Power Plant (NPP) monitoring with neural networks, which create the plant models by the learning of the past normal operation patterns. The concept of this method is to detect the symptom of small anomalies by monitoring the deviations between the process signals measured from an actual plant and corresponding output signals from the neural network model, which might not be equal if the abnormal operational patterns are presented to the input of the neural network. Auto-associative network, which has same output as inputs, can detect an kind of anomaly condition by using normal operation data only. The monitoring tests of the feedforward neural network with adaptive learning were performed using the PWR plant simulator by which many kinds of anomaly conditions can be easily simulated. The adaptively trained feedforward network could follow the actual plant dynamics and the changes of plant condition, and then find most of the anomalies much earlier than the conventional alarm system during steady state and transient operations. Then the off-line and on-line test results during one year operation at the actual NPP (PWR) showed that the neural network could detect several small anomalies which the operators or the conventional alarm system didn't noticed. Furthermore, the sensitivity analysis suggests that the plant models by neural networks are appropriate. Finally, the simulation results show that the recurrent neural network with feedback connections could successfully model the slow behavior of the reactor dynamics without adaptive learning. Therefore, the recurrent neural network with adaptive learning will be the best choice for the actual reactor monitoring system. (author)

Learning State Space Dynamics in Recurrent Networks

Science.gov (United States)

Simard, Patrice Yvon

Fully recurrent (asymmetrical) networks can be used to learn temporal trajectories. The network is unfolded in time, and backpropagation is used to train the weights. The presence of recurrent connections creates internal states in the system which vary as a function of time. The resulting dynamics can provide interesting additional computing power but learning is made more difficult by the existence of internal memories. This study first exhibits the properties of recurrent networks in terms of convergence when the internal states of the system are unknown. A new energy functional is provided to change the weights of the units in order to the control the stability of the fixed points of the network's dynamics. The power of the resultant algorithm is illustrated with the simulation of a content addressable memory. Next, the more general case of time trajectories on a recurrent network is studied. An application is proposed in which trajectories are generated to draw letters as a function of an input. In another application of recurrent systems, a neural network certain temporal properties observed in human callosally sectioned brains. Finally the proposed algorithm for stabilizing dynamics around fixed points is extended to one for stabilizing dynamics around time trajectories. Its effects are illustrated on a network which generates Lisajous curves.

Impacts of single and recurrent wildfires on topsoil moisture regime

Science.gov (United States)

González-Pelayo, Oscar; Malvar, Maruxa; van den Elsen, Erik; Hosseini, Mohammadreza; Coelho, Celeste; Ritsema, Coen; Bautista, Susana; Keizer, Jacob

2017-04-01

The increasing fire recurrence on forest in the Mediterranean basin is well-established by future climate scenarios due to land use changes and climate predictions. By this, shifts on mature pine woodlands to shrub rangelands are of major importance on forest ecosystems buffer functions, since historical patterns of established vegetation help to recover from fire disturbances. This fact, together with the predicted expansion of the drought periods, will affect feedback processes of vegetation patterns since water availability on these seasons are driven by post-fire local soil properties. Although fire impacts of soil properties and water availability has been widely studied using the fire severity as the main factor, little research is developed on post-fire soil moisture patterns, including the fire recurrence as a key explanatory variable. The following research investigated, in pine woodlands of north central Portugal, the short-term consequences (one year after a fire) of wildfire recurrence on the surface soil moisture content (SMC) and on effective soil water (SWEFF, parameter that includes actual daily soil moisture, soil field capacity-FC and permanent wilting point-PWP). The study set-up includes analyses at two fire recurrence scenarios (1x- and 4x-burnt since 1975), at a patch level (shrub patch/interpatch) and at two soil depths (2.5 and 7.5 cm) in a nested approach. Understanding how fire recurrence affects water in soil over space and time is the main goal of this research. The use of soil moisture sensors in a nested approach, the rainfall features and analyses on basic soil properties as soil organic matter, texture, bulk density, pF curves, soil water repellency and soil surface components will establish which factors has the largest role in controlling soil moisture behavior. Main results displayed, in a seasonal and yearly basis, no differences on SMC as increasing fire recurrence (1x- vs 4x-burnt) neither between patch/interpatch microsites at

On the Nature of the Intrinsic Connectivity of the Cat Motor Cortex: Evidence for a Recurrent Neural Network Topology

DEFF Research Database (Denmark)

Capaday, Charles; Ethier, C; Brizzi, L

2009-01-01

and functional significance of the intrinsic horizontal connections between neurons in the motor cortex (MCx) remain to be clarified. To further elucidate the nature of this intracortical connectivity pattern, experiments were done on the MCx of three cats. The anterograde tracer biocytin was ejected......Capaday C, Ethier C, Brizzi L, Sik A, van Vreeswijk C, Gingras D. On the nature of the intrinsic connectivity of the cat motor cortex: evidence for a recurrent neural network topology. J Neurophysiol 102: 2131-2141, 2009. First published July 22, 2009; doi: 10.1152/jn.91319.2008. The details...... iontophoretically in layers II, III, and V. Some 30-50 neurons within a radius of similar to 250 mu m were thus stained. The functional output of the motor cortical point at which biocytin was injected, and of the surrounding points, was identified by microstimulation and electromyographic recordings. The axonal...

Prediction of beta-turns and beta-turn types by a novel bidirectional Elman-type recurrent neural network with multiple output layers (MOLEBRNN).

Science.gov (United States)

Kirschner, Andreas; Frishman, Dmitrij

2008-10-01

Prediction of beta-turns from amino acid sequences has long been recognized as an important problem in structural bioinformatics due to their frequent occurrence as well as their structural and functional significance. Because various structural features of proteins are intercorrelated, secondary structure information has been often employed as an additional input for machine learning algorithms while predicting beta-turns. Here we present a novel bidirectional Elman-type recurrent neural network with multiple output layers (MOLEBRNN) capable of predicting multiple mutually dependent structural motifs and demonstrate its efficiency in recognizing three aspects of protein structure: beta-turns, beta-turn types, and secondary structure. The advantage of our method compared to other predictors is that it does not require any external input except for sequence profiles because interdependencies between different structural features are taken into account implicitly during the learning process. In a sevenfold cross-validation experiment on a standard test dataset our method exhibits the total prediction accuracy of 77.9% and the Mathew's Correlation Coefficient of 0.45, the highest performance reported so far. It also outperforms other known methods in delineating individual turn types. We demonstrate how simultaneous prediction of multiple targets influences prediction performance on single targets. The MOLEBRNN presented here is a generic method applicable in a variety of research fields where multiple mutually depending target classes need to be predicted. http://webclu.bio.wzw.tum.de/predator-web/.

Neural network decoder for quantum error correcting codes

Science.gov (United States)

Krastanov, Stefan; Jiang, Liang

Artificial neural networks form a family of extremely powerful - albeit still poorly understood - tools used in anything from image and sound recognition through text generation to, in our case, decoding. We present a straightforward Recurrent Neural Network architecture capable of deducing the correcting procedure for a quantum error-correcting code from a set of repeated stabilizer measurements. We discuss the fault-tolerance of our scheme and the cost of training the neural network for a system of a realistic size. Such decoders are especially interesting when applied to codes, like the quantum LDPC codes, that lack known efficient decoding schemes.

Recurrent neural network-based modeling of gene regulatory network using elephant swarm water search algorithm.

Science.gov (United States)

Mandal, Sudip; Saha, Goutam; Pal, Rajat Kumar

2017-08-01

Correct inference of genetic regulations inside a cell from the biological database like time series microarray data is one of the greatest challenges in post genomic era for biologists and researchers. Recurrent Neural Network (RNN) is one of the most popular and simple approach to model the dynamics as well as to infer correct dependencies among genes. Inspired by the behavior of social elephants, we propose a new metaheuristic namely Elephant Swarm Water Search Algorithm (ESWSA) to infer Gene Regulatory Network (GRN). This algorithm is mainly based on the water search strategy of intelligent and social elephants during drought, utilizing the different types of communication techniques. Initially, the algorithm is tested against benchmark small and medium scale artificial genetic networks without and with presence of different noise levels and the efficiency was observed in term of parametric error, minimum fitness value, execution time, accuracy of prediction of true regulation, etc. Next, the proposed algorithm is tested against the real time gene expression data of Escherichia Coli SOS Network and results were also compared with others state of the art optimization methods. The experimental results suggest that ESWSA is very efficient for GRN inference problem and performs better than other methods in many ways.

Classification of epileptic seizures using wavelet packet log energy and norm entropies with recurrent Elman neural network classifier.

Science.gov (United States)

Raghu, S; Sriraam, N; Kumar, G Pradeep

2017-02-01

Electroencephalogram shortly termed as EEG is considered as the fundamental segment for the assessment of the neural activities in the brain. In cognitive neuroscience domain, EEG-based assessment method is found to be superior due to its non-invasive ability to detect deep brain structure while exhibiting superior spatial resolutions. Especially for studying the neurodynamic behavior of epileptic seizures, EEG recordings reflect the neuronal activity of the brain and thus provide required clinical diagnostic information for the neurologist. This specific proposed study makes use of wavelet packet based log and norm entropies with a recurrent Elman neural network (REN) for the automated detection of epileptic seizures. Three conditions, normal, pre-ictal and epileptic EEG recordings were considered for the proposed study. An adaptive Weiner filter was initially applied to remove the power line noise of 50 Hz from raw EEG recordings. Raw EEGs were segmented into 1 s patterns to ensure stationarity of the signal. Then wavelet packet using Haar wavelet with a five level decomposition was introduced and two entropies, log and norm were estimated and were applied to REN classifier to perform binary classification. The non-linear Wilcoxon statistical test was applied to observe the variation in the features under these conditions. The effect of log energy entropy (without wavelets) was also studied. It was found from the simulation results that the wavelet packet log entropy with REN classifier yielded a classification accuracy of 99.70 % for normal-pre-ictal, 99.70 % for normal-epileptic and 99.85 % for pre-ictal-epileptic.

International Conference on Artificial Neural Networks (ICANN)

CERN Document Server

Mladenov, Valeri; Kasabov, Nikola; Artificial Neural Networks : Methods and Applications in Bio-/Neuroinformatics

2015-01-01

The book reports on the latest theories on artificial neural networks, with a special emphasis on bio-neuroinformatics methods. It includes twenty-three papers selected from among the best contributions on bio-neuroinformatics-related issues, which were presented at the International Conference on Artificial Neural Networks, held in Sofia, Bulgaria, on September 10-13, 2013 (ICANN 2013). The book covers a broad range of topics concerning the theory and applications of artificial neural networks, including recurrent neural networks, super-Turing computation and reservoir computing, double-layer vector perceptrons, nonnegative matrix factorization, bio-inspired models of cell communities, Gestalt laws, embodied theory of language understanding, saccadic gaze shifts and memory formation, and new training algorithms for Deep Boltzmann Machines, as well as dynamic neural networks and kernel machines. It also reports on new approaches to reinforcement learning, optimal control of discrete time-delay systems, new al...

Identifying time-delayed gene regulatory networks via an evolvable hierarchical recurrent neural network.

Science.gov (United States)

Kordmahalleh, Mina Moradi; Sefidmazgi, Mohammad Gorji; Harrison, Scott H; Homaifar, Abdollah

2017-01-01

The modeling of genetic interactions within a cell is crucial for a basic understanding of physiology and for applied areas such as drug design. Interactions in gene regulatory networks (GRNs) include effects of transcription factors, repressors, small metabolites, and microRNA species. In addition, the effects of regulatory interactions are not always simultaneous, but can occur after a finite time delay, or as a combined outcome of simultaneous and time delayed interactions. Powerful biotechnologies have been rapidly and successfully measuring levels of genetic expression to illuminate different states of biological systems. This has led to an ensuing challenge to improve the identification of specific regulatory mechanisms through regulatory network reconstructions. Solutions to this challenge will ultimately help to spur forward efforts based on the usage of regulatory network reconstructions in systems biology applications. We have developed a hierarchical recurrent neural network (HRNN) that identifies time-delayed gene interactions using time-course data. A customized genetic algorithm (GA) was used to optimize hierarchical connectivity of regulatory genes and a target gene. The proposed design provides a non-fully connected network with the flexibility of using recurrent connections inside the network. These features and the non-linearity of the HRNN facilitate the process of identifying temporal patterns of a GRN. Our HRNN method was implemented with the Python language. It was first evaluated on simulated data representing linear and nonlinear time-delayed gene-gene interaction models across a range of network sizes and variances of noise. We then further demonstrated the capability of our method in reconstructing GRNs of the Saccharomyces cerevisiae synthetic network for in vivo benchmarking of reverse-engineering and modeling approaches (IRMA). We compared the performance of our method to TD-ARACNE, HCC-CLINDE, TSNI and ebdbNet across different network

Issues in the use of neural networks in information retrieval

CERN Document Server

Iatan, Iuliana F

2017-01-01

This book highlights the ability of neural networks (NNs) to be excellent pattern matchers and their importance in information retrieval (IR), which is based on index term matching. The book defines a new NN-based method for learning image similarity and describes how to use fuzzy Gaussian neural networks to predict personality. It introduces the fuzzy Clifford Gaussian network, and two concurrent neural models: (1) concurrent fuzzy nonlinear perceptron modules, and (2) concurrent fuzzy Gaussian neural network modules. Furthermore, it explains the design of a new model of fuzzy nonlinear perceptron based on alpha level sets and describes a recurrent fuzzy neural network model with a learning algorithm based on the improved particle swarm optimization method.

Biologically Inspired Modular Neural Control for a Leg-Wheel Hybrid Robot

DEFF Research Database (Denmark)

Manoonpong, Poramate; Wörgötter, Florentin; Laksanacharoen, Pudit

2014-01-01

In this article we present modular neural control for a leg-wheel hybrid robot consisting of three legs with omnidirectional wheels. This neural control has four main modules having their functional origin in biological neural systems. A minimal recurrent control (MRC) module is for sensory signal...... processing and state memorization. Its outputs drive two front wheels while the rear wheel is controlled through a velocity regulating network (VRN) module. In parallel, a neural oscillator network module serves as a central pattern generator (CPG) controls leg movements for sidestepping. Stepping directions...... or they can serve as useful modules for other module-based neural control applications....

Recurrent Syncope due to Esophageal Squamous Cell Carcinoma

Directory of Open Access Journals (Sweden)

A. Casini

2011-09-01

Full Text Available Syncope is caused by a wide variety of disorders. Recurrent syncope as a complication of malignancy is uncommon and may be difficult to diagnose and to treat. Primary neck carcinoma or metastases spreading in parapharyngeal and carotid spaces can involve the internal carotid artery and cause neurally mediated syncope with a clinical presentation like carotid sinus syndrome. We report the case of a 76-year-old man who suffered from recurrent syncope due to invasion of the right carotid sinus by metastases of a carcinoma of the esophagus, successfully treated by radiotherapy. In such cases, surgery, chemotherapy or radiotherapy can be performed. Because syncope may be an early sign of neck or cervical cancer, the diagnostic approach of syncope in patients with a past history of cancer should include the possibility of neck tumor recurrence or metastasis and an oncologic workout should be considered.

Real-Time Inverse Optimal Neural Control for Image Based Visual Servoing with Nonholonomic Mobile Robots

Directory of Open Access Journals (Sweden)

Carlos López-Franco

2015-01-01

Full Text Available We present an inverse optimal neural controller for a nonholonomic mobile robot with parameter uncertainties and unknown external disturbances. The neural controller is based on a discrete-time recurrent high order neural network (RHONN trained with an extended Kalman filter. The reference velocities for the neural controller are obtained with a visual sensor. The effectiveness of the proposed approach is tested by simulations and real-time experiments.

Single-Cell Transcriptomics and Fate Mapping of Ependymal Cells Reveals an Absence of Neural Stem Cell Function.

Science.gov (United States)

Shah, Prajay T; Stratton, Jo A; Stykel, Morgan Gail; Abbasi, Sepideh; Sharma, Sandeep; Mayr, Kyle A; Koblinger, Kathrin; Whelan, Patrick J; Biernaskie, Jeff

2018-05-03

Ependymal cells are multi-ciliated cells that form the brain's ventricular epithelium and a niche for neural stem cells (NSCs) in the ventricular-subventricular zone (V-SVZ). In addition, ependymal cells are suggested to be latent NSCs with a capacity to acquire neurogenic function. This remains highly controversial due to a lack of prospective in vivo labeling techniques that can effectively distinguish ependymal cells from neighboring V-SVZ NSCs. We describe a transgenic system that allows for targeted labeling of ependymal cells within the V-SVZ. Single-cell RNA-seq revealed that ependymal cells are enriched for cilia-related genes and share several stem-cell-associated genes with neural stem or progenitors. Under in vivo and in vitro neural-stem- or progenitor-stimulating environments, ependymal cells failed to demonstrate any suggestion of latent neural-stem-cell function. These findings suggest remarkable stability of ependymal cell function and provide fundamental insights into the molecular signature of the V-SVZ niche. Copyright © 2018 Elsevier Inc. All rights reserved.

arXiv The prototype of the HL-LHC magnets monitoring system based on Recurrent Neural Networks and adaptive quantization

CERN Document Server

Wielgosz, Maciej; Skoczeń, Andrzej

This paper focuses on an examination of an applicability of Recurrent Neural Network models for detecting anomalous behavior of the CERN superconducting magnets. In order to conduct the experiments, the authors designed and implemented an adaptive signal quantization algorithm and a custom GRU-based detector and developed a method for the detector parameters selection. Three different datasets were used for testing the detector. Two artificially generated datasets were used to assess the raw performance of the system whereas the 231 MB dataset composed of the signals acquired from HiLumi magnets was intended for real-life experiments and model training. Several different setups of the developed anomaly detection system were evaluated and compared with state-of-the-art OC-SVM reference model operating on the same data. The OC-SVM model was equipped with a rich set of feature extractors accounting for a range of the input signal properties. It was determined in the course of the experiments that the detector, a...

Association of the IL4R single-nucleotide polymorphism I50V with recurrent spontaneous abortion (RSA).

Science.gov (United States)

Tavasolian, Fataneh; Abdollahi, Elham; Samadi, Morteza

2014-07-01

Recurrent spontaneous abortion (RSA) is defined as three or more consecutive abortions before the 20th week of gestation. There is increasing evidence to support an immunological mechanism for the occurrence of RSA. The purpose of our study was to examine whether single-nucleotide polymorphisms (SNPs) of the interleukin-4 receptor gene IL4R influence susceptibility to, recurrent spontaneous abortion. This is a case-control study. We recruited 200 patients with RSA (case group) using established diagnostic criteria and 200, normal individuals (control group) at the fertility and infertility center in Yazd city and Isfahan city during 2012 to 2013. We screened the I50V variant in IL-4R in patients and controls by PCR-RFLF method, and we performed an association analysis between I50V variant and RSA.the data was analyzed by spss 16 software using Chi-square test. No differences in the genotype and allele frequencies of the I50V SNPs were identified between patients with RSA and healthy controls. The frequency of SNP in IL-4 receptor (I50V) in patients with recurrent spontaneous abortion did not differ significantly compared with the control group. Analysis of IL4R SNP haplotypes or complex alleles suggested no dominant protection in patients with RSA.

Beneficial role of noise in artificial neural networks

International Nuclear Information System (INIS)

Monterola, Christopher; Saloma, Caesar; Zapotocky, Martin

2008-01-01

We demonstrate enhancement of neural networks efficacy to recognize frequency encoded signals and/or to categorize spatial patterns of neural activity as a result of noise addition. For temporal information recovery, noise directly added to the receiving neurons allow instantaneous improvement of signal-to-noise ratio [Monterola and Saloma, Phys. Rev. Lett. 2002]. For spatial patterns however, recurrence is necessary to extend and homogenize the operating range of a feed-forward neural network [Monterola and Zapotocky, Phys. Rev. E 2005]. Finally, using the size of the basin of attraction of the networks learned patterns (dynamical fixed points), a procedure for estimating the optimal noise is demonstrated

Persistent and recurrent hyperparathyroidism.

Science.gov (United States)

Guerin, Carole; Paladino, Nunzia Cinzia; Lowery, Aoife; Castinetti, Fréderic; Taieb, David; Sebag, Fréderic

2017-06-01

Despite remarkable progress in imaging modalities and surgical management, persistence or recurrence of primary hyperparathyroidism (PHPT) still occurs in 2.5-5% of cases of PHPT. The aim of this review is to expose the management of persistent and recurrent hyperparathyroidism. A literature search was performed on MEDLINE using the search terms "recurrent" or "persistent" and "hyperparathyroidism" within the past 10 years. We also searched the reference lists of articles identified by this search strategy and selected those we judged relevant. Before considering reoperation, the surgeon must confirm the diagnosis of PHPT. Then, the patient must be evaluated with new imaging modalities. A single adenoma is found in 68% of cases, multiglandular disease in 28%, and parathyroid carcinoma in 3%. Others causes (<1%) include parathyromatosis and graft recurrence. The surgeon must balance the benefits against the risks of a reoperation (permanent hypocalcemia and recurrent laryngeal nerve palsy). If surgery is necessary, a focused approach can be considered in cases of significant imaging foci, but in the case of multiglandular disease, a bilateral neck exploration could be necessary. Patients with multiple endocrine neoplasia syndromes are at high risk of recurrence and should be managed regarding their hereditary pathology. The cure rate of persistent-PHPT or recurrent-PHPT in expert centers is estimated from 93 to 97%. After confirming the diagnosis of PHPT, patients with persistent-PHPT and recurrent-PHPT should be managed in an expert center with all dedicated competencies.

Tuning Neural Phase Entrainment to Speech.

Science.gov (United States)

Falk, Simone; Lanzilotti, Cosima; Schön, Daniele

2017-08-01

Musical rhythm positively impacts on subsequent speech processing. However, the neural mechanisms underlying this phenomenon are so far unclear. We investigated whether carryover effects from a preceding musical cue to a speech stimulus result from a continuation of neural phase entrainment to periodicities that are present in both music and speech. Participants listened and memorized French metrical sentences that contained (quasi-)periodic recurrences of accents and syllables. Speech stimuli were preceded by a rhythmically regular or irregular musical cue. Our results show that the presence of a regular cue modulates neural response as estimated by EEG power spectral density, intertrial coherence, and source analyses at critical frequencies during speech processing compared with the irregular condition. Importantly, intertrial coherences for regular cues were indicative of the participants' success in memorizing the subsequent speech stimuli. These findings underscore the highly adaptive nature of neural phase entrainment across fundamentally different auditory stimuli. They also support current models of neural phase entrainment as a tool of predictive timing and attentional selection across cognitive domains.

Natural Language Video Description using Deep Recurrent Neural Networks

Science.gov (United States)

2015-11-23

ht = f (Wxhxt + Whhht−1) (2.1) zt = g(Wzhht) (2.2) where f and g are element-wise non-linear functions such as a sigmoid or hyperbolic tan - gent, xt...space. arXiv preprint arXiv:1301.3781, 2013. 22 [68] Volodymyr Mnih, Nicolas Heess, Alex Graves, et al. Recurrent models of visual attention. In...2010. 2 36 Bibliography [107] Li Yao, Atousa Torabi, Kyunghyun Cho, Nicolas Ballas, Christopher Pal, Hugo Larochelle, and Aaron Courville. Describing

On the identification of instabilities with neural networks on JET

International Nuclear Information System (INIS)

Murari, A.; Arena, P.; Buscarino, A.; Fortuna, L.; Iachello, M.

2013-01-01

JET plasmas are affected by various instabilities, which can be particularly dangerous in high performance discharges. An identification method, based on the use of advanced neural networks, called Recurrent Neural Networks (RNNs), has been applied to ELMs. The potential of the recurrent networks to identify the dynamics of the instabilities has been first tested using synthetic data. The networks have then been applied to JET experimental signals. An appropriate selection of the networks topology allows identifying quite well the time evolution of the edge temperature and of the magnetic fields, considered the best indicators of the ELMs. A quite limited number of periodic oscillations are used to train the networks, which then manage to follow quite well the dynamics of the instabilities, in a recurrent configuration on one of the inputs. The time evolution of the aforementioned signals, also during intervals not used in the training and never seen by the networks, are properly reproduced. A careful analysis of the various terms in the RNNs has the potential to give clear indications about the nature of these instabilities and their dynamical behaviour

Cytoreductive surgery and hyperthermic intraperitoneal chemotherapy for the treatment of advanced epithelial and recurrent ovarian carcinoma: a single center experience.

Science.gov (United States)

Pavlov, Maja J; Ceranic, Miljan S; Latincic, Stojan M; Sabljak, Predrag V; Kecmanovic, Dragutin M; Sugarbaker, Paul H

2017-09-07

With standard treatment of epithelial ovarian cancer (EOC), prognosis is very poor. The aim of this study is to show early and late results in patients who underwent cytoreductive surgery and intraperitoneal chemotherapy. This was a retrospective single centre study. All patients with advanced and recurrent ovarian cancer treated with cytoreductive surgery and hyperthermic intraperitoneal chemotherapy (HIPEC) or modified early postoperative intraperitoneal chemotherapy (EPIC) were included in the study. In the period 1995-2014, 116 patients were treated, 55 with primary EOC and 61 with recurrent EOC. The mean age was 59 years (26-74). Statistically, median survival time was significantly longer in the group with primary advanced cancer of the ovary (41.3 months) compared to relapsed ovarian cancer (27.3 months). Survival for the primary EOC was 65 and 24% at 3 and 5 years, respectively. Survival for recurrent EOC was 33 and 16% at 3 and 5 years, respectively. Mortality was 1/116 (0.8%). Morbidity was 11/116 (9.5%). Peritoneal cancer index (PCI) was ≤20 in 59 (51%) patients and statistically, their average survival was significantly longer than in the group of 57 (49%) patients with PCI >20 (p = 0.014). In advanced or recurrent EOC, a curative therapeutic approach was pursued that combined optimal cytoreductive surgery and intraperitoneal chemotherapy. PCI and timing of the intervention (primary or recurrent) were the strongest independent prognostic factors.

Empirical model development and validation with dynamic learning in the recurrent multilayer perception

International Nuclear Information System (INIS)

Parlos, A.G.; Chong, K.T.; Atiya, A.F.

1994-01-01

A nonlinear multivariable empirical model is developed for a U-tube steam generator using the recurrent multilayer perceptron network as the underlying model structure. The recurrent multilayer perceptron is a dynamic neural network, very effective in the input-output modeling of complex process systems. A dynamic gradient descent learning algorithm is used to train the recurrent multilayer perceptron, resulting in an order of magnitude improvement in convergence speed over static learning algorithms. In developing the U-tube steam generator empirical model, the effects of actuator, process,and sensor noise on the training and testing sets are investigated. Learning and prediction both appear very effective, despite the presence of training and testing set noise, respectively. The recurrent multilayer perceptron appears to learn the deterministic part of a stochastic training set, and it predicts approximately a moving average response. Extensive model validation studies indicate that the empirical model can substantially generalize (extrapolate), though online learning becomes necessary for tracking transients significantly different than the ones included in the training set and slowly varying U-tube steam generator dynamics. In view of the satisfactory modeling accuracy and the associated short development time, neural networks based empirical models in some cases appear to provide a serious alternative to first principles models. Caution, however, must be exercised because extensive on-line validation of these models is still warranted

Modelling the phonotactic structure of natural language words with simple recurrent networks

NARCIS (Netherlands)

Stoianov, [No Value; Nerbonne, J; Bouma, H; Coppen, PA; vanHalteren, H; Teunissen, L

1998-01-01

Simple Recurrent Networks (SRN) are Neural Network (connectionist) models able to process natural language. Phonotactics concerns the order of symbols in words. We continued an earlier unsuccessful trial to model the phonotactics of Dutch words with SRNs. In order to overcome the previously reported

Adding bevacizumab to single agent chemotherapy for the treatment of platinum-resistant recurrent ovarian cancer: A cost effectiveness analysis of the AURELIA trial.

Science.gov (United States)

Wysham, Weiya Z; Schaffer, Elisabeth M; Coles, Theresa; Roque, Dario R; Wheeler, Stephanie B; Kim, Kenneth H

2017-05-01

AURELIA, a randomized phase III trial of adding bevacizumab (B) to single agent chemotherapy (CT) for the treatment of platinum-resistant recurrent ovarian cancer, demonstrated improved progression free survival (PFS) in the B+CT arm compared to CT alone. We aimed to evaluate the cost effectiveness of adding B to CT in the treatment of platinum-resistant recurrent ovarian cancer. A decision tree model was constructed to evaluate the cost effectiveness of adding bevacizumab (B) to single agent chemotherapy (CT) based on the arms of the AURELIA trial. Costs, quality-adjusted life years (QALYs), and progression free survival (PFS) were modeled over fifteen months. Model inputs were extracted from published literature and public sources. Incremental cost effectiveness ratios (ICERs) per QALY gained and ICERs per progression free life year saved (PF-LYS) were calculated. One-way sensitivity analyses were performed to evaluate the robustness of results. The ICER associated with B+CT is $410,455 per QALY gained and $217,080 per PF-LYS. At a willingness to pay (WTP) threshold of $50,000/QALY, adding B to single agent CT is not cost effective for this patient population. Even at a WTP threshold of $100,000/QALY, B+CT is not cost effective. These findings are robust to sensitivity analyses. Despite gains in QALY and PFS, the addition of B to single agent CT for treatment of platinum-resistant recurrent ovarian cancer is not cost effective. Benefits, risks, and costs associated with treatment should be taken into consideration when prescribing chemotherapy for this patient population. Copyright © 2017 Elsevier Inc. All rights reserved.

Cognitive Processes Underlying Nonnative Speech Production: The Significance of Recurrent Sequences.

Science.gov (United States)

Oppenheim, Nancy

This study was designed to identify whether advanced nonnative speakers of English rely on recurrent sequences to produce fluent speech in conformance with neural network theories and symbolic network theories; participants were 6 advanced, speaking and listening university students, aged 18-37 years (their native countries being Korea, Japan,…

Recurrent neural networks with specialized word embeddings for health-domain named-entity recognition.

Science.gov (United States)

Jauregi Unanue, Iñigo; Zare Borzeshi, Ehsan; Piccardi, Massimo

2017-12-01

Previous state-of-the-art systems on Drug Name Recognition (DNR) and Clinical Concept Extraction (CCE) have focused on a combination of text "feature engineering" and conventional machine learning algorithms such as conditional random fields and support vector machines. However, developing good features is inherently heavily time-consuming. Conversely, more modern machine learning approaches such as recurrent neural networks (RNNs) have proved capable of automatically learning effective features from either random assignments or automated word "embeddings". (i) To create a highly accurate DNR and CCE system that avoids conventional, time-consuming feature engineering. (ii) To create richer, more specialized word embeddings by using health domain datasets such as MIMIC-III. (iii) To evaluate our systems over three contemporary datasets. Two deep learning methods, namely the Bidirectional LSTM and the Bidirectional LSTM-CRF, are evaluated. A CRF model is set as the baseline to compare the deep learning systems to a traditional machine learning approach. The same features are used for all the models. We have obtained the best results with the Bidirectional LSTM-CRF model, which has outperformed all previously proposed systems. The specialized embeddings have helped to cover unusual words in DrugBank and MedLine, but not in the i2b2/VA dataset. We present a state-of-the-art system for DNR and CCE. Automated word embeddings has allowed us to avoid costly feature engineering and achieve higher accuracy. Nevertheless, the embeddings need to be retrained over datasets that are adequate for the domain, in order to adequately cover the domain-specific vocabulary. Copyright © 2017 Elsevier Inc. All rights reserved.

BRITS: Bidirectional Recurrent Imputation for Time Series

OpenAIRE

Cao, Wei; Wang, Dong; Li, Jian; Zhou, Hao; Li, Lei; Li, Yitan

2018-01-01

Time series are widely used as signals in many classification/regression tasks. It is ubiquitous that time series contains many missing values. Given multiple correlated time series data, how to fill in missing values and to predict their class labels? Existing imputation methods often impose strong assumptions of the underlying data generating process, such as linear dynamics in the state space. In this paper, we propose BRITS, a novel method based on recurrent neural networks for missing va...

Different risk-increasing drugs in recurrent versus single fallers: are recurrent fallers a distinct population?

NARCIS (Netherlands)

Askari, Marjan; Eslami, Saied; Scheffer, Alice C.; Medlock, Stephanie; de Rooij, Sophia E.; van der Velde, Nathalie; Abu-Hanna, Ameen

2013-01-01

Polypharmacy, and specifically the use of multiple fall-risk-increasing drugs (FRID), have been associated with increased risk of falling in older age. However, it is not yet clear whether the known set of FRIDs can be extrapolated to recurrent fallers, since they form a distinct group of more

Electrocardiogram (ECG Signal Modeling and Noise Reduction Using Hopfield Neural Networks

Directory of Open Access Journals (Sweden)

F. Bagheri

2013-02-01

Full Text Available The Electrocardiogram (ECG signal is one of the diagnosing approaches to detect heart disease. In this study the Hopfield Neural Network (HNN is applied and proposed for ECG signal modeling and noise reduction. The Hopfield Neural Network (HNN is a recurrent neural network that stores the information in a dynamic stable pattern. This algorithm retrieves a pattern stored in memory in response to the presentation of an incomplete or noisy version of that pattern. Computer simulation results show that this method can successfully model the ECG signal and remove high-frequency noise.

Attractor neural networks with resource-efficient synaptic connectivity

Science.gov (United States)

Pehlevan, Cengiz; Sengupta, Anirvan

Memories are thought to be stored in the attractor states of recurrent neural networks. Here we explore how resource constraints interplay with memory storage function to shape synaptic connectivity of attractor networks. We propose that given a set of memories, in the form of population activity patterns, the neural circuit choses a synaptic connectivity configuration that minimizes a resource usage cost. We argue that the total synaptic weight (l1-norm) in the network measures the resource cost because synaptic weight is correlated with synaptic volume, which is a limited resource, and is proportional to neurotransmitter release and post-synaptic current, both of which cost energy. Using numerical simulations and replica theory, we characterize optimal connectivity profiles in resource-efficient attractor networks. Our theory explains several experimental observations on cortical connectivity profiles, 1) connectivity is sparse, because synapses are costly, 2) bidirectional connections are overrepresented and 3) are stronger, because attractor states need strong recurrence.

Antiangiogenic agents in the treatment of recurrent or newly diagnosed glioblastoma: Analysis of single-agent and combined modality approaches

International Nuclear Information System (INIS)

Beal, Kathryn; Abrey, Lauren E; Gutin, Philip H

2011-01-01

Surgical resection followed by radiotherapy and temozolomide in newly diagnosed glioblastoma can prolong survival, but it is not curative. For patients with disease progression after frontline therapy, there is no standard of care, although further surgery, chemotherapy, and radiotherapy may be used. Antiangiogenic therapies may be appropriate for treating glioblastomas because angiogenesis is critical to tumor growth. In a large, noncomparative phase II trial, bevacizumab was evaluated alone and with irinotecan in patients with recurrent glioblastoma; combination treatment was associated with an estimated 6-month progression-free survival (PFS) rate of 50.3%, a median overall survival of 8.9 months, and a response rate of 37.8%. Single-agent bevacizumab also exceeded the predetermined threshold of activity for salvage chemotherapy (6-month PFS rate, 15%), achieving a 6-month PFS rate of 42.6% (p < 0.0001). On the basis of these results and those from another phase II trial, the US Food and Drug Administration granted accelerated approval of single-agent bevacizumab for the treatment of glioblastoma that has progressed following prior therapy. Potential antiangiogenic agents-such as cilengitide and XL184-also show evidence of single-agent activity in recurrent glioblastoma. Moreover, the use of antiangiogenic agents with radiation at disease progression may improve the therapeutic ratio of single-modality approaches. Overall, these agents appear to be well tolerated, with adverse event profiles similar to those reported in studies of other solid tumors. Further research is needed to determine the role of antiangiogenic therapy in frontline treatment and to identify the optimal schedule and partnering agents for use in combination therapy

Conversion of Human Fibroblasts to Stably Self-Renewing Neural Stem Cells with a Single Zinc-Finger Transcription Factor

Directory of Open Access Journals (Sweden)

Ebrahim Shahbazi

2016-04-01

Full Text Available Direct conversion of somatic cells into neural stem cells (NSCs by defined factors holds great promise for mechanistic studies, drug screening, and potential cell therapies for different neurodegenerative diseases. Here, we report that a single zinc-finger transcription factor, Zfp521, is sufficient for direct conversion of human fibroblasts into long-term self-renewable and multipotent NSCs. In vitro, Zfp521-induced NSCs maintained their characteristics in the absence of exogenous factor expression and exhibited morphological, molecular, developmental, and functional properties that were similar to control NSCs. In addition, the single-seeded induced NSCs were able to form NSC colonies with efficiency comparable with control NSCs and expressed NSC markers. The converted cells were capable of surviving, migrating, and attaining neural phenotypes after transplantation into neonatal mouse and adult rat brains, without forming tumors. Moreover, the Zfp521-induced NSCs predominantly expressed rostral genes. Our results suggest a facilitated approach for establishing human NSCs through Zfp521-driven conversion of fibroblasts.

Persistent activity in a recurrent circuit underlies courtship memory in Drosophila

Science.gov (United States)

Zhao, Xiaoliang; Lenek, Daniela; Dag, Ugur; Dickson, Barry J

2018-01-01

Recurrent connections are thought to be a common feature of the neural circuits that encode memories, but how memories are laid down in such circuits is not fully understood. Here we present evidence that courtship memory in Drosophila relies on the recurrent circuit between mushroom body gamma (MBγ), M6 output, and aSP13 dopaminergic neurons. We demonstrate persistent neuronal activity of aSP13 neurons and show that it transiently potentiates synaptic transmission from MBγ>M6 neurons. M6 neurons in turn provide input to aSP13 neurons, prolonging potentiation of MBγ>M6 synapses over time periods that match short-term memory. These data support a model in which persistent aSP13 activity within a recurrent circuit lays the foundation for a short-term memory. PMID:29322941

Application of neural networks to waste site screening

International Nuclear Information System (INIS)

Dabiri, A.E.; Garrett, M.; Kraft, T.; Hilton, J.; VanHammersveld, M.

1993-02-01

Waste site screening requires knowledge of the actual concentrations of hazardous materials and rates of flow around and below the site with time. The present approach consists primarily of drilling boreholes near contaminated sites and chemically analyzing the extracted physical samples and processing the data. This is expensive and time consuming. The feasibility of using neural network techniques to reduce the cost of waste site screening was investigated. Two neural network techniques, gradient descent back propagation and fully recurrent back propagation were utilized. The networks were trained with data received from Westinghouse Hanford Corporation. The results indicate that the network trained with the fully recurrent technique shows satisfactory generalization capability. The predicted results are close to the results obtained from a mathematical flow prediction model. It is possible to develop a new tool to predict the waste plume, thus substantially reducing the number of the bore sites and samplings. There are a variety of applications for this technique in environmental site screening and remediation. One of the obvious applications would be for optimum well siting. A neural network trained from the existing sampling data could be utilized to decide where would be the best position for the next bore site. Other applications are discussed in the report

Intelligent control of PV system on the basis of the fuzzy recurrent neuronet*

Science.gov (United States)

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

2016-04-01

This paper presents the fuzzy recurrent neuronet for PV system’s control. Based on the PV system’s state, the fuzzy recurrent neural net tracks the maximum power point under random perturbations. The validity and advantages of the proposed intelligent control of PV system are demonstrated by numerical simulations. The simulation results show that the proposed intelligent control of PV system achieves real-time control speed and competitive performance, as compared to a classical control scheme on the basis of the perturbation & observation algorithm.

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

Science.gov (United States)

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.

Word embeddings and recurrent neural networks based on Long-Short Term Memory nodes in supervised biomedical word sense disambiguation.

Science.gov (United States)

Jimeno Yepes, Antonio

2017-09-01

Word sense disambiguation helps identifying the proper sense of ambiguous words in text. With large terminologies such as the UMLS Metathesaurus ambiguities appear and highly effective disambiguation methods are required. Supervised learning algorithm methods are used as one of the approaches to perform disambiguation. Features extracted from the context of an ambiguous word are used to identify the proper sense of such a word. The type of features have an impact on machine learning methods, thus affect disambiguation performance. In this work, we have evaluated several types of features derived from the context of the ambiguous word and we have explored as well more global features derived from MEDLINE using word embeddings. Results show that word embeddings improve the performance of more traditional features and allow as well using recurrent neural network classifiers based on Long-Short Term Memory (LSTM) nodes. The combination of unigrams and word embeddings with an SVM sets a new state of the art performance with a macro accuracy of 95.97 in the MSH WSD data set. Copyright © 2017 Elsevier Inc. All rights reserved.

Optimization Study of Hydrogen Gas Adsorption on Zig-zag Single-walled Carbon Nanotubes: The Artificial Neural Network Analysis

Science.gov (United States)

Nasruddin; Lestari, M.; Supriyadi; Sholahudin

2018-03-01

The use of hydrogen gas in fuel cell technology has a huge opportunity to be applied in upcoming vehicle technology. One of the most important problems in fuel cell technology is the hydrogen storage. The adsorption of hydrogen in carbon-based materials attracts a lot of attention because of its reliability. This study investigated the adsorption of hydrogen gas in Single-walled Carbon Nano Tubes (SWCNT) with chilarity of (0, 12), (0, 15), and (0, 18) to find the optimum chilarity. Artificial Neural Networks (ANN) can be used to predict the hydrogen storage capacity at different pressure and temperature conditions appropriately, using simulated series of data. The Artificial Neural Network is modeled as a predictor of the hydrogen adsorption capacity which provides solutions to some deficiencies in molecular dynamics (MD) simulations. In a previous study, ANN configurations have been developed for 77k, 233k, and 298k temperatures in hydrogen gas storage. To prepare this prediction, ANN is modeled to find out the configurations that exist in the set of training and validation of specified data selection, the distance between data, and the number of neurons that produce the smallest error. This configuration is needed to make an accurate artificial neural network. The configuration of neural network was then applied to this research. The neural network analysis results show that the best configuration of artificial neural network in hydrogen storage is at 233K temperature i.e. on SWCNT with chilarity of (0.12).

Training trajectories by continuous recurrent multilayer networks.

Science.gov (United States)

Leistritz, L; Galicki, M; Witte, H; Kochs, E

2002-01-01

This paper addresses the problem of training trajectories by means of continuous recurrent neural networks whose feedforward parts are multilayer perceptrons. Such networks can approximate a general nonlinear dynamic system with arbitrary accuracy. The learning process is transformed into an optimal control framework where the weights are the controls to be determined. A training algorithm based upon a variational formulation of Pontryagin's maximum principle is proposed for such networks. Computer examples demonstrating the efficiency of the given approach are also presented.

Recurrent loss of specific introns during angiosperm evolution.

Directory of Open Access Journals (Sweden)

Hao Wang

2014-12-01

Full Text Available Numerous instances of presence/absence variations for introns have been documented in eukaryotes, and some cases of recurrent loss of the same intron have been suggested. However, there has been no comprehensive or phylogenetically deep analysis of recurrent intron loss. Of 883 cases of intron presence/absence variation that we detected in five sequenced grass genomes, 93 were confirmed as recurrent losses and the rest could be explained by single losses (652 or single gains (118. No case of recurrent intron gain was observed. Deep phylogenetic analysis often indicated that apparent intron gains were actually numerous independent losses of the same intron. Recurrent loss exhibited extreme non-randomness, in that some introns were removed independently in many lineages. The two larger genomes, maize and sorghum, were found to have a higher rate of both recurrent loss and overall loss and/or gain than foxtail millet, rice or Brachypodium. Adjacent introns and small introns were found to be preferentially lost. Intron loss genes exhibited a high frequency of germ line or early embryogenesis expression. In addition, flanking exon A+T-richness and intron TG/CG ratios were higher in retained introns. This last result suggests that epigenetic status, as evidenced by a loss of methylated CG dinucleotides, may play a role in the process of intron loss. This study provides the first comprehensive analysis of recurrent intron loss, makes a series of novel findings on the patterns of recurrent intron loss during the evolution of the grass family, and provides insight into the molecular mechanism(s underlying intron loss.

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

Science.gov (United States)

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.

Recurrent Artificial Neural Networks and Finite State Natural Language Processing.

Science.gov (United States)

Moisl, Hermann

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

Recurrent meningitis--a review of current literature.

Science.gov (United States)

Janocha-Litwin, Justyna; Simon, Krzysztof

2013-01-01

The paper discusses epidemiology, aetiology and the most important predisposing factors associated with recurrent meningitis, as well as the possibilities to prevent this particularly challenging clinical problem. The frequency of recurrent meningitis is estimated to be 2-9%. However, the case fatality is lower compared to a single episode of meningitis. The main causes of recurrent meningitis are considered to be: head injury, congenital or acquired (post-traumatic or post-surgical) cranial or spinal defects, chronic intracranial inflammation, complement system dysfunction, as well as congenital and acquired humoral or cellular immunodeficiency.

A Hybrid Fuzzy Time Series Approach Based on Fuzzy Clustering and Artificial Neural Network with Single Multiplicative Neuron Model

Directory of Open Access Journals (Sweden)

Ozge Cagcag Yolcu

2013-01-01

Full Text Available Particularly in recent years, artificial intelligence optimization techniques have been used to make fuzzy time series approaches more systematic and improve forecasting performance. Besides, some fuzzy clustering methods and artificial neural networks with different structures are used in the fuzzification of observations and determination of fuzzy relationships, respectively. In approaches considering the membership values, the membership values are determined subjectively or fuzzy outputs of the system are obtained by considering that there is a relation between membership values in identification of relation. This necessitates defuzzification step and increases the model error. In this study, membership values were obtained more systematically by using Gustafson-Kessel fuzzy clustering technique. The use of artificial neural network with single multiplicative neuron model in identification of fuzzy relation eliminated the architecture selection problem as well as the necessity for defuzzification step by constituting target values from real observations of time series. The training of artificial neural network with single multiplicative neuron model which is used for identification of fuzzy relation step is carried out with particle swarm optimization. The proposed method is implemented using various time series and the results are compared with those of previous studies to demonstrate the performance of the proposed method.

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

Science.gov (United States)

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

Memory replay in balanced recurrent networks.

Directory of Open Access Journals (Sweden)

Nikolay Chenkov

2017-01-01

Full Text Available Complex patterns of neural activity appear during up-states in the neocortex and sharp waves in the hippocampus, including sequences that resemble those during prior behavioral experience. The mechanisms underlying this replay are not well understood. How can small synaptic footprints engraved by experience control large-scale network activity during memory retrieval and consolidation? We hypothesize that sparse and weak synaptic connectivity between Hebbian assemblies are boosted by pre-existing recurrent connectivity within them. To investigate this idea, we connect sequences of assemblies in randomly connected spiking neuronal networks with a balance of excitation and inhibition. Simulations and analytical calculations show that recurrent connections within assemblies allow for a fast amplification of signals that indeed reduces the required number of inter-assembly connections. Replay can be evoked by small sensory-like cues or emerge spontaneously by activity fluctuations. Global-potentially neuromodulatory-alterations of neuronal excitability can switch between network states that favor retrieval and consolidation.

Composing Music with Grammar Argumented Neural Networks and Note-Level Encoding

OpenAIRE

Sun, Zheng; Liu, Jiaqi; Zhang, Zewang; Chen, Jingwen; Huo, Zhao; Lee, Ching Hua; Zhang, Xiao

2016-01-01

Creating aesthetically pleasing pieces of art, including music, has been a long-term goal for artificial intelligence research. Despite recent successes of long-short term memory (LSTM) recurrent neural networks (RNNs) in sequential learning, LSTM neural networks have not, by themselves, been able to generate natural-sounding music conforming to music theory. To transcend this inadequacy, we put forward a novel method for music composition that combines the LSTM with Grammars motivated by mus...

De-identification of clinical notes via recurrent neural network and conditional random field.

Science.gov (United States)

Liu, Zengjian; Tang, Buzhou; Wang, Xiaolong; Chen, Qingcai

2017-11-01

De-identification, identifying information from data, such as protected health information (PHI) present in clinical data, is a critical step to enable data to be shared or published. The 2016 Centers of Excellence in Genomic Science (CEGS) Neuropsychiatric Genome-scale and RDOC Individualized Domains (N-GRID) clinical natural language processing (NLP) challenge contains a de-identification track in de-identifying electronic medical records (EMRs) (i.e., track 1). The challenge organizers provide 1000 annotated mental health records for this track, 600 out of which are used as a training set and 400 as a test set. We develop a hybrid system for the de-identification task on the training set. Firstly, four individual subsystems, that is, a subsystem based on bidirectional LSTM (long-short term memory, a variant of recurrent neural network), a subsystem-based on bidirectional LSTM with features, a subsystem based on conditional random field (CRF) and a rule-based subsystem, are used to identify PHI instances. Then, an ensemble learning-based classifiers is deployed to combine all PHI instances predicted by above three machine learning-based subsystems. Finally, the results of the ensemble learning-based classifier and the rule-based subsystem are merged together. Experiments conducted on the official test set show that our system achieves the highest micro F1-scores of 93.07%, 91.43% and 95.23% under the "token", "strict" and "binary token" criteria respectively, ranking first in the 2016 CEGS N-GRID NLP challenge. In addition, on the dataset of 2014 i2b2 NLP challenge, our system achieves the highest micro F1-scores of 96.98%, 95.11% and 98.28% under the "token", "strict" and "binary token" criteria respectively, outperforming other state-of-the-art systems. All these experiments prove the effectiveness of our proposed method. Copyright © 2017. Published by Elsevier Inc.

Tracking Single Units in Chronic, Large Scale, Neural Recordings for Brain Machine Interface Applications

Directory of Open Access Journals (Sweden)

Ahmed eEleryan

2014-07-01

Full Text Available In the study of population coding in neurobiological systems, tracking unit identity may be critical to assess possible changes in the coding properties of neuronal constituents over prolonged periods of time. Ensuring unit stability is even more critical for reliable neural decoding of motor variables in intra-cortically controlled brain-machine interfaces (BMIs. Variability in intrinsic spike patterns, tuning characteristics, and single-unit identity over chronic use is a major challenge to maintaining this stability, requiring frequent daily calibration of neural decoders in BMI sessions by an experienced human operator. Here, we report on a unit-stability tracking algorithm that efficiently and autonomously identifies putative single-units that are stable across many sessions using a relatively short duration recording interval at the start of each session. The algorithm first builds a database of features extracted from units' average spike waveforms and firing patterns across many days of recording. It then uses these features to decide whether spike occurrences on the same channel on one day belong to the same unit recorded on another day or not. We assessed the overall performance of the algorithm for different choices of features and classifiers trained using human expert judgment, and quantified it as a function of accuracy and execution time. Overall, we found a trade-off between accuracy and execution time with increasing data volumes from chronically implanted rhesus macaques, with an average of 12 seconds processing time per channel at ~90% classification accuracy. Furthermore, 77% of the resulting putative single-units matched those tracked by human experts. These results demonstrate that over the span of a few months of recordings, automated unit tracking can be performed with high accuracy and used to streamline the calibration phase during BMI sessions.

Nonlinear adaptive inverse control via the unified model neural network

Science.gov (United States)

Jeng, Jin-Tsong; Lee, Tsu-Tian

1999-03-01

In this paper, we propose a new nonlinear adaptive inverse control via a unified model neural network. In order to overcome nonsystematic design and long training time in nonlinear adaptive inverse control, we propose the approximate transformable technique to obtain a Chebyshev Polynomials Based Unified Model (CPBUM) neural network for the feedforward/recurrent neural networks. It turns out that the proposed method can use less training time to get an inverse model. Finally, we apply this proposed method to control magnetic bearing system. The experimental results show that the proposed nonlinear adaptive inverse control architecture provides a greater flexibility and better performance in controlling magnetic bearing systems.

Personality predicts recurrence of late-life depression.

Science.gov (United States)

Steunenberg, Bas; Beekman, Aartjan T F; Deeg, Dorly J H; Kerkhof, Ad J F M

2010-06-01

To examine the association of personality with recurrence of depression in later life. A subsample of 91 subjects from the Longitudinal Aging Study Amsterdam (LASA; baseline sample size n=3107; aged > or = 55 years) depressed at baseline, who had recovered in the course of three years (first follow-up cycle) was identified. 41 (45%) respondents experienced a recurrence during the subsequent six years. The influences of personality and late life stress (demographic factors, health and social factors) on recurrence were investigated prospectively. Recurrence of depression was associated with a high level of neuroticism and low level of mastery, residual depressive symptoms at time of recovery, female gender, pain complaints and feelings of loneliness. In multivariable analysis entering all predictors significant in single variable analysis, residual depressive symptoms and lack of mastery remained significantly associated with recurrence. In predicting the recurrence of depression in later life, the direct effects of personality remain important and comparable in strength with other late life stressors related to recurrence. Copyright 2009 Elsevier B.V. All rights reserved.

Recurrent LDL-receptor mutation causes familial ...

African Journals Online (AJOL)

1995-05-05

May 5, 1995 ... 3. eaudet . New. Recurrent LDL-receptor mutation causes familial hypercholesterolaemia in ... amplification refractory mutation system (ARMS)" and single- strand conformation .... Location. Afrikaner. Mixed race. ApaLl.

Persistent activity in a recurrent circuit underlies courtship memory in Drosophila.

Science.gov (United States)

Zhao, Xiaoliang; Lenek, Daniela; Dag, Ugur; Dickson, Barry J; Keleman, Krystyna

2018-01-11

Recurrent connections are thought to be a common feature of the neural circuits that encode memories, but how memories are laid down in such circuits is not fully understood. Here we present evidence that courtship memory in Drosophila relies on the recurrent circuit between mushroom body gamma (MBγ), M6 output, and aSP13 dopaminergic neurons. We demonstrate persistent neuronal activity of aSP13 neurons and show that it transiently potentiates synaptic transmission from MBγ>M6 neurons. M6 neurons in turn provide input to aSP13 neurons, prolonging potentiation of MB γ >M6 synapses over time periods that match short-term memory. These data support a model in which persistent aSP13 activity within a recurrent circuit lays the foundation for a short-term memory. © 2018, Zhao et al.

Lifelong learning of human actions with deep neural network self-organization.

Science.gov (United States)

Parisi, German I; Tani, Jun; Weber, Cornelius; Wermter, Stefan

2017-12-01

Lifelong learning is fundamental in autonomous robotics for the acquisition and fine-tuning of knowledge through experience. However, conventional deep neural models for action recognition from videos do not account for lifelong learning but rather learn a batch of training data with a predefined number of action classes and samples. Thus, there is the need to develop learning systems with the ability to incrementally process available perceptual cues and to adapt their responses over time. We propose a self-organizing neural architecture for incrementally learning to classify human actions from video sequences. The architecture comprises growing self-organizing networks equipped with recurrent neurons for processing time-varying patterns. We use a set of hierarchically arranged recurrent networks for the unsupervised learning of action representations with increasingly large spatiotemporal receptive fields. Lifelong learning is achieved in terms of prediction-driven neural dynamics in which the growth and the adaptation of the recurrent networks are driven by their capability to reconstruct temporally ordered input sequences. Experimental results on a classification task using two action benchmark datasets show that our model is competitive with state-of-the-art methods for batch learning also when a significant number of sample labels are missing or corrupted during training sessions. Additional experiments show the ability of our model to adapt to non-stationary input avoiding catastrophic interference. Copyright © 2017 The Author(s). Published by Elsevier Ltd.. All rights reserved.

Stereotactic body radiotherapy for lung metastases as oligo-recurrence: a single institutional study.

Science.gov (United States)

Aoki, Masahiko; Hatayama, Yoshiomi; Kawaguchi, Hideo; Hirose, Katsumi; Sato, Mariko; Akimoto, Hiroyoshi; Miura, Hiroyuki; Ono, Shuichi; Takai, Yoshihiro

2016-01-01

The purpose of this study was to investigate clinical outcomes following stereotactic body radiotherapy (SBRT) for lung metastases as oligo-recurrence. From May 2003 to June 2014, records for 66 patients with 76 oligo-recurrences in the lungs treated with SBRT were retrospectively reviewed. Oligo-recurrence primary sites and patient numbers were as follows: lungs, 31; colorectal, 13; head and neck, 10; esophagus, 3; uterus, 3; and others, 6. The median SBRT dose was 50 Gy (range, 45-60 Gy) administered in a median of 5 (range, 5-9) fractions. All patients received SBRT, with no acute toxicity. Surviving patients had a median follow-up time of 36.5 months. The 3-year rates of local control, overall survival and disease-free survival were 90.6%, 76.0% and 53.7%, respectively. Longer disease-free interval from initial treatment to SBRT, and non-colorectal cancer were both associated with favorable outcomes. Disease progression after SBRT occurred in 31 patients, most with distant metastases (n = 24) [among whom, 87.5% (n = 21) had new lung metastases]. Among these 21 patients, 12 were judged as having a second oligo-recurrence. Additional SBRT was performed for these 12 patients, and all 12 tumors were controlled without disease progression. Three patients (4.5%) developed Grade 2 radiation pneumonitis. No other late adverse events of Grade ≥2 were identified. Thus, SBRT for oligo-recurrence achieved acceptable tumor control, with additional SBRT also effective for selected patients with a second oligo-recurrence after primary SBRT. © The Author 2015. Published by Oxford University Press on behalf of The Japan Radiation Research Society and Japanese Society for Radiation Oncology.

Neural Networks in Control Applications

DEFF Research Database (Denmark)

Sørensen, O.

are examined. The models are separated into three groups representing input/output descriptions as well as state space descriptions: - Models, where all in- and outputs are measurable (static networks). - Models, where some inputs are non-measurable (recurrent networks). - Models, where some in- and some...... outputs are non-measurable (recurrent networks with incomplete state information). The three groups are ordered in increasing complexity, and for each group it is shown how to solve the problems concerning training and application of the specific model type. Of particular interest are the model types...... Kalmann filter) representing state space description. The potentials of neural networks for control of non-linear processes are also examined, focusing on three different groups of control concepts, all considered as generalizations of known linear control concepts to handle also non-linear processes...

Spatiotemporal Dynamics and Reliable Computations in Recurrent Spiking Neural Networks

Science.gov (United States)

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.

Spatiotemporal Dynamics and Reliable Computations in Recurrent Spiking Neural Networks.

Science.gov (United States)

Pyle, Ryan; Rosenbaum, Robert

2017-01-06

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.

Nonlinearly Activated Neural Network for Solving Time-Varying Complex Sylvester Equation.

Science.gov (United States)

Li, Shuai; Li, Yangming

2013-10-28

The Sylvester equation is often encountered in mathematics and control theory. For the general time-invariant Sylvester equation problem, which is defined in the domain of complex numbers, the Bartels-Stewart algorithm and its extensions are effective and widely used with an O(n³) time complexity. When applied to solving the time-varying Sylvester equation, the computation burden increases intensively with the decrease of sampling period and cannot satisfy continuous realtime calculation requirements. For the special case of the general Sylvester equation problem defined in the domain of real numbers, gradient-based recurrent neural networks are able to solve the time-varying Sylvester equation in real time, but there always exists an estimation error while a recently proposed recurrent neural network by Zhang et al [this type of neural network is called Zhang neural network (ZNN)] converges to the solution ideally. The advancements in complex-valued neural networks cast light to extend the existing real-valued ZNN for solving the time-varying real-valued Sylvester equation to its counterpart in the domain of complex numbers. In this paper, a complex-valued ZNN for solving the complex-valued Sylvester equation problem is investigated and the global convergence of the neural network is proven with the proposed nonlinear complex-valued activation functions. Moreover, a special type of activation function with a core function, called sign-bi-power function, is proven to enable the ZNN to converge in finite time, which further enhances its advantage in online processing. In this case, the upper bound of the convergence time is also derived analytically. Simulations are performed to evaluate and compare the performance of the neural network with different parameters and activation functions. Both theoretical analysis and numerical simulations validate the effectiveness of the proposed method.

New BFA Method Based on Attractor Neural Network and Likelihood Maximization

Czech Academy of Sciences Publication Activity Database

Frolov, A. A.; Húsek, Dušan; Polyakov, P.Y.; Snášel, V.

2014-01-01

Roč. 132, 20 May (2014), s. 14-29 ISSN 0925-2312 Grant - others:GA MŠk(CZ) ED1.1.00/02.0070; GA MŠk(CZ) EE.2.3.20.0073 Program:ED Institutional support: RVO:67985807 Keywords : recurrent neural network * associative memory * Hebbian learning rule * neural network application * data mining * statistics * Boolean factor analysis * information gain * dimension reduction * likelihood-maximization * bars problem Subject RIV: IN - Informatics, Computer Science Impact factor: 2.083, year: 2014

Artificial neural networks applied to forecasting time series.

Science.gov (United States)

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

2011-04-01

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

MATLAB Simulation of Gradient-Based Neural Network for Online Matrix Inversion

Science.gov (United States)

Zhang, Yunong; Chen, Ke; Ma, Weimu; Li, Xiao-Dong

This paper investigates the simulation of a gradient-based recurrent neural network for online solution of the matrix-inverse problem. Several important techniques are employed as follows to simulate such a neural system. 1) Kronecker product of matrices is introduced to transform a matrix-differential-equation (MDE) to a vector-differential-equation (VDE); i.e., finally, a standard ordinary-differential-equation (ODE) is obtained. 2) MATLAB routine "ode45" is introduced to solve the transformed initial-value ODE problem. 3) In addition to various implementation errors, different kinds of activation functions are simulated to show the characteristics of such a neural network. Simulation results substantiate the theoretical analysis and efficacy of the gradient-based neural network for online constant matrix inversion.

Representation of neural networks as Lotka-Volterra systems

International Nuclear Information System (INIS)

Moreau, Yves; Vandewalle, Joos; Louies, Stephane; Brenig, Leon