Register your interests and receive email alerts tailored to your needs
Most Cited Neural Networks Articles
Modeling attention to salient proto-objects
Volume 19, Issue 9, November 2006, Pages 1395-1407
Walther, D. | Koch, C.
Selective visual attention is believed to be responsible for serializing visual information for recognizing one object at a time in a complex scene. But how can we attend to objects before they are recognized? In coherence theory of visual cognition, so-called proto-objects form volatile units of visual information that can be accessed by selective attention and subsequently validated as actual objects. We propose a biologically plausible model of forming and attending to proto-objects in natural scenes. We demonstrate that the suggested model can enable a model of object recognition in cortex to expand from recognizing individual objects in isolation to sequentially recognizing all objects in a more complex scene. © 2006.
Global exponential stability of generalized recurrent neural networks with discrete and distributed delays
Volume 19, Issue 5, June 2006, Pages 667-675
Liu, Y. | Wang, Z. | Liu, X.
This paper is concerned with analysis problem for the global exponential stability of a class of recurrent neural networks (RNNs) with mixed discrete and distributed delays. We first prove the existence and uniqueness of the equilibrium point under mild conditions, assuming neither differentiability nor strict monotonicity for the activation function. Then, by employing a new Lyapunov-Krasovskii functional, a linear matrix inequality (LMI) approach is developed to establish sufficient conditions for the RNNs to be globally exponentially stable. Therefore, the global exponential stability of the delayed RNNs can be easily checked by utilizing the numerically efficient Matlab LMI toolbox, and no tuning of parameters is required. A simulation example is exploited to show the usefulness of the derived LMI-based stability conditions. © 2005 Elsevier Ltd. All rights reserved.
Central pattern generators for locomotion control in animals and robots: A review
Volume 21, Issue 4, May 2008, Pages 642-653
Ijspeert, A.J.
The problem of controlling locomotion is an area in which neuroscience and robotics can fruitfully interact. In this article, I will review research carried out on locomotor central pattern generators (CPGs), i.e. neural circuits capable of producing coordinated patterns of high-dimensional rhythmic output signals while receiving only simple, low-dimensional, input signals. The review will first cover neurobiological observations concerning locomotor CPGs and their numerical modelling, with a special focus on vertebrates. It will then cover how CPG models implemented as neural networks or systems of coupled oscillators can be used in robotics for controlling the locomotion of articulated robots. The review also presents how robots can be used as scientific tools to obtain a better understanding of the functioning of biological CPGs. Finally, various methods for designing CPGs to control specific modes of locomotion will be briefly reviewed. In this process, I will discuss different types of CPG models, the pros and cons of using CPGs with robots, and the pros and cons of using robots as scientific tools. Open research topics both in biology and in robotics will also be discussed. © 2008 Elsevier Ltd. All rights reserved.
Neural systems implicated in delayed and probabilistic reinforcement
Volume 19, Issue 8, October 2006, Pages 1277-1301
Cardinal, R.N.
This review considers the theoretical problems facing agents that must learn and choose on the basis of reward or reinforcement that is uncertain or delayed, in implicit or procedural (stimulus-response) representational systems and in explicit or declarative (action-outcome-value) representational systems. Individual differences in sensitivity to delays and uncertainty may contribute to impulsivity and risk taking. Learning and choice with delayed and uncertain reinforcement are related but in some cases dissociable processes. The contributions to delay and uncertainty discounting of neuromodulators including serotonin, dopamine, and noradrenaline, and of specific neural structures including the nucleus accumbens core, nucleus accumbens shell, orbitofrontal cortex, basolateral amygdala, anterior cingulate cortex, medial prefrontal (prelimbic/infralimbic) cortex, insula, subthalamic nucleus, and hippocampus are examined. © 2006 Elsevier Ltd. All rights reserved.
Hold your horses: A dynamic computational role for the subthalamic nucleus in decision making
Volume 19, Issue 8, October 2006, Pages 1120-1136
Frank, M.J.
The basal ganglia (BG) coordinate decision making processes by facilitating adaptive frontal motor commands while suppressing others. In previous work, neural network simulations accounted for response selection deficits associated with BG dopamine depletion in Parkinson's disease. Novel predictions from this model have been subsequently confirmed in Parkinson patients and in healthy participants under pharmacological challenge. Nevertheless, one clear limitation of that model is in its omission of the subthalamic nucleus (STN), a key BG structure that participates in both motor and cognitive processes. The present model incorporates the STN and shows that by modulating when a response is executed, the STN reduces premature responding and therefore has substantial effects on which response is ultimately selected, particularly when there are multiple competing responses. Increased cortical response conflict leads to dynamic adjustments in response thresholds via cortico-subthalamic-pallidal pathways. The model accurately captures the dynamics of activity in various BG areas during response selection. Simulated dopamine depletion results in emergent oscillatory activity in BG structures, which has been linked with Parkinson's tremor. Finally, the model accounts for the beneficial effects of STN lesions on these oscillations, but suggests that this benefit may come at the expense of impaired decision making. © 2006 Elsevier Ltd. All rights reserved.
A new approach to exponential stability analysis of neural networks with time-varying delays
Volume 19, Issue 1, January 2006, Pages 76-83
Xu, S. | Lam, J.
This paper considers the problem of exponential stability analysis of neural networks with time-varying delays. The activation functions are assumed to be globally Lipschitz continuous. A linear matrix inequality (LMI) approach is developed to derive sufficient conditions ensuring the delayed neural network to have a unique equilibrium point, which is globally exponentially stable. The proposed LMI conditions can be checked easily by recently developed algorithms solving LMIs. Examples are provided to demonstrate the reduced conservativeness of the proposed results. © 2005 Elsevier Ltd. All rights reserved.
Mirror neurons and imitation: A computationally guided review
Volume 19, Issue 3, April 2006, Pages 254-271
Oztop, E. | Kawato, M. | Arbib, M.
Neurophysiology reveals the properties of individual mirror neurons in the macaque while brain imaging reveals the presence of 'mirror systems' (not individual neurons) in the human. Current conceptual models attribute high level functions such as action understanding, imitation, and language to mirror neurons. However, only the first of these three functions is well-developed in monkeys. We thus distinguish current opinions (conceptual models) on mirror neuron function from more detailed computational models. We assess the strengths and weaknesses of current computational models in addressing the data and speculations on mirror neurons (macaque) and mirror systems (human). In particular, our mirror neuron system (MNS), mental state inference (MSI) and modular selection and identification for control (MOSAIC) models are analyzed in more detail. Conceptual models often overlook the computational requirements for posited functions, while too many computational models adopt the erroneous hypothesis that mirror neurons are interchangeable with imitation ability. Our meta-analysis underlines the gap between conceptual and computational models and points out the research effort required from both sides to reduce this gap. © 2006 Elsevier Ltd. All rights reserved.
Neuropsychological correlates of decision-making in ambiguous and risky situations
Volume 19, Issue 8, October 2006, Pages 1266-1276
Brand, M. | Labudda, K. | Markowitsch, H.J.
Decision-making situations in real life differ regarding their explicitness of positive and negative consequences as well as regarding the directness of probabilities for reward and punishment. In neuropsychological research, decisions under ambiguity and decisions under risk are differentiated. To assess decisions under ambiguity the Iowa Gambling Task (IGT) is one of the most frequently used tasks. Decisions under risk can be measured by a task that offers explicit rules for gains and losses and stable winning probabilities, as the Game of Dice Task (GDT) does. In this contribution we firstly summarize studies that investigated decision-making in various groups of patients using the IGT or the GDT. We also propose a new model of decision-making in risky situations and describe differences between decisions under ambiguity and decisions under risk from a theoretical and clinical perspective. © 2006 Elsevier Ltd. All rights reserved.
The use of artificial neural networks in decision support in cancer: A systematic review
Volume 19, Issue 4, May 2006, Pages 408-415
Lisboa, P.J. | Taktak, A.F.G.
Artificial neural networks have featured in a wide range of medical journals, often with promising results. This paper reports on a systematic review that was conducted to assess the benefit of artificial neural networks (ANNs) as decision making tools in the field of cancer. The number of clinical trials (CTs) and randomised controlled trials (RCTs) involving the use of ANNs in diagnosis and prognosis increased from 1 to 38 in the last decade. However, out of 396 studies involving the use of ANNs in cancer, only 27 were either CTs or RCTs. Out of these trials, 21 showed an increase in benefit to healthcare provision and 6 did not. None of these studies however showed a decrease in benefit. This paper reviews the clinical fields where neural network methods figure most prominently, the main algorithms featured, methodologies for model selection and the need for rigorous evaluation of results. © 2005 Elsevier Ltd. All rights reserved.
An experimental unification of reservoir computing methods
Volume 20, Issue 3, April 2007, Pages 391-403
Verstraeten, D. | Schrauwen, B. | D'Haene, M. | Stroobandt, D.
Three different uses of a recurrent neural network (RNN) as a reservoir that is not trained but instead read out by a simple external classification layer have been described in the literature: Liquid State Machines (LSMs), Echo State Networks (ESNs) and the Backpropagation Decorrelation (BPDC) learning rule. Individual descriptions of these techniques exist, but a overview is still lacking. Here, we present a series of experimental results that compares all three implementations, and draw conclusions about the relation between a broad range of reservoir parameters and network dynamics, memory, node complexity and performance on a variety of benchmark tests with different characteristics. Next, we introduce a new measure for the reservoir dynamics based on Lyapunov exponents. Unlike previous measures in the literature, this measure is dependent on the dynamics of the reservoir in response to the inputs, and in the cases we tried, it indicates an optimal value for the global scaling of the weight matrix, irrespective of the standard measures. We also describe the Reservoir Computing Toolbox that was used for these experiments, which implements all the types of Reservoir Computing and allows the easy simulation of a wide range of reservoir topologies for a number of benchmarks. © 2007 Elsevier Ltd. All rights reserved.
State estimation for jumping recurrent neural networks with discrete and distributed delays
Volume 22, Issue 1, January 2009, Pages 41-48
Wang, Z. | Liu, Y. | Liu, X.
This paper is concerned with the state estimation problem for a class of Markovian neural networks with discrete and distributed time-delays. The neural networks have a finite number of modes, and the modes may jump from one to another according to a Markov chain. The main purpose is to estimate the neuron states, through available output measurements, such that for all admissible time-delays, the dynamics of the estimation error is globally asymptotically stable in the mean square. An effective linear matrix inequality approach is developed to solve the neuron state estimation problem. Both the existence conditions and the explicit characterization of the desired estimator are derived. Furthermore, it is shown that the traditional stability analysis issue for delayed neural networks with Markovian jumping parameters can be included as a special case of our main results. Finally, numerical examples are given to illustrate the applicability of the proposed design method. © 2008 Elsevier Ltd. All rights reserved.
Optimization and applications of echo state networks with leaky- integrator neurons
Volume 20, Issue 3, April 2007, Pages 335-352
Jaeger, H. | Lukoševičius, M. | Popovici, D. | Siewert, U.
Standard echo state networks (ESNs) are built from simple additive units with a sigmoid activation function. Here we investigate ESNs whose reservoir units are leaky integrator units. Units of this type have individual state dynamics, which can be exploited in various ways to accommodate the network to the temporal characteristics of a learning task. We present stability conditions, introduce and investigate a stochastic gradient descent method for the optimization of the global learning parameters (input and output feedback scalings, leaking rate, spectral radius) and demonstrate the usefulness of leaky-integrator ESNs for (i) learning very slow dynamic systems and replaying the learnt system at different speeds, (ii) classifying relatively slow and noisy time series (the Japanese Vowel dataset - here we obtain a zero test error rate), and (iii) recognizing strongly time-warped dynamic patterns. © 2007 Elsevier Ltd. All rights reserved.
Training neural network classifiers for medical decision making: The effects of imbalanced datasets on classification performance
Volume 21, Issues 2-3, March 2008, Pages 427-436
Mazurowski, M.A. | Habas, P.A. | Zurada, J.M. | Lo, J.Y. | Baker, J.A. | Tourassi, G.D.
This study investigates the effect of class imbalance in training data when developing neural network classifiers for computer-aided medical diagnosis. The investigation is performed in the presence of other characteristics that are typical among medical data, namely small training sample size, large number of features, and correlations between features. Two methods of neural network training are explored: classical backpropagation (BP) and particle swarm optimization (PSO) with clinically relevant training criteria. An experimental study is performed using simulated data and the conclusions are further validated on real clinical data for breast cancer diagnosis. The results show that classifier performance deteriorates with even modest class imbalance in the training data. Further, it is shown that BP is generally preferable over PSO for imbalanced training data especially with small data sample and large number of features. Finally, it is shown that there is no clear preference between oversampling and no compensation approach and some guidance is provided regarding a proper selection. © 2007 Elsevier Ltd. All rights reserved.
An incremental network for on-line unsupervised classification and topology learning
Volume 19, Issue 1, January 2006, Pages 90-106
Furao, S. | Hasegawa, O.
This paper presents an on-line unsupervised learning mechanism for unlabeled data that are polluted by noise. Using a similarity threshold-based and a local error-based insertion criterion, the system is able to grow incrementally and to accommodate input patterns of on-line non-stationary data distribution. A definition of a utility parameter, the error-radius, allows this system to learn the number of nodes needed to solve a task. The use of a new technique for removing nodes in low probability density regions can separate clusters with low-density overlaps and dynamically eliminate noise in the input data. The design of two-layer neural network enables this system to represent the topological structure of unsupervised on-line data, report the reasonable number of clusters, and give typical prototype patterns of every cluster without prior conditions such as a suitable number of nodes or a good initial codebook. © 2005 Elsevier Ltd. All rights reserved.
Weighing up the benefits of work: Behavioral and neural analyses of effort-related decision making
Volume 19, Issue 8, October 2006, Pages 1302-1314
Walton, M.E. | Kennerley, S.W. | Bannerman, D.M. | Phillips, P.E.M. | Rushworth, M.F.S.
How we decide whether a course of action is worth undertaking is largely unknown. Recently, neuroscientists have been turning to ecological approaches to address this issue, examining how animals evaluate the costs and benefits of different options. We present here evidence from rodents and monkeys that demonstrate the degree to which they take into account work and energetic requirements when deciding what responses to make. These calculations appear to be critically mediated by the anterior cingulate cortex (ACC) and mesolimbic dopamine (DA) pathways, with damage to either causing a bias towards options that are easily obtained but yield relatively smaller reward rather than alternatives that require more work but result in greater reward. The evaluation of such decisions appears to be carried out in systems independent of those involved in delay-discounting. We suggest that top-down signals from ACC to nucleus accumbens (NAc) and/or midbrain DA cells may be vital for overcoming effort-related response costs. © 2006 Elsevier Ltd. All rights reserved.
Global exponential stability of impulsive high-order BAM neural networks with time-varying delays
Volume 19, Issue 10, December 2006, Pages 1581-1590
Ho, D.W.C. | Liang, J. | Lam, J.
In this paper, global exponential stability and exponential convergence are studied for a class of impulsive high-order bidirectional associative memory (BAM) neural networks with time-varying delays. By employing linear matrix inequalities (LMIs) and differential inequalities with delays and impulses, several sufficient conditions are obtained for ensuring the system to be globally exponentially stable. Three illustrative examples are also given at the end of this paper to show the effectiveness of our results. © 2006 Elsevier Ltd. All rights reserved.
Stable concurrent synchronization in dynamic system networks
Volume 20, Issue 1, January 2007, Pages 62-77
Pham, Q.-C. | Slotine, J.-J.
In a network of dynamical systems, concurrent synchronization is a regime where multiple groups of fully synchronized elements coexist. In the brain, concurrent synchronization may occur at several scales, with multiple "rhythms" interacting and functional assemblies combining neural oscillators of many different types. Mathematically, stable concurrent synchronization corresponds to convergence to a flow-invariant linear subspace of the global state space. We derive a general condition for such convergence to occur globally and exponentially. We also show that, under mild conditions, global convergence to a concurrently synchronized regime is preserved under basic system combinations such as negative feedback or hierarchies, so that stable concurrently synchronized aggregates of arbitrary size can be constructed. Robustnesss of stable concurrent synchronization to variations in individual dynamics is also quantified. Simple applications of these results to classical questions in systems neuroscience and robotics are discussed. © 2006 Elsevier Ltd. All rights reserved.
A robot model of the basal ganglia: Behavior and intrinsic processing
Volume 19, Issue 1, January 2006, Pages 31-61
Prescott, T.J. | Montes González, F.M. | Gurney, K. | Humphries, M.D. | Redgrave, P.
The existence of multiple parallel loops connecting sensorimotor systems to the basal ganglia has given rise to proposals that these nuclei serve as a selection mechanism resolving competitions between the alternative actions available in a given context. A strong test of this hypothesis is to require a computational model of the basal ganglia to generate integrated selection sequences in an autonomous agent, we therefore describe a robot architecture into which such a model is embedded, and require it to control action selection in a robotic task inspired by animal observations. Our results demonstrate effective action selection by the embedded model under a wide range of sensory and motivational conditions. When confronted with multiple, high salience alternatives, the robot also exhibits forms of behavioral disintegration that show similarities to animal behavior in conflict situations. The model is shown to cast light on recent neurobiological findings concerning behavioral switching and sequencing. © 2005 Elsevier Ltd. All rights reserved.
A new supervised learning algorithm for multiple spiking neural networks with application in epilepsy and seizure detection
Volume 22, Issue 10, December 2009, Pages 1419-1431
Ghosh-Dastidar, S. | Adeli, H.
A new Multi-Spiking Neural Network (MuSpiNN) model is presented in which information from one neuron is transmitted to the next in the form of multiple spikes via multiple synapses. A new supervised learning algorithm, dubbed Multi-SpikeProp, is developed for training MuSpiNN. The model and learning algorithm employ the heuristic rules and optimum parameter values presented by the authors in a recent paper that improved the efficiency of the original single-spiking Spiking Neural Network (SNN) model by two orders of magnitude. The classification accuracies of MuSpiNN and Multi-SpikeProp are evaluated using three increasingly more complicated problems: the XOR problem, the Fisher iris classification problem, and the epilepsy and seizure detection (EEG classification) problem. It is observed that MuSpiNN learns the XOR problem in twice the number of epochs compared with the single-spiking SNN model but requires only one-fourth the number of synapses. For the iris and EEG classification problems, a modular architecture is employed to reduce each 3-class classification problem to three 2-class classification problems and improve the classification accuracy. For the complicated EEG classification problem a classification accuracy in the range of 90.7%-94.8% was achieved, which is significantly higher than the 82% classification accuracy obtained using the single-spiking SNN with SpikeProp. © 2009 Elsevier Ltd. All rights reserved.
Batch and median neural gas
Volume 19, Issues 6-7, July 2006, Pages 762-771
Cottrell, M. | Hammer, B. | Hasenfuß, A. | Villmann, T.
Neural Gas (NG) constitutes a very robust clustering algorithm given Euclidean data which does not suffer from the problem of local minima like simple vector quantization, or topological restrictions like the self-organizing map. Based on the cost function of NG, we introduce a batch variant of NG which shows much faster convergence and which can be interpreted as an optimization of the cost function by the Newton method. This formulation has the additional benefit that, based on the notion of the generalized median in analogy to Median SOM, a variant for non-vectorial proximity data can be introduced. We prove convergence of batch and median versions of NG, SOM, and k-means in a unified formulation, and we investigate the behavior of the algorithms in several experiments. © 2006 Elsevier Ltd. All rights reserved.
Analyzing and shaping human attentional networks
Volume 19, Issue 9, November 2006, Pages 1422-1429
Posner, M.I. | Sheese, B.E. | Odludaş, Y. | Tang, Y.
In this paper we outline a conception of attentional networks arising from imaging studies as connections between activated brain areas carrying out localized mental operations. We consider both the areas of functional activation (nodes) and the structural (DTI) and functional connections (DCM) between them in real time (EEG, frequency analysis) as important tools in analyzing the network. The efficiency of network function involves the time course of activation of nodes and their connectivity to other areas of the network. We outline landmarks in the development of brain networks underlying executive attention from infancy and childhood. We use individual differences in network efficiency to examine genetic alleles that are related to performance. We consider how animal studies might be used to determine the genes that influence network development. Finally we indicate how training may aid in enhancing attentional networks. Our goal is to show the wide range of methods that can be used to suggest and analyze models of network function in the study of attention. © 2006 Elsevier Ltd. All rights reserved.
Global exponential stability of recurrent neural networks with time-varying delays in the presence of strong external stimuli
Volume 19, Issue 10, December 2006, Pages 1528-1537
Zeng, Z. | Wang, J.
This paper presents new theoretical results on the global exponential stability of recurrent neural networks with bounded activation functions and bounded time-varying delays in the presence of strong external stimuli. It is shown that the Cohen-Grossberg neural network is globally exponentially stable, if the absolute value of the input vector exceeds a criterion. As special cases, the Hopfield neural network and the cellular neural network are examined in detail. In addition, it is shown that criteria herein, if partially satisfied, can still be used in combination with existing stability conditions. Simulation results are also discussed in two illustrative examples. © 2006 Elsevier Ltd. All rights reserved.
Local multidimensional scaling
Volume 19, Issues 6-7, July 2006, Pages 889-899
Venna, J. | Kaski, S.
In a visualization task, every nonlinear projection method needs to make a compromise between trustworthiness and continuity. In a trustworthy projection the visualized proximities hold in the original data as well, whereas a continuous projection visualizes all proximities of the original data. We show experimentally that one of the multidimensional scaling methods, curvilinear components analysis, is good at maximizing trustworthiness. We then extend it to focus on local proximities both in the input and output space, and to explicitly make a user-tunable parameterized compromise between trustworthiness and continuity. The new method compares favorably to alternative nonlinear projection methods. © 2006 Elsevier Ltd. All rights reserved.
Edge of chaos and prediction of computational performance for neural circuit models
Volume 20, Issue 3, April 2007, Pages 323-334
Legenstein, R. | Maass, W.
We analyze in this article the significance of the edge of chaos for real-time computations in neural microcircuit models consisting of spiking neurons and dynamic synapses. We find that the edge of chaos predicts quite well those values of circuit parameters that yield maximal computational performance. But obviously it makes no prediction of their computational performance for other parameter values. Therefore, we propose a new method for predicting the computational performance of neural microcircuit models. The new measure estimates directly the kernel property and the generalization capability of a neural microcircuit. We validate the proposed measure by comparing its prediction with direct evaluations of the computational performance of various neural microcircuit models. The proposed method also allows us to quantify differences in the computational performance and generalization capability of neural circuits in different dynamic regimes (UP- and DOWN-states) that have been demonstrated through intracellular recordings in vivo. © 2007 Elsevier Ltd. All rights reserved.
Reinforcement learning of motor skills with policy gradients
Volume 21, Issue 4, May 2008, Pages 682-697
Peters, J. | Schaal, S.
Autonomous learning is one of the hallmarks of human and animal behavior, and understanding the principles of learning will be crucial in order to achieve true autonomy in advanced machines like humanoid robots. In this paper, we examine learning of complex motor skills with human-like limbs. While supervised learning can offer useful tools for bootstrapping behavior, e.g., by learning from demonstration, it is only reinforcement learning that offers a general approach to the final trial-and-error improvement that is needed by each individual acquiring a skill. Neither neurobiological nor machine learning studies have, so far, offered compelling results on how reinforcement learning can be scaled to the high-dimensional continuous state and action spaces of humans or humanoids. Here, we combine two recent research developments on learning motor control in order to achieve this scaling. First, we interpret the idea of modular motor control by means of motor primitives as a suitable way to generate parameterized control policies for reinforcement learning. Second, we combine motor primitives with the theory of stochastic policy gradient learning, which currently seems to be the only feasible framework for reinforcement learning for humanoids. We evaluate different policy gradient methods with a focus on their applicability to parameterized motor primitives. We compare these algorithms in the context of motor primitive learning, and show that our most modern algorithm, the Episodic Natural Actor-Critic outperforms previous algorithms by at least an order of magnitude. We demonstrate the efficiency of this reinforcement learning method in the application of learning to hit a baseball with an anthropomorphic robot arm. © 2008 Elsevier Ltd. All rights reserved.
