Showing papers in "Neural Networks in 2004"

TL;DR: This work describes a new analytical prescription for setting the value of insensitive zone epsilon, as a function of training sample size, and compares generalization performance of SVM regression under sparse sample settings with regression using 'least-modulus' loss (epsilon=0) and standard squared loss.

TL;DR: It is shown that exact leave-one-out cross-validation of sparse Least-Squares Support Vector Machines (LS-SVMs) can be implemented with a computational complexity of only O(ln2) floating point operations, rather than the O(l2n2) operations of a naïve implementation.

TL;DR: A new model, called TELOS, is proposed to explain how laminar circuitry of the frontal cortex interacts with the BG, thalamus, superior colliculus, and inferotemporal and parietal cortices to learn and perform reactive and planned eye movements.

TL;DR: In the model proposed here, visual attention is defined as a convolution of sensori-motor processing with memory that can be dissociated from the reportable form, depending on attention, called access awareness.

TL;DR: A new sufficient condition for the exponential stability of the equilibrium point for delayed neural networks with time varying delays is derived by employing a Lyapunov-Krasovskii functional and using Linear Matrix Inequality (LMI) approach.

TL;DR: A connectionist model, the recurrent neural network with parametric biases (RNNPB), in which multiple behavior schemata can be learned by the network in a distributed manner is reviewed, explaining how self-organizing internal structures can contribute to generalization in learning, and diversity in behavior generation, in the proposed distributed representation scheme.

TL;DR: In simulations, DevLex develops topographically organized representations for linguistic categories over time, models lexical confusion as a function of word density and semantic similarity, and shows age-of-acquisition effects in the course of learning a growing lexicon.

TL;DR: The results herein answer a question: if a neural network without any delay is absolutely exponentially stable, then under what additional conditions, the neural networks with delay is alsoabsolutely exponentially stable.

TL;DR: By constructing several novel Lyapunov functionals, some sufficient criteria for the existence of a unique equilibrium and global exponential stability of the network are derived.

TL;DR: Some new criteria ensuring the existence and uniqueness, and the global asymptotic stability (GAS) of equilibrium point are derived from dynamical behaviors of Hopfield neural networks system with distributed delays.

TL;DR: A new on-line algorithm for creating a self-organizing fuzzy neural network (SOFNN) from sample patterns to implement a singleton or Takagi-Sugeno (TS) type fuzzy model is presented.

TL;DR: Observations of the functional interactions between cortical areas and modules and the mechanisms by which fine scale microcircuits influence interactions at more coarse levels of organization have informed current views about the functions of these circuits.

TL;DR: This paper presents a recurrent neural network for solving strict convex quadratic programming problems and related linear piecewise equations with a one-layer structure with a low model complexity and shown to have a finite-time convergence and exponential convergence.

TL;DR: It is suggested that feedback from high-level visual areas reduces activity in lower areas in order to simplify the description of a visual image-consistent with both predictive coding models of perception and probabilistic notions of 'explaining away.

TL;DR: The CRI based GenSoFNN neural fuzzy network, henceforth denoted as Gen soFNN-CRI(S), functions as an EWS and is able to identify the inherent traits of financial distress based on financial covariates ( features) derived from publicly available financial statements.

TL;DR: This paper presents a Lyapunov analysis suggesting that the condition of strictly positive realness (SPR) associated with the tracking error dynamics is a sufficient condition for asymptotic stability of the closed-loop dynamics of FEL.

TL;DR: This article focuses on extensions of basic vector-based models by recursive computation in such a way that sequential and tree-structured data can be processed directly.

TL;DR: The comparison of the neuron state modeling and the local field modeling reveals an important stability invariance property of the two models, which lays a sound theoretical foundation of validity of a useful, cross-fertilization type stability analysis methodology for various neural network models.

TL;DR: Good agreement is found with the values that had previously been predicted by a theoretical argument based on a the asymptotic efficiency of a simplified model of SV regression of Support Vector regression.

TL;DR: In the proposed incremental constructive training schemes for an OHL-FNN, input-side training and output-sideTraining may be separated in order to reduce the training time and a new technique is proposed to scale the error signal during the constructive learning process to improve the input- side training efficiency and to obtain better generalization performance.

TL;DR: Experimental results have shown the superior performance of the proposed RGNG method over the original GNG incorporating MDL method, called GNG-M, in static data clustering tasks on both artificial and UCI data sets.

TL;DR: A brief description of electrophysiological and morphological characteristics of neocortical cells that allow their classification in categories is presented and some examples of differences in functional properties among different electrophYSiological cell classes in the visual cortex are reviewed.

TL;DR: This model can well describe many practical architectures of delayed Neural networks, which is generalization of some additive delayed neural networks such as delayed Hopfield neural networks and delayed cellular neural networks, under a time-varying environment, particularly when the network parameters and input stimuli are varied periodically with time.

TL;DR: Some new sufficient conditions on the global exponential stability of solutions are obtained by constructing a suitable Liapunov functional and utilizing the technique of matrix analysis.

TL;DR: A neural network model of auditory scene analysis, called the ARTSTREAM model, is presented to propose how the brain accomplishes this feat by clarifying how the frequency components that correspond to a given acoustic source may be coherently grouped together into a distinct stream based on pitch and spatial location cues.

TL;DR: A multilayer feed-forward network algorithm is developed that can be used to characterize nonlinear stimulus-response mapping functions of neurons in primary visual cortex (area V1) using natural image stimuli.

TL;DR: An artificial neural network (ANN)-based controller for hydronic heating plants of buildings that includes a meteorological module, forecasting the ambient temperature and solar irradiance, an indoor temperature predictor module, a supply temperature predictor Module and an optimizing module for the water supply temperature is presented.

TL;DR: Model results support the idea that contour extraction is one the primary steps in the visual processing stream, and that local processing in V1 is able to solve this task even in difficult conditions, without the participation of higher visual centers.

TL;DR: By constructing proper vector Liapunov functions and nonlinear integro-differential inequalities involving both variable delays and unbounded delay, using M-matrix theory, sufficient conditions for absolutely exponential stability are obtained.

TL;DR: The multiple packet continuous attractor networks described here may be used for spatial representations in brain areas such as the parietal cortex and hippocampus, and it is shown how high-order synapses can improve the performance of these networks, and how the location of a packet could be read by motor networks.