Results 1  10
of
440,652
Stability Of Stochastic Neural Networks
"... Although the stability of neural networks has been studied by many authors, the problem of stochastic effects to the stability has not been investigated until recently by Liao & Mao (1996), where the exponentially stability and insta bility of stochastic neural networks were discussed. In this ..."
Abstract

Cited by 5 (2 self)
 Add to MetaCart
Although the stability of neural networks has been studied by many authors, the problem of stochastic effects to the stability has not been investigated until recently by Liao & Mao (1996), where the exponentially stability and insta bility of stochastic neural networks were discussed
Modelling Displacement Fields of Wood in Compression Loading Using Stochastic Neural Networks
"... stochastic neural networks, deformation profiles, wood ..."
Stochastic Neural Networks
 ALGORITHMICA (1991) 6:466478
, 1991
"... The first purpose of this paper is to present a class of algorithms for finding the global minimum of a continuousvariable function defined on a hypercube. These algorithms, based on both diffusion processes and simulated annealing, are implementable as analog integrated circuits. Such circuits c ..."
Abstract

Cited by 5 (0 self)
 Add to MetaCart
can be viewed as generalizations of neural networks of the Hopfield type, and are called "diffusion machines." Our second objective isto show that "learning " in these networks can be achieved by a set of three interconnected diffusion machines: one that learns, one to model
An Introduction to Stochastic Neural Networks
"... Introduction How does the brain compute? Particularly in the last hundred years have we gathered an enormous amount of experimental findings that shed some light on this question. The picture that has emerged is that the neuron is the central computing element of the brain which performs a nonline ..."
Abstract

Cited by 1 (0 self)
 Add to MetaCart
linear input to output mapping between its synaptic inputs and its spiky output. The neurons are connected by synaptic junctions, thus forming a neural network. A central question is how such a neural network implements brain functions such as vision, audition and motor control. These questions are to a
STOCHASTIC NEURAL NETWORKS
, 1991
"... Artificial neural networks are brainlike models of parallel computations and cognitive phenomena. We sample some basic results about neural networks as they relate to stochastic and statistical processes. Given the explosive amount of material, only models bearing a stochastic component in the func ..."
Abstract
 Add to MetaCart
Artificial neural networks are brainlike models of parallel computations and cognitive phenomena. We sample some basic results about neural networks as they relate to stochastic and statistical processes. Given the explosive amount of material, only models bearing a stochastic component
SelfOrganization in Stochastic Neural:Networks
"... The maximization of the Mutual Information between the stochastic outputs neurons and the clamped inputs is used as unsupervised criterion for training a Boltzmann Machine. The resulting learning rule contains two terms comsponding to the Hebbian and antiHebbian learning, The two terms are weighte ..."
Abstract
 Add to MetaCart
performance of this method. Boltzmann Machines [l] are a class of stochastic neural networks which applied the principles of statistical mechanics to implement a kind of recurrent network witlh symmetrical connections which is capable to learn in a supervised fashion a given probabillity distribution. Boltz
Theory of Correlations in Stochastic Neural Networks
 PHYSICAL REVIEW E
, 1994
"... One of the main experimental tools in probing the interactions between neurons has been the measurement of the correlations in their activity. In general, however the interpretation of the observed correlations is difficult, since the correlation between a pair of neurons is influenced not only b ..."
Abstract

Cited by 36 (4 self)
 Add to MetaCart
networks comprising of several highly connected subpopulations, and obey stochastic dynamic rules. When the networks are in asynchronous states, the crosscorrelations are relatively weak, i.e., their amplitude relative to that of the autocorrelations is of order of 1=N , N being the size
Stochastic Neural Networks with Applications to Nonlinear Time Series
 JOURNAL OF THE AMERICAN STATISTICAL ASSOCIATION
, 2001
"... Neural networks have a burgeoning literature in nonlinear time series. We consider here a variant of the conventional neural network model, called the stochastic neural network, that can be used to approximate complex nonlinear stochastic systems. We show how the EM algorithm can be used to develop ..."
Abstract

Cited by 9 (2 self)
 Add to MetaCart
Neural networks have a burgeoning literature in nonlinear time series. We consider here a variant of the conventional neural network model, called the stochastic neural network, that can be used to approximate complex nonlinear stochastic systems. We show how the EM algorithm can be used to develop
Correlation Coding in Stochastic Neural Networks
"... Abstract. Stimulus4ependent changes have been observed in the correlations between the spike trains of simultaneouslyrecorded pairs of neurons from the auditory cortex of marmosets even when there was no change in the average firing rates. A simple neural model can reproduce most of the characteris ..."
Abstract
 Add to MetaCart
Abstract. Stimulus4ependent changes have been observed in the correlations between the spike trains of simultaneouslyrecorded pairs of neurons from the auditory cortex of marmosets even when there was no change in the average firing rates. A simple neural model can reproduce most
Correlation Coding in Stochastic Neural Networks
, 1997
"... Stimulusdependent changes have been observed in the correlations between the spike trains of simultaneouslyrecorded pairs of neurons from the auditory cortex of marmosets even when there was no change in the average firing rates. A simple neural model can reproduce most of the characteristics of ..."
Abstract
 Add to MetaCart
Stimulusdependent changes have been observed in the correlations between the spike trains of simultaneouslyrecorded pairs of neurons from the auditory cortex of marmosets even when there was no change in the average firing rates. A simple neural model can reproduce most of the characteristics
Results 1  10
of
440,652