NONEQUILIBRIUM NEURAL-NETWORK WITH COMPETING DYNAMICS

A stochastic neural-network model with superposition of neuron and syn apse kinetics with a priori probabilities p and 1 - p, respectively, i s presented. We report on exact and approximate results for p --> 0. T his includes Hopfield-like models in which synaptic intensities locall y fluctuate around Hebbian values. It is illustrated how fluctuations influence the phase diagram and, in particular, that an appropriate ch oice of details may significantly improve the retrieval process. (C) 1 998 Elsevier Science B.V. All rights reserved.