Transient dynamics for sequence processing neural networks

DOI10.1088/0305-4470/35/2/306MaRDI QIDQ4465540zbMATH OpenOpenAlexFDO

Authors Masaki Kawamura, Masato Okada

Publication date 9 June 2004

Published in Journal of Physics A: Mathematical and General (Search for Journal in Brave)

Full work available at URL https://arxiv.org/abs/cond-mat/0202431

Mathematics Subject Classification ID

Neural nets applied to problems in time-dependent statistical mechanics (82C32) Neural networks for/in biological studies, artificial life and related topics (92B20)

Abstract: An exact solution of the transient dynamics for a sequential associative memory model is discussed through both the path-integral method and the statistical neurodynamics. Although the path-integral method has the ability to give an exact solution of the transient dynamics, only stationary properties have been discussed for the sequential associative memory. We have succeeded in deriving an exact macroscopic description of the transient dynamics by analyzing the correlation of crosstalk noise. Surprisingly, the order parameter equations of this exact solution are completely equivalent to those of the statistical neurodynamics, which is an approximation theory that assumes crosstalk noise to obey the Gaussian distribution. In order to examine our theoretical findings, we numerically obtain cumulants of the crosstalk noise. We verify that the third- and fourth-order cumulants are equal to zero, and that the crosstalk noise is normally distributed even in the non-retrieval case. We show that the results obtained by our theory agree with those obtained by computer simulations. We have also found that the macroscopic unstable state completely coincides with the separatrix.

Recommendations

• Dynamics of Sequence-Associative Memory for Discrete Maps in XY Spin Systems
• The signal-to-noise analysis of the Little–Hopfield model revisited
• Phase diagram and storage capacity of sequence processing neural networks
• The path-integral analysis of an associative memory model storing an infinite number of finite limit cycles
• Mean-field dynamics of sequence processing neural networks with finite connectivity

Cited in

(10)

• Mean-field dynamics of sequence processing neural networks with finite connectivity
• Hidden chaotic sets in a Hopfield neural system
• Associative memory by recurrent neural networks with delay elements
• Hopfield neuronal network of fractional order: a note on its numerical integration
• STORING LIMIT CYCLES USING DELAYED FEEDBACK NEURAL NETWORKS
• On the macroscopic description of recurrent neural network dynamics
• Dynamics of Sequence-Associative Memory for Discrete Maps in XY Spin Systems
• Order Parameter Flow of Auto-Associative Memory in an XY Spin System
• Stimulus-Driven and Spontaneous Dynamics in Excitatory-Inhibitory Recurrent Neural Networks for Sequence Representation
• FRACTAL TRANSITION IN CONTINUOUS RECURRENT NEURAL NETWORKS

This page was built for publication: Transient dynamics for sequence processing neural networks

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q4465540)