Stochastic Dynamics of Three-State Neural Networks

Part of Advances in Neural Information Processing Systems 7 (NIPS 1994)

Bibtex Metadata Paper


Toru Ohira, Jack Cowan


We present here an analysis of the stochastic neurodynamics of a neural network composed of three-state neurons described by a master equation. An outer-product representation of the mas(cid:173) ter equation is employed. In this representation, an extension of the analysis from two to three-state neurons is easily performed. We apply this formalism with approximation schemes to a sim(cid:173) ple three-state network and compare the results with Monte Carlo simulations.