Modern Analytic Techniques to Solve the Dynamics of Recurrent Neural Networks

Part of Advances in Neural Information Processing Systems 8 (NIPS 1995)

Bibtex Metadata Paper

Authors

A.C.C. Coolen, S. Laughton, D. Sherrington

Abstract

We describe the use of modern analytical techniques in solving the dynamics of symmetric and nonsymmetric recurrent neural net(cid:173) works near saturation. These explicitly take into account the cor(cid:173) relations between the post-synaptic potentials, and thereby allow for a reliable prediction of transients.