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


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


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.