Discontinuous Recall Transitions Induced by Competition Between Short- and Long-Range Interactions in Recurrent Networks

Part of Advances in Neural Information Processing Systems 11 (NIPS 1998)

Authors

N. Skantzos, C. Beckmann, Anthony Coolen

Abstract

We present exact analytical equilibrium solutions for a class of recur(cid:173) rent neural network models, with both sequential and parallel neuronal dynamics, in which there is a tunable competition between nearest(cid:173) neighbour and long-range synaptic interactions. This competition is found to induce novel coexistence phenomena as well as discontinuous transitions between pattern recall states, 2-cycles and non-recall states.