Discontinuous Recall Transitions Induced by Competition Between Short- and Long-Range Interactions in Recurrent Networks
暂无分享,去创建一个
We present exact analytical equilibrium solutions for a class of recurrent neural network models, with both sequential and parallel neuronal dynamics, in which there is a tunable competition between nearest-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.
[1] Haim Sompolinsky,et al. STATISTICAL MECHANICS OF NEURAL NETWORKS , 1988 .
[2] C. Thompson. The Statistical Mechanics of Phase Transitions , 1978 .
[3] Michael I. Jordan,et al. Advances in Neural Information Processing Systems 30 , 1995 .
[4] L Delpuech,et al. Models of Neural Networks, Deuxième édition, E Domany, JL van Hemmen, K Schulten. Springer Verlag, Marseille (1995) , 1997 .
[5] J. G. Taylor,et al. Mathematical Approaches to Neural Networks , 1993 .