Retrieval Phase Diagrams of Non-monotonic Hopfield Networks

Дата и время публикации : 1996-04-11T03:53:21Z

Авторы публикации и институты :
Jun-ichi Inoue (Department of Physics, Tokyo Institute of Technology and RIKEN)

Ссылка на журнал-издание: J.Phys.A: Math.Gen. 29 (1996) 4815-4826
Коментарии к cтатье: Latex 13 pages using IOP style file
Первичная категория: cond-mat.dis-nn

Все категории : cond-mat.dis-nn

Краткий обзор статьи: We investigate the retrieval phase diagrams of an asynchronous fully-connected attractor network with non-monotonic transfer function by means of a mean-field approximation. We find for the noiseless zero-temperature case that this non-monotonic Hopfield network can store more patterns than a network with monotonic transfer function investigated by Amit et al. Properties of retrieval phase diagrams of non-monotonic networks agree with the results obtained by Nishimori and Opris who treated synchronous networks. We also investigate the optimal storage capacity of the non-monotonic Hopfield model with state-dependent synaptic couplings introduced by Zertuche et el. We show that the non-monotonic Hopfield model with state-dependent synapses stores more patterns than the conventional Hopfield model. Our formulation can be easily extended to a general transfer function.

Category: Physics