Associative Memory by Recurrent Neural Networks with Delay Elements

Simple item page
dc.creatorMiyoshi, Seiji
dc.creatorYanai, Hiro-Fumi
dc.creatorOkada, Masato
dc.date2002-09-11
dc.date2002-09-12
dc.date.accessioned2026-07-07T02:47:14Z
dc.date.available2026-07-07T02:47:14Z
dc.descriptionThe synapses of real neural systems seem to have delays. Therefore, it is worthwhile to analyze associative memory models with delayed synapses. Thus, a sequential associative memory model with delayed synapses is discussed, where a discrete synchronous updating rule and a correlation learning rule are employed. Its dynamic properties are analyzed by the statistical neurodynamics. In this paper, we first re-derive the Yanai-Kim theory, which involves macrodynamical equations for the dynamics of the network with serial delay elements. Since their theory needs a computational complexity of $O(L^4t)$ to obtain the macroscopic state at time step t where L is the length of delay, it is intractable to discuss the macroscopic properties for a large L limit. Thus, we derive steady state equations using the discrete Fourier transformation, where the computational complexity does not formally depend on L. We show that the storage capacity $α_C$ is in proportion to the delay length L with a large L limit, and the proportion constant is 0.195, i.e., $α_C = 0.195 L$. These results are supported by computer simulations.
dc.description17 pages, 10figures
dc.identifierhttps://arxiv.org/abs/cond-mat/0209258
dc.identifierhttp://arxiv.org/abs/cond-mat/0209258
dc.identifier.urihttp://salesiana.dossiersoluciones.com/handle/123456789/19934
dc.subjectDisordered Systems and Neural Networks
dc.subjectQuantitative Biology
dc.titleAssociative Memory by Recurrent Neural Networks with Delay Elements
dc.typetext

Files

Collections

arXiv