Retrieval of spatio-temporal sequence in asynchronous neural network

Hidetoshi Nishimori, Tota Nakamura, Masatoshi Shiino

Research output: Contribution to journalArticle

33 Citations (Scopus)

Abstract

We develop an argument that a neural network with asynchronous updating dynamics is capable of sequential retrieval of properly embedded spatial patterns. It is not necessary that the patterns be random, but they have to satisfy certain restrictions. The network is a generalization of the Hopfield model with a specific type of asymmetric synaptic connections. No time delay is introduced in signal transmission, in contrast to some of the recently proposed networks.

Original languageEnglish
Pages (from-to)3346-3354
Number of pages9
JournalPhysical Review A
Volume41
Issue number6
DOIs
Publication statusPublished - 1990
Externally publishedYes

Fingerprint

retrieval
signal transmission
constrictions
time lag

ASJC Scopus subject areas

  • Atomic and Molecular Physics, and Optics
  • Physics and Astronomy(all)

Cite this

Retrieval of spatio-temporal sequence in asynchronous neural network. / Nishimori, Hidetoshi; Nakamura, Tota; Shiino, Masatoshi.

In: Physical Review A, Vol. 41, No. 6, 1990, p. 3346-3354.

Research output: Contribution to journalArticle

Nishimori, Hidetoshi ; Nakamura, Tota ; Shiino, Masatoshi. / Retrieval of spatio-temporal sequence in asynchronous neural network. In: Physical Review A. 1990 ; Vol. 41, No. 6. pp. 3346-3354.
@article{8b7c7244ea3645b880618b3e71b12319,
title = "Retrieval of spatio-temporal sequence in asynchronous neural network",
abstract = "We develop an argument that a neural network with asynchronous updating dynamics is capable of sequential retrieval of properly embedded spatial patterns. It is not necessary that the patterns be random, but they have to satisfy certain restrictions. The network is a generalization of the Hopfield model with a specific type of asymmetric synaptic connections. No time delay is introduced in signal transmission, in contrast to some of the recently proposed networks.",
author = "Hidetoshi Nishimori and Tota Nakamura and Masatoshi Shiino",
year = "1990",
doi = "10.1103/PhysRevA.41.3346",
language = "English",
volume = "41",
pages = "3346--3354",
journal = "Physical Review A",
issn = "2469-9926",
publisher = "American Physical Society",
number = "6",

}

TY - JOUR

T1 - Retrieval of spatio-temporal sequence in asynchronous neural network

AU - Nishimori, Hidetoshi

AU - Nakamura, Tota

AU - Shiino, Masatoshi

PY - 1990

Y1 - 1990

N2 - We develop an argument that a neural network with asynchronous updating dynamics is capable of sequential retrieval of properly embedded spatial patterns. It is not necessary that the patterns be random, but they have to satisfy certain restrictions. The network is a generalization of the Hopfield model with a specific type of asymmetric synaptic connections. No time delay is introduced in signal transmission, in contrast to some of the recently proposed networks.

AB - We develop an argument that a neural network with asynchronous updating dynamics is capable of sequential retrieval of properly embedded spatial patterns. It is not necessary that the patterns be random, but they have to satisfy certain restrictions. The network is a generalization of the Hopfield model with a specific type of asymmetric synaptic connections. No time delay is introduced in signal transmission, in contrast to some of the recently proposed networks.

UR - http://www.scopus.com/inward/record.url?scp=0000154746&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0000154746&partnerID=8YFLogxK

U2 - 10.1103/PhysRevA.41.3346

DO - 10.1103/PhysRevA.41.3346

M3 - Article

VL - 41

SP - 3346

EP - 3354

JO - Physical Review A

JF - Physical Review A

SN - 2469-9926

IS - 6

ER -