Sequential retrieval of non-random patterns in a neural network

Tota Nakamura, H. Nishimori

Research output: Contribution to journalArticle

2 Citations (Scopus)

Abstract

A neural network capable of retrieval of sequential patterns is analysed. The authors treat the network proposed by Buhmann and Schulten (1987). Although they concluded that the thermal noise induces retrieval of sequential patterns, the authors show that the network has limit cycle solutions even at zero temperature. Behaviour of the network at high temperatures is also analysed. The transition temperatures between a high-temperature fixed point phase and a limit cycle phase are calculated numerically to draw a phase diagram. The characteristic features of the phase diagram are discussed. The reentrant transition temperatures between the limit cycle and low-temperature fixed point phases are calculated analytically.

Original languageEnglish
Article number024
Pages (from-to)4627-4641
Number of pages15
JournalJournal of Physics A: Mathematical and General
Volume23
Issue number20
DOIs
Publication statusPublished - 1990
Externally publishedYes

Fingerprint

retrieval
Neural networks
cycles
Superconducting transition temperature
Phase diagrams
transition temperature
phase diagrams
Temperature
Thermal noise
thermal noise
temperature

ASJC Scopus subject areas

  • Statistical and Nonlinear Physics
  • Physics and Astronomy(all)
  • Mathematical Physics

Cite this

Sequential retrieval of non-random patterns in a neural network. / Nakamura, Tota; Nishimori, H.

In: Journal of Physics A: Mathematical and General, Vol. 23, No. 20, 024, 1990, p. 4627-4641.

Research output: Contribution to journalArticle

@article{df00d184412c425aafc60e0cfdc59b9d,
title = "Sequential retrieval of non-random patterns in a neural network",
abstract = "A neural network capable of retrieval of sequential patterns is analysed. The authors treat the network proposed by Buhmann and Schulten (1987). Although they concluded that the thermal noise induces retrieval of sequential patterns, the authors show that the network has limit cycle solutions even at zero temperature. Behaviour of the network at high temperatures is also analysed. The transition temperatures between a high-temperature fixed point phase and a limit cycle phase are calculated numerically to draw a phase diagram. The characteristic features of the phase diagram are discussed. The reentrant transition temperatures between the limit cycle and low-temperature fixed point phases are calculated analytically.",
author = "Tota Nakamura and H. Nishimori",
year = "1990",
doi = "10.1088/0305-4470/23/20/024",
language = "English",
volume = "23",
pages = "4627--4641",
journal = "Journal of Physics A: Mathematical and Theoretical",
issn = "1751-8113",
publisher = "IOP Publishing Ltd.",
number = "20",

}

TY - JOUR

T1 - Sequential retrieval of non-random patterns in a neural network

AU - Nakamura, Tota

AU - Nishimori, H.

PY - 1990

Y1 - 1990

N2 - A neural network capable of retrieval of sequential patterns is analysed. The authors treat the network proposed by Buhmann and Schulten (1987). Although they concluded that the thermal noise induces retrieval of sequential patterns, the authors show that the network has limit cycle solutions even at zero temperature. Behaviour of the network at high temperatures is also analysed. The transition temperatures between a high-temperature fixed point phase and a limit cycle phase are calculated numerically to draw a phase diagram. The characteristic features of the phase diagram are discussed. The reentrant transition temperatures between the limit cycle and low-temperature fixed point phases are calculated analytically.

AB - A neural network capable of retrieval of sequential patterns is analysed. The authors treat the network proposed by Buhmann and Schulten (1987). Although they concluded that the thermal noise induces retrieval of sequential patterns, the authors show that the network has limit cycle solutions even at zero temperature. Behaviour of the network at high temperatures is also analysed. The transition temperatures between a high-temperature fixed point phase and a limit cycle phase are calculated numerically to draw a phase diagram. The characteristic features of the phase diagram are discussed. The reentrant transition temperatures between the limit cycle and low-temperature fixed point phases are calculated analytically.

UR - http://www.scopus.com/inward/record.url?scp=36149035086&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=36149035086&partnerID=8YFLogxK

U2 - 10.1088/0305-4470/23/20/024

DO - 10.1088/0305-4470/23/20/024

M3 - Article

VL - 23

SP - 4627

EP - 4641

JO - Journal of Physics A: Mathematical and Theoretical

JF - Journal of Physics A: Mathematical and Theoretical

SN - 1751-8113

IS - 20

M1 - 024

ER -