Retrieval property of associative memory based on inverse function delayed neural networks

Hongge Li, Yoshihiro Hayakawa, Koji Nakajima

Research output: Contribution to journalArticlepeer-review

7 Citations (Scopus)

Abstract

Self-connection can enlarge the memory capacity of an associative memory based on the neural network. However, the basin size of the embedded memory state shrinks. The problem of basin size is related to undesirable stable states which are spurious. If we can destabilize these spurious states, we expect to improve the basin size. The inverse function delayed (ID) model, which includes the Bonhoeffer-van der Pol (BVP) model, has negative resistance in its dynamics. The negative resistance of the ID model can destabilize the equilibrium states on certain regions of the conventional neural network. Therefore, the associative memory based on the ID model, which has self-connection in order to enlarge the memory capacity, has the possibility to improve the basin size of the network. In this paper, we examine the fundamental characteristics of an associative memory based on the ID model by numerical simulation and show the improvement of performance compared with the conventional neural network.

Original languageEnglish
Pages (from-to)2192-2198
Number of pages7
JournalIEICE Transactions on Fundamentals of Electronics, Communications and Computer Sciences
VolumeE88-A
Issue number8
DOIs
Publication statusPublished - 2005 Aug

Keywords

  • Associative memory
  • Basin of attraction
  • Inverse function delayed model
  • Negative resistance
  • Retrieval dynamics

ASJC Scopus subject areas

  • Signal Processing
  • Computer Graphics and Computer-Aided Design
  • Electrical and Electronic Engineering
  • Applied Mathematics

Fingerprint Dive into the research topics of 'Retrieval property of associative memory based on inverse function delayed neural networks'. Together they form a unique fingerprint.

Cite this