Retrieval Property of Associative Memory Based on Inverse Function Delayed Neural Networks(Nonlinear Problems)

• LI Hongge

  Laboratory for Brainware Systems, Laboratory for Nanoelectronics and Spintronics, Research Institute of Electrical Communication, Tohoku University

• HAYAKAWA Yoshihiro

  Laboratory for Brainware Systems, Laboratory for Nanoelectronics and Spintronics, Research Institute of Electrical Communication, Tohoku University

• NAKAJIMA Koji

  Laboratory for Brainware Systems, Laboratory for Nanoelectronics and Spintronics, Research Institute of Electrical Communication, Tohoku University

抄録

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.

収録刊行物

• IEICE transactions on fundamentals of electronics, communications and computer sciences

  IEICE transactions on fundamentals of electronics, communications and computer sciences 88 (8), 2192-2199, 2005-08-01

  一般社団法人電子情報通信学会

キーワード

• associative memory
• inverse function delayed model
• retrieval dynamics
• basin of attraction
• negative resistance

詳細情報

• CRID: 1573668925024024192
• NII論文ID: 10016781872
• NII書誌ID: AA10826239
• ISSN: 09168508
• 本文言語コード: en
• データソース種別:
  • CiNii Articles