Associative Memory Model with Forgetting Process Using Nonmonotonic Neurons

スポンサーリンク

概要

• 論文の詳細を見る

• An associative memory model with a forgetting process a la Mezard et al. is investigated for a piecewise non-monotonic output function by the SCSNA proposed by Shiino and Fukai. Similar to the formal monotonic two-state model analyzed by Mezard et al., the discussed nonmonotonic model is also free from a catastrophic deterioration of memory due to overloading. We theoretically obtain a relationship between the storage capacity and the forgetting rate, and find that there is an optimal value of forgetting rate, at which the storate capacity is maximized for the given nonmonotonicity. The maximal storage capacity and capacity ratio (a ratio of the storage capacity for the conventional correlation learning rule to the maximal storage capacity) increase with nonmonotonicity, whereas the optimal forgetting rate decreases with nonmonotonicity.

• 社団法人電子情報通信学会の論文
• 1998-11-25

著者

• Okada M

  Riken Wako‐shi Jpn

• Kurata Koji

  The Authors Are With The Department Of Systems And Human Science Graduate School Of Engineering Scie

• MIMURA Kazushi

  The authors are with the Department of Systems and Human Science, Graduate School of Engineering Sci

• OKADA Masato

  The author is with Kawato Dynamic Brain Project, ERATO, Japan Science and Technology Corporation (JS

• Mimura Kazushi

  The Authors Are With The Department Of Systems And Human Science Graduate School Of Engineering Scie

関連論文

• Associative Memory Model with Forgetting Process Using Nonmonotonic Neurons
• Robustness to Noise of Associative Memory Using Nonmonotonic Analogue Neurons

スポンサーリンク