Presentation 2011-07-25
Optimization of the Sparsely Encoded Associative Memory Model with Forgetting Process by the Mutual Information.
Jun TSUZURUGI, Ryouta MIYATA, Kouji KURATA,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) According to the previous researches, the associative memory model with forgetting process could avoid overloading due to exponential decay of its connection weights at each learning step for embedding a new pattern. However, the previous researches decided whether the network could retrieve the stored pattern correctly in an arbitrary manner, in other words, the dirrection cosine between the memory pattern and the stationary state of the network. Recently, it has been shown that the mutual information should be the most appropriate concept to measure the retrieval quality, especially for sparsely encoded networks but also in general. In this paper, from the view of information theory, we analyze the sparsely encoded associative memory model with forgetting process. We searched the optimal decay rate to maximize the mutual information at each ring rate by the numerical simulations. Moreover, we compare optimization of the decay rate utilizing mutual information with the ordinary one utilizing the direction cosine.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) Associative Memory Mode / Sparsely Encoded / Mutual Information / Forgetting Process / Optimization
Paper # NC2011-21
Date of Issue

Conference Information
Committee NC
Conference Date 2011/7/18(1days)
Place (in Japanese) (See Japanese page)
Place (in English)
Topics (in Japanese) (See Japanese page)
Topics (in English)
Chair
Vice Chair
Secretary
Assistant

Paper Information
Registration To Neurocomputing (NC)
Language JPN
Title (in Japanese) (See Japanese page)
Sub Title (in Japanese) (See Japanese page)
Title (in English) Optimization of the Sparsely Encoded Associative Memory Model with Forgetting Process by the Mutual Information.
Sub Title (in English)
Keyword(1) Associative Memory Mode
Keyword(2) Sparsely Encoded
Keyword(3) Mutual Information
Keyword(4) Forgetting Process
Keyword(5) Optimization
1st Author's Name Jun TSUZURUGI
1st Author's Affiliation Okayama University of Science Faculty of Engineering Department of Intelligent Mechanical Engineering()
2nd Author's Name Ryouta MIYATA
2nd Author's Affiliation Interdisciplinary Graduate School of Science and Engineering, Tokyo Institute of Technology
3rd Author's Name Kouji KURATA
3rd Author's Affiliation Faculty of Engineering University of the Ryukyus
Date 2011-07-25
Paper # NC2011-21
Volume (vol) vol.111
Number (no) 157
Page pp.pp.-
#Pages 4
Date of Issue