当システム
  詳細検索
Japanese | English 

Nara Women's University Digital Information Repository > 020 理学部 > 学外刊行物(理学部) > 雑誌 >

このアイテムのファイル:

ファイル 記述 サイズ形式
AA00704814_v84n1_pp014002.pdf1.02 MBAdobe PDF見る/開く
タイトル: Unlearning of Mixed States in the Hopfield Model : Finite Loading Case
著者: Ohtani, Haruka; Yoshida, Midori; Kiyokawa, Shuji; Uezu, Tatsuya link image
著者(別表記) : 大谷, 遥; 吉田, 緑; 清川, 修二; 上江洌, 達也
著者読み: おおたに, はるか; よしだ, みどり; きよかわ, しゅうじ; うえず, たつや
キーワード: unlearning of mixed states; Hopfield model
発行日: 2015年 1月
出版者: The Physical Society of Japan
引用: H.Otani, M.Yoshida, S.Kiyokawa, T.Uezu: Journal of the Physical Society of Japan, Vol.84(1), pp014002
抄録: We study the unlearning of mixed states in the Hopfield model for the finite loading case, that is, α = p/N ≪ 1, where N and p are the numbers of neurons and embedded patterns, respectively. In the general situation that any number of mixed states that exist in the model is unlearned, we derive the saddle point equations (SPEs) and evolution equations for overlaps by introducing sublattices. We postulate a condition that the solutions are stable in equilibrium, and prove that the static and dynamic stabilities are the same. We also prove that the stable state of the Hopfield model continuously changes and is statically and dynamically stable for sufficiently small unlearning coefficients. For p = 3, we perform detailed theoretical and numerical calculations. In the case that a single mixed state is unlearned, we determine phase boundaries using the Hessian matrix and by numerically integrating evolution equations. We performed Markov chain Monte Carlo simulations and find that the simulation results agree with the theoretical ones reasonably well. For general p, when all of the mixed states are unlearned with an equal unlearning coefficient η, we derive the formulae for critical unlearning coefficients at the temperature T = 0 below which embedded patterns and mixed states exist and are stable as solutions of the SPEs. We found that there is an unlearning region of (T,η) in which all patterns are retained and all mixed states are deleted, although tuning the parameters in this region is more difficult as p increases since the region shrinks. We numerically confirmed the theoretical results of the p dependences of the critical unlearning coefficients.
記述: 本論文の著作権は一般社団法人日本物理学会(The Physical Society of Japan)が保有しています。
???metadata.dc.relation.doi???: http://dx.doi.org/10.7566/JPSJ.84.014002
URI: http://hdl.handle.net/10935/3917
ISSN: 1347-4073
出現コレクション:雑誌

このアイテムの引用には次の識別子を使用してください: http://hdl.handle.net/10935/3917

当システムに保管されているアイテムはすべて著作権により保護されています。

 

Valid XHTML 1.0! DSpace Software Copyright © 2002-2006 MIT and Hewlett-Packard - ご意見をお寄せください