« Combinatorial Problem Solving Using Randomized Dynamic Composition of Production Rules | メイン | Constraint Satisfaction by Parallel Optimization of Local Evaluation Functions with Annealing »

Constraint Satisfaction Using Neural Networks with a Local and Autonomous Annealing Technique

Kanada, Y., 未出版, 1996.

[ English page ]
[ 論文 PDF ファイル ] [ 論文 ポストスクリプト ファイル ]

要旨 (英語のみ): A method for solving large-scale constraint satisfaction problems using an annealed symmetrically-connected neural network, which is called DSN-FAM, is proposed in the present paper. Some conventional methods, such as Hopfield networks, often fail to find a solution. Some others, such as Boltzmann Machines, take too much time. These difficulties are solved by a type of annealing technique, which we call the frustration accumulation method (FAM). DSN-FAM works only with local information, and no global functions or global parameters such as a temperature are used. DSN-FAM thus works autonomously. That is, no external control is necessary while operating. Experiments show that this method does not fail to find a solution and the execution time is less than one tenth of Boltzmann Machines. The performance can be easily and almost linearly improved by parallel processing using tens of processors.

研究テーマ紹介: CCM: 化学的計算のモデル

キーワード: CCM, ニューラル・ネットワーク, ニューラルネットワーク, 制約充足問題, ランダム化計算, ランダム化問題解決, ランダマイズド計算, ランダマイズド問題解決, 規則ベース計算, 規則ベース問題解決, ルールベース計算, ルールベース問題解決, アニーリング, FAM, フラストレーション蓄積法



1996-01-01 00:00に投稿されたエントリーのページです。


(C) 2008 by Yasusi Kanada
Powered by
Movable Type 3.36