<会議発表論文>
Mutually Connected Neural Network Can Learn Some Patterns by Means of GA

作成者
本文言語
発行日
出版タイプ
アクセス権
関連URI
概要 We simulated an associative memory with mutually connected neural network, and successfully made the connection matrix learn some binary patterns only by means of generic algorithm. Although the memor...y capacity is about 12% of the number of neurons, the fact that it was made without any learning algorithm like Hebbian rule is very interesting. The structure of connection matrics we obtained is quite different from that of Hopfield network. Our overall goal for this research is two fold. One is to know if we can use generic algorithm as a more effective learning method than that proposed so far, and another is to understand this learning mechanism of generic algorithm.続きを見る

本文情報を非表示

imada95mutually pdf 100 KB 145  

詳細

レコードID
査読有無
主題
注記
タイプ
登録日 2009.04.22
更新日 2020.10.13