| 作成者 |
|
|
|
| 本文言語 |
|
| 発行日 |
|
| 出版タイプ |
|
| アクセス権 |
|
| 関連DOI |
|
| 関連URI |
|
| 関連HDL |
|
| 概要 |
There have been a lot of researches which apply evolutionary techniques to layered neural networks. However, their applications to Hopfield neural networks remain few so far. We have been applying a g...enetic algorithm to fully connected associative memory model of Hopfield, and reported elsewhere that the network can store some number of patterns only by evolving weight matrices with the genetic algorithm. In this paper, we present that evolving both weight matrices and patterns to be stored results in the higher capacity of associative memory than in the case of fixed patterns above. From an Artificial Life perspective, the patterns to be stored are considered to be an environment.続きを見る
|
Mendeley出力
evolution-of-associative-memory