A localized learning rule for analog VLSI implementation of neural networks

Hiroyuki Wasaki, Yoshihiko Horio, Shogo Nakamura

研究成果: Conference contribution

1 被引用数 (Scopus)

抄録

A modified Hebbian type learning rule for self-organization which uses only the local information is proposed. As the result of computer simulations of self-organizing networks, the validity of the rule was confirmed and learning speed was improved. Furthermore, circuit examples for implementing the learning rule are proposed.

本文言語English
ホスト出版物のタイトルMidwest Symposium on Circuits and Systems
出版社Publ by IEEE
ページ17-20
ページ数4
ISBN(印刷版)0780300815
出版ステータスPublished - 1991 12 1
外部発表はい
イベント33rd Midwest Symposium on Circuits and Systems - Calgary, Alberta, Can
継続期間: 1990 8 121990 8 15

出版物シリーズ

名前Midwest Symposium on Circuits and Systems
1

Other

Other33rd Midwest Symposium on Circuits and Systems
CityCalgary, Alberta, Can
Period90/8/1290/8/15

ASJC Scopus subject areas

  • 電子材料、光学材料、および磁性材料
  • 電子工学および電気工学

フィンガープリント

「A localized learning rule for analog VLSI implementation of neural networks」の研究トピックを掘り下げます。これらがまとまってユニークなフィンガープリントを構成します。

引用スタイル