Neural networks with input gates

Junichi Murata, Tetsushi Noda, Kotaro Hirasawa

研究成果: ジャーナルへの寄稿学術誌査読

抄録

An architecture of multi layer neural networks is proposed. The networks are equipped with gates on their input channels to control flow of the input signals. A gate on an input channel opens and closes depending on the current values of the other input signals. The dependency is automatically determined based on training data so that the gate opens when the corresponding input is necessary and closed when not necessary. These gates give the networks a good generalization ability because they can eliminate harmful inputs. And they provides us with an insight into the input-output relationship since they can indicate which input is significant in what situation.

本文言語英語
ページ(範囲)283-288
ページ数6
ジャーナルResearch Reports on Information Science and Electrical Engineering of Kyushu University
2
2
出版ステータス出版済み - 9月 1997

!!!All Science Journal Classification (ASJC) codes

  • コンピュータサイエンス一般
  • 電子工学および電気工学

フィンガープリント

「Neural networks with input gates」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