Training a kind of hybrid universal learning networks with classification problems

Dazi Li*, Kotaro Hirasawa, Jinglu Hu, Junichi Murata

*この研究の対応する著者

研究成果: Paper査読

抄録

In the search for even better parsimonious neural network modeling, this paper describes a novel approach which attempts to exploit redundancy found in the conventional sigmoidal networks. A hybrid universal learning network constructed by the combination of proposed multiplication units with summation units is trained for several classification problems. It is clarified that the multiplication units in different layers in the network improve the performance of the network.

本文言語English
ページ703-708
ページ数6
出版ステータスPublished - 2002 1 1
外部発表はい
イベント2002 International Joint Conference on Neural Networks (IJCNN '02) - Honolulu, HI, United States
継続期間: 2002 5 122002 5 17

Conference

Conference2002 International Joint Conference on Neural Networks (IJCNN '02)
国/地域United States
CityHonolulu, HI
Period02/5/1202/5/17

ASJC Scopus subject areas

  • ソフトウェア
  • 人工知能

フィンガープリント

「Training a kind of hybrid universal learning networks with classification problems」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