Training a kind of hybrid universal learning networks with classification problems

Dazi Li, Kotaro Hirasawa, Jinglu Hu, Junichi Murata

研究成果: Chapter in Book/Report/Conference proceedingConference contribution

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.

本文言語英語
ホスト出版物のタイトルProceedings of the International Joint Conference on Neural Networks
ページ703-708
ページ数6
1
出版ステータス出版済み - 2002
イベント2002 International Joint Conference on Neural Networks (IJCNN '02) - Honolulu, HI, 米国
継続期間: 5 12 20025 17 2002

その他

その他2002 International Joint Conference on Neural Networks (IJCNN '02)
Country米国
CityHonolulu, HI
Period5/12/025/17/02

All Science Journal Classification (ASJC) codes

  • Software
  • Artificial Intelligence

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