Hybrid Universal Learning Networks.

• Li Dazi

  Graduate School of Information Science and Electrical Eng., Kyushu University

• Hirasawa Kotaro

  Graduate School of Information, Production and Systems, Waseda University

• Hu Jinglu

  Graduate School of Information Science and Electrical Eng., Kyushu University

• Murata Junichi

  Graduate School of Information Science and Electrical Eng., Kyushu University

抄録

A variety of neuron models combine the neural inputs through their summation and sigmoidal functions.<br>Such structure of neural networks leads to shortcomings such as a large number of neurons in hidden layers and huge training data required. We introduce a kind of multiplication neuron which multiplies their inputs instead of summing to overcome the above problems. A hybrid universal learning network constructed by the combination of multiplication units and summation units is proposed and trained for several well known benchmark problems. Different combinations of the above two are tried. It is clarified that multiplication is an essential computational element in many cases and the combination of the multiplication units with summation units in different layers in the networks improved the performance of the network.

収録刊行物

• 電気学会論文誌Ｃ（電子・情報・システム部門誌）

  電気学会論文誌Ｃ（電子・情報・システム部門誌） 123 (3), 552-559, 2003

  一般社団法人 電気学会

キーワード

• hybrid Universal Learning Networks
• multiplication units
• summation units

詳細情報

• CRID: 1390001204606306176
• NII論文ID: 130000089349
• NII書誌ID: AN10065950
• DOI: 10.1541/ieejeiss.123.552
• ISSN: 13488155
• ISSN: 03854221
• NDL書誌ID: 6480679
• Web Site: https://ndlsearch.ndl.go.jp/books/R000000004-I6480679
• Web Site: http://www.jstage.jst.go.jp/article/ieejeiss/123/3/123_3_552/_pdf
• 本文言語コード: en
• データソース種別:
  • JaLC
  • NDL
  • Crossref
  • CiNii Articles
• 抄録ライセンスフラグ: 使用不可