An Improvement of Neural Networks Applied to Pharmaceutical Problems.

• SATO Kenichi

• NAKAGAWA Junko

書誌事項

タイトル別名

• Improvement of Neural Networks Applied

抄録

In applying the neural network to the classification problem in pharmacology, we adopt an extended back-propagation (EBP) learning which adjusts the parameters appearing in an activation function, as well as the weights. The results of simulations show that such an extended learning speeds up the learning process as compared with the conventional basic back-propagation procedure, irrespective of the initial values of the parameters, which is extremely useful in the practical application of the neural network in the pharmaceutical field. We have also found that use of Morita's activation function beyond the sigmoid type further accelerates the EBP learning in some cases.

収録刊行物

• ＣＨＥＭＩＣＡＬ　＆　ＰＨＡＲＭＡＣＥＵＴＩＣＡＬ　ＢＵＬＬＥＴＩＮ

  ＣＨＥＭＩＣＡＬ　＆　ＰＨＡＲＭＡＣＥＵＴＩＣＡＬ　ＢＵＬＬＥＴＩＮ 45 (1), 107-115, 1997

  公益社団法人 日本薬学会

キーワード

• neural network
• extended back-propagation
• classification problem
• Morita's activation function

詳細情報

• CRID: 1390282679139027584
• NII論文ID: 130003947168
• NII論文ID: 110003616376
• NII書誌ID: AA00602100
• DOI: 10.1248/cpb.45.107
• COI: 1:CAS:528:DyaK2sXotFSltg%3D%3D
• ISSN: 13475223
• ISSN: 00092363
• ISSN: http://id.crossref.org/issn/00092363
• NDL書誌ID: 4121829
• PubMed: 9023972
• Web Site: https://ndlsearch.ndl.go.jp/books/R000000004-I4121829
• Web Site: http://www.jstage.jst.go.jp/article/cpb1958/45/1/45_1_107/_pdf
• 本文言語コード: en
• データソース種別:
  • JaLC
  • NDL
  • Crossref
  • PubMed
  • CiNii Articles
• 抄録ライセンスフラグ: 使用不可