表現型レベルの遺伝的操作を用いたニューラルネットワークの合成

• 佐藤 裕二

  日立製作所中央研究所

書誌事項

タイトル別名

• Phenotype Genetic Operation for Determining Neural Network Structure and Weights.

抄録

This paper describes a phenotype genetic operation for determining the structure and connection weights for neural networks. This technique defines the network as a two-dimensional chromosome, performs crossover using two-dimensional substructures, and application of genetic operation to both determining the network structure and training the connection weights. Using problems which partially involve Exclusive-OR logic, or training data that is partly dynamically changing, the proposed method is shown to be more effective than the standard genetic algorithms with one-point, two-point, or uniform crossover in the synthesis of neural networks that have two-dimensional building blocks.

収録刊行物

• 日本神経回路学会誌

  日本神経回路学会誌 4 (2), 62-73, 1997

  日本神経回路学会

キーワード

• evolutionary computation
• genetic algorithms
• schema theorem
• neural networks
• self-organization

詳細情報

• CRID: 1390001204465296256
• NII論文ID: 10008841294
• NII書誌ID: AA11658570
• DOI: 10.3902/jnns.4.62
• ISSN: 18830455
• ISSN: 1340766X
• 本文言語コード: ja
• データソース種別:
  • JaLC
  • Crossref
  • CiNii Articles
• 抄録ライセンスフラグ: 使用不可