New genetic approach to universal rule generation from trained neural networks

Minoru Fukumi, Yasue Mitsukura, Norio Akamatsu

研究成果: Paper査読

1 被引用数 (Scopus)


In this paper a new rule generation method from neural networks is presented. A neural network (NN) is formed using a genetic algorithm (GA) with virus infection and deterministic mutation to represent regularities in training data. This method utilizes a modular structure in GA. Each module learns a different neural network architecture, such as sigmoid and a higher order neural networks. Those chromosome information is communicated to the other modules by the virus infection. The higher order units are connected to an output unit or hidden units. By using these architectures, rules can be extracted. The results of computer simulations show that this approach can generate obvious, network architectures and as a result simple rules.

出版ステータスPublished - 2000 12月 1
イベント2000 TENCON Proceedings - Kuala Lumpur, Malaysia
継続期間: 2000 9月 242000 9月 27


Other2000 TENCON Proceedings
CityKuala Lumpur, Malaysia

ASJC Scopus subject areas

  • コンピュータ サイエンスの応用
  • 電子工学および電気工学


「New genetic approach to universal rule generation from trained neural networks」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。