Learning of symbiotic relations among agents by using neural networks

Kotaro Hirasawa, Hidemasa Yoshida, Jinglu Hu

研究成果: Article査読

抄録

Symbiotic relation among the agents is regarded as one of the most basic relations in the complex systems. In this paper, a method for constructing the required symbiotic relations among the agents is proposed, where the agent is made up of a hierarchical neural network and its parameters are trained in order to realize the required symbiotic relations. From the simulations of the ecosystem, where the agent corresponds to the species, it has been cleared that the proposed method can give the ecosystem model with more flexible and more powerful representation abilities than the conventional Lotka-Volterra model.

本文言語English
ページ(範囲)215-222
ページ数8
ジャーナルResearch Reports on Information Science and Electrical Engineering of Kyushu University
5
2
出版ステータスPublished - 2000 9月 1
外部発表はい

ASJC Scopus subject areas

  • コンピュータ サイエンス(全般)
  • 電子工学および電気工学

フィンガープリント

「Learning of symbiotic relations among agents by using 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。

引用スタイル