Learning of symbiotic relations among agents by using neural networks

Kotaro Hirasawa, Hidemasa Yoshida, Jinglu Hu

Research output: Contribution to journalArticlepeer-review

Abstract

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.

Original languageEnglish
Pages (from-to)215-222
Number of pages8
JournalResearch Reports on Information Science and Electrical Engineering of Kyushu University
Volume5
Issue number2
Publication statusPublished - 2000 Sept 1
Externally publishedYes

ASJC Scopus subject areas

  • Computer Science(all)
  • Electrical and Electronic Engineering

Fingerprint

Dive into the research topics of 'Learning of symbiotic relations among agents by using neural networks'. Together they form a unique fingerprint.

Cite this