Learning of Symbiotic Relations among Agents by Using Neural Networks - Collections | Kyushu University Library

Back to Results List

＜departmental bulletin paper＞
Learning of Symbiotic Relations among Agents by Using Neural Networks

Creator	Creator Name Hirasawa, Kotaro 平澤, 宏太郎ヒラサワ, コウタロウ Affiliation Affiliation Name Dept. of Electrical and Electronic Systems Engineering, Graduate School of Information Science and Electrical Engineering, Kyushu University 九州大学大学院システム情報科学研究科電気電子システム工学専攻
	Creator Name Yoshida, Hidemasa 吉田, 英正ヨシダ, ヒデマサ Affiliation Affiliation Name Dept. of Electrical and Electronic Systems Engineering, Graduate School of Information Science and Electrical Engineering, Kyushu University : Graduate Student 九州大学大学院システム情報科学研究科電気電子システム工学専攻
	Creator Name Hu, Jinglu 胡, 敬炉 Affiliation Affiliation Name Dept. of Electrical and Electronic Systems Engineering, Graduate School of Information Science and Electrical Engineering, Kyushu University 九州大学大学院システム情報科学研究科電気電子システム工学専攻
Language	English
Publisher	九州大学大学院システム情報科学研究院
Publisher	Faculty of Information Science and Electrical Engineering, Kyushu University
Date	2000-09-26
Source Title	Research reports on information science and electrical engineering of Kyushu University
Vol	5
Issue	2
First Page	215
Last Page	222
Publication Type	Version of Record
Access Rights	open access
JaLC DOI	https://doi.org/10.15017/1515686
Related DOI	https://portal.isee.kyushu-u.ac.jp/
Related URI	https://portal.isee.kyushu-u.ac.jp/
Relation	https://portal.isee.kyushu-u.ac.jp/
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.show more

Hide fulltext details.

File	FileType	Size	Views	Description
p215	pdf	757 KB	274

Details

PISSN	1342-3819
EISSN	2188-0891
NCID	AN10569524
Record ID	1515686
Peer-Reviewed	Refereed
Subject Terms	Symbiotic relation
	Learning
	Multi-agent
	Neural networks
	Complex systems
	Fuzzy systems
	Emergence
	RasID learning
Created Date	2015.05.18
Modified Date	2020.10.26