Presentation 1994/5/20
Learning of chaos by nueral network and its bifurcation phenomena
Itaru Nagayama, Norio Akamatsu,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) In this paper,we show that the neural network can easily learn the chaos by Elman type recurrent architecture.The network is four layered feedback network(FFBN).The FFBN does not require any specific modification about learning algorithm and network dynamics.Also we show that the chaotic sequence of the FFBN can be controled by changing a network parameter.We indicate the bifurcation diagram of the FFBN which exhibits chaotic features. Furthermore,we show that Feigenbaum number is found in FFBN.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) neural network / chaos / feedback / bifurcation / Feigenbaum number
Paper # NLP94-15
Date of Issue

Conference Information
Committee NLP
Conference Date 1994/5/20(1days)
Place (in Japanese) (See Japanese page)
Place (in English)
Topics (in Japanese) (See Japanese page)
Topics (in English)
Chair
Vice Chair
Secretary
Assistant

Paper Information
Registration To Nonlinear Problems (NLP)
Language JPN
Title (in Japanese) (See Japanese page)
Sub Title (in Japanese) (See Japanese page)
Title (in English) Learning of chaos by nueral network and its bifurcation phenomena
Sub Title (in English)
Keyword(1) neural network
Keyword(2) chaos
Keyword(3) feedback
Keyword(4) bifurcation
Keyword(5) Feigenbaum number
1st Author's Name Itaru Nagayama
1st Author's Affiliation Department of Information science,Faculty of Engineering, University of Tokushima()
2nd Author's Name Norio Akamatsu
2nd Author's Affiliation Department of Information science,Faculty of Engineering, University of Tokushima
Date 1994/5/20
Paper # NLP94-15
Volume (vol) vol.94
Number (no) 45
Page pp.pp.-
#Pages 8
Date of Issue