Presentation	2000/10/14 On the Chaos Neurons and Invariant Measure Masahiro Nakagawa,
PDF Download Page	PDF download Page Link
Abstract(in Japanese)	(See Japanese page)
Abstract(in English)	We have shown hitherto the capability of the chaos associative model with a periodic activation function. In practice it has been noted that, from the application point of view, such a periodic chaos neuron has the great advantage such that the chaotic dynamics can be easily controlled in comparison with the conventional monotonous chaos neuron. In particular, the memory capacity has been found to be apparently larger than that of the conventional chaos associative memory with a monotonous activation function. In this report, we shall mention the relationship between the chaotic associative abillity from the viewpoint of the invariant measure of the chaos neuron with a sinusoidal activation function on the basis of the Frobenius-Perron equation.
Keyword(in Japanese)	(See Japanese page)
Keyword(in English)	Chaon Neurons / Associative Models / Frobenius-Perron Equation
Paper #	NLP2000-89
Date of Issue

Conference Information
Committee	NLP
Conference Date	2000/10/14(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)	On the Chaos Neurons and Invariant Measure
Sub Title (in English)
Keyword(1)	Chaon Neurons
Keyword(2)	Associative Models
Keyword(3)	Frobenius-Perron Equation
1st Author's Name	Masahiro Nakagawa
1st Author's Affiliation	Nagaoka University of Technology()
Date	2000/10/14
Paper #	NLP2000-89
Volume (vol)	vol.100
Number (no)	382
Page	pp.pp.-
#Pages	8
Date of Issue