Presentation 1996/7/24
Mechanism of Self-excitatory Oscillation in Neural Networks
Hideki Hayashi, Yoichi Okabe,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) Creature has several kinds of self-excitatory oscillation in his Neural Networks(NN). We have analyzed/simulated structure and synapse weight of NN to find the following mechanism : -Constant frequency oscillation by simple loop NN -Variable frequency oscillation by multi-loop NN Characteristic equation and sensitivity of eigen value are induced in a general mathematical expression, showing multi-oscillation in 4-neuron systems. We also show the outline of new learning algorithm ("Co-oscillation Model") based on "moderationism with moderate frequency".
Keyword(in Japanese) (See Japanese page)
Keyword(in English) Neural Network / oscillation / characteristic equation / moderationism / self-organization / co-oscillation model
Paper # NC96-22
Date of Issue

Conference Information
Committee NC
Conference Date 1996/7/24(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 Neurocomputing (NC)
Language JPN
Title (in Japanese) (See Japanese page)
Sub Title (in Japanese) (See Japanese page)
Title (in English) Mechanism of Self-excitatory Oscillation in Neural Networks
Sub Title (in English)
Keyword(1) Neural Network
Keyword(2) oscillation
Keyword(3) characteristic equation
Keyword(4) moderationism
Keyword(5) self-organization
Keyword(6) co-oscillation model
1st Author's Name Hideki Hayashi
1st Author's Affiliation Toshiba Corp.,:Research Center for Advanced Science and Technology()
2nd Author's Name Yoichi Okabe
2nd Author's Affiliation Research Center for Advanced Science and Technology
Date 1996/7/24
Paper # NC96-22
Volume (vol) vol.96
Number (no) 178
Page pp.pp.-
#Pages 8
Date of Issue