Presentation 2000/6/15
Self-organization of information expression by sparse and random local excitation
Koji WADA, Koji KURATA,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) By introducing randomness to Mexican-hat type intralayer connections, we can make a nervfield which has random and sparse and local excitations as equilibrium states. We already succeeded, by applying SOM like learning rule to such nerv field, in coding the first nonlinear principal component of input signal by the position of local excitations and the second by difference in detail of local excitation patterns. In this paper we improved the model to code the second principal component by the position of local excitation.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) Kohonen's SOM / Principal component analysis / Random symmetric connection / Grand moher cell / Pattern representation
Paper # NLP2000-19,NC2000-13
Date of Issue

Conference Information
Committee NLP
Conference Date 2000/6/15(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) Self-organization of information expression by sparse and random local excitation
Sub Title (in English)
Keyword(1) Kohonen's SOM
Keyword(2) Principal component analysis
Keyword(3) Random symmetric connection
Keyword(4) Grand moher cell
Keyword(5) Pattern representation
1st Author's Name Koji WADA
1st Author's Affiliation Department of Systems and Human Science, Graduate School of Engineering Science, Osaka University()
2nd Author's Name Koji KURATA
2nd Author's Affiliation Department of Mechanical Systems Engineering, Faculty of Engineering, University of the Ryukyus
Date 2000/6/15
Paper # NLP2000-19,NC2000-13
Volume (vol) vol.100
Number (no) 124
Page pp.pp.-
#Pages 7
Date of Issue