Presentation 2010-12-13
Influence of correlated patterns in dynamical associative network using SVM
Akinori KATO, Masaharu ADACHI,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) In this paper, we investigate influence of correlated patterns in dynamical associative network using nonlinear SVM. Recall performance of dynamical associative memory is improved by using nonlinear Support Vector Machines (SVMs) instead of linear SVMs [1]. We introduce chaotic model neurons as the constituents of the associative memory model with nonlinear SVMs. Numerical experiments show that the high recall frequency with orbital instability can be realized even if there are correlations among stored patterns.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) Support Vector Machine / Dynamical Associative Memory / Chaotic Neural Network
Paper # NLP2010-117
Date of Issue

Conference Information
Committee NLP
Conference Date 2010/12/6(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) Influence of correlated patterns in dynamical associative network using SVM
Sub Title (in English)
Keyword(1) Support Vector Machine
Keyword(2) Dynamical Associative Memory
Keyword(3) Chaotic Neural Network
1st Author's Name Akinori KATO
1st Author's Affiliation Department of Electrical and Electronic Engineering, Graduate School of Engineering, Tokyo Denki University()
2nd Author's Name Masaharu ADACHI
2nd Author's Affiliation Department of Electrical and Electronic Engineering, Graduate School of Engineering, Tokyo Denki University
Date 2010-12-13
Paper # NLP2010-117
Volume (vol) vol.110
Number (no) 335
Page pp.pp.-
#Pages 6
Date of Issue