Presentation 2011-12-20
Complex-valued Multilayer Perceptron Search Utilizing Eigen Vector Descent and Reducibility Mapping
Shinya SUZUMURA, Ryohei NAKANO,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) A complex-valued multilayer perceptron (MLP) can approximate a periodic or unbounded function, which cannot be easily realized by a real-valued MLP. The complex-valued MLP search space is, like a real-valued one, full of crevasse-like forms having huge condition numbers; thus, it is very hard for existing methods to perform efficient search in the space. The space also includes the structure of reducibility mapping. The paper proposes a new search method for a complex-valued MLP, which employs both eigen vector descent and reducibility mapping search. Our experiments showed the proposed method worked well.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) complex-valued multilayer perceptron / search method / search space / eigen vector / reducibility mapping
Paper # NC2011-88
Date of Issue

Conference Information
Committee NC
Conference Date 2011/12/13(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) Complex-valued Multilayer Perceptron Search Utilizing Eigen Vector Descent and Reducibility Mapping
Sub Title (in English)
Keyword(1) complex-valued multilayer perceptron
Keyword(2) search method
Keyword(3) search space
Keyword(4) eigen vector
Keyword(5) reducibility mapping
1st Author's Name Shinya SUZUMURA
1st Author's Affiliation Chubu University()
2nd Author's Name Ryohei NAKANO
2nd Author's Affiliation Chubu University
Date 2011-12-20
Paper # NC2011-88
Volume (vol) vol.111
Number (no) 368
Page pp.pp.-
#Pages 6
Date of Issue