Presentation 1997/3/17
An Associative Memory using Complex-Valued Neural Networks and It's Ability
N. Hashimoto, Y. Kuroe, Y. Mori,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) In this paper, we propose a model of associative memory with complex-valued neural networks and analyze it's ability. The proposed model is a complex associative memory of self association type with orthogonal vector as memory vector, and the correlation matrix as the weight matrix. The analysis is (done from the view point of stability of the memory pattern. A condition which assures that all the memory patterns are correctly recalled is obtained. By numerical experiments, we show the validity of the obtained analysis results.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) complex-valued neural network / associative memory / stability of memory patterns
Paper # NC96-122
Date of Issue

Conference Information
Committee NC
Conference Date 1997/3/17(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) An Associative Memory using Complex-Valued Neural Networks and It's Ability
Sub Title (in English)
Keyword(1) complex-valued neural network
Keyword(2) associative memory
Keyword(3) stability of memory patterns
1st Author's Name N. Hashimoto
1st Author's Affiliation Department of Electronics and Information Science Faculty of Engineering and Design Kyoto Institute of Technology()
2nd Author's Name Y. Kuroe
2nd Author's Affiliation Department of Electronics and Information Science Faculty of Engineering and Design Kyoto Institute of Technology
3rd Author's Name Y. Mori
3rd Author's Affiliation Department of Electronics and Information Science Faculty of Engineering and Design Kyoto Institute of Technology
Date 1997/3/17
Paper # NC96-122
Volume (vol) vol.96
Number (no) 583
Page pp.pp.-
#Pages 8
Date of Issue