Presentation 1993/11/24
Associative Memories Using Dynamical Neural Networks with Limit Cycles
Hiroshi Inaba, Kiyoshi Ishii,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) This paper studies associative memories using a dynamical neural network of the McCullough-Pitts model in which the given standard information patterns are assigned as limit cycles.First,some properties of the network with orthogonal connection matrix are presented and a method to construct a connection matrix which assigns standard pattern vectors as equilibrium point of the network in more general fashion is proposed.Further,a method to construct a connection matrix of the neural network which assigns limit cycles as required is studied and some results of computer simulation are given to evaluate the performance statistically.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) McCullough-Pitts model / Domain of Attraction / Limit Cycle
Paper # NC93-47
Date of Issue

Conference Information
Committee NC
Conference Date 1993/11/24(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) Associative Memories Using Dynamical Neural Networks with Limit Cycles
Sub Title (in English)
Keyword(1) McCullough-Pitts model
Keyword(2) Domain of Attraction
Keyword(3) Limit Cycle
1st Author's Name Hiroshi Inaba
1st Author's Affiliation Department of Information Sciences,Tokyo Denki University()
2nd Author's Name Kiyoshi Ishii
2nd Author's Affiliation Department of Information Sciences,Tokyo Denki University
Date 1993/11/24
Paper # NC93-47
Volume (vol) vol.93
Number (no) 341
Page pp.pp.-
#Pages 8
Date of Issue