Presentation 1999/11/9
Associative memory for higher order neural networks with patterns correlated to each other
Shuji Yatsuki, Nobumitsu Toda, Hiromi Miyajima,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) In this paper, we analyze the ability of associative memory with patterns correlated to each other. Using second order neural networks, the dynamics of the network's state is not influenced by the distribution of patterns. As a result, it is shown that the ability of higher order neural networks is superior to one of the traditional model in the case where memorized patterns are correlated to each other.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) associative memory / neural networks / memory capacity / correlation learning
Paper # CST99-42
Date of Issue

Conference Information
Committee CST
Conference Date 1999/11/9(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 Concurrent System Technology (CST)
Language JPN
Title (in Japanese) (See Japanese page)
Sub Title (in Japanese) (See Japanese page)
Title (in English) Associative memory for higher order neural networks with patterns correlated to each other
Sub Title (in English)
Keyword(1) associative memory
Keyword(2) neural networks
Keyword(3) memory capacity
Keyword(4) correlation learning
1st Author's Name Shuji Yatsuki
1st Author's Affiliation Ube National College of Technology()
2nd Author's Name Nobumitsu Toda
2nd Author's Affiliation Ube National College of Technology
3rd Author's Name Hiromi Miyajima
3rd Author's Affiliation Fac. of Eng., Kagoshima University
Date 1999/11/9
Paper # CST99-42
Volume (vol) vol.99
Number (no) 418
Page pp.pp.-
#Pages 8
Date of Issue