Presentation 1997/2/6
Leaming performance of a neural network using a renewal mechanism with a threshold
Yoshiyuki Matsuura, Yoshihiro Hayakawa, Kouji Nakajima, Yasuji Sawada,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) The efficiency of learning algorithm should be researched, when we use a neural network as an information processing machine. In this study, we propose a threshold renewal mechanism based on Deterministic Boltzmann Machine(DBM) leaming algorithm, and investigate the leaming performance of a neural network with the algorithm. As a result, the average of the updating accumulation of synapse weight is decreased by the factor 1/2-1/5 compared to that in ordinary DBM alghrithm.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) neural network / learning algorithm / threshold
Paper # NLP96-129,NC96-83
Date of Issue

Conference Information
Committee NC
Conference Date 1997/2/6(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 Neurocomputing (NC)
Language JPN
Title (in Japanese) (See Japanese page)
Sub Title (in Japanese) (See Japanese page)
Title (in English) Leaming performance of a neural network using a renewal mechanism with a threshold
Sub Title (in English)
Keyword(1) neural network
Keyword(2) learning algorithm
Keyword(3) threshold
1st Author's Name Yoshiyuki Matsuura
1st Author's Affiliation Institute of Electrical Communication, Tohoku University()
2nd Author's Name Yoshihiro Hayakawa
2nd Author's Affiliation Institute of Electrical Communication, Tohoku University
3rd Author's Name Kouji Nakajima
3rd Author's Affiliation Institute of Electrical Communication, Tohoku University
4th Author's Name Yasuji Sawada
4th Author's Affiliation Institute of Electrical Communication, Tohoku University
Date 1997/2/6
Paper # NLP96-129,NC96-83
Volume (vol) vol.96
Number (no) 511
Page pp.pp.-
#Pages 7
Date of Issue