DocumentCode
1167080
Title
Integration of magnified gradient function and weight evolution with deterministic perturbation into back-propagation
Author
Ng, Sin-Chun ; Cheung, Chi-Chung ; Leung, Shu-hung
Author_Institution
Sch. of Sci. & Technol., Open Univ. of Hong Kong, Kowloon, China
Volume
39
Issue
5
fYear
2003
fDate
3/6/2003 12:00:00 AM
Firstpage
447
Lastpage
448
Abstract
An integrated approach of magnified gradient function and weight evolution with deterministic perturbation to improve the performance of back-propagation learning is proposed. Simulation results show that, in terms of the convergence rate and the percentage of global convergence, the integrated approach always outperforms the other traditional methods.
Keywords
backpropagation; convergence; back-propagation algorithm; backpropagation learning; convergence rate; deterministic perturbation; global convergence; magnified gradient function; performance improvement; weight evolution;
fLanguage
English
Journal_Title
Electronics Letters
Publisher
iet
ISSN
0013-5194
Type
jour
DOI
10.1049/el:20030277
Filename
1190005
Link To Document