DocumentCode :
1046060
Title :
New learning strategies from the microscopic level of an artificial neural network
Author :
Joya, G. ; Frias, J.J. ; Mar Marin, M. ; Sandoval, F.
Author_Institution :
Dept. de Arquitectura y Tecnologia de Computadores y Electron., Malaga Univ., Spain
Volume :
29
Issue :
20
fYear :
1993
Firstpage :
1775
Lastpage :
1777
Abstract :
New learning strategies deduced from a microscopic level study of the weights space of an artificial neural network (ANN) are presented. These strategies improve the efficiency of learning algorithms, reducing the amount of patterns to be presented to the ANN.
Keywords :
learning (artificial intelligence); neural nets; artificial neural network; efficiency; learning algorithms; learning strategies; microscopic level; weights space;
fLanguage :
English
Journal_Title :
Electronics Letters
Publisher :
iet
ISSN :
0013-5194
Type :
jour
DOI :
10.1049/el:19931182
Filename :
274910
Link To Document :
بازگشت