DocumentCode
3635080
Title
Supervised learning in linear neural networks by a pseudogradient algorithm
Author
V. Tadic;S. Stankovic
Author_Institution
Autom. Control Lab., Mihailo Pupin Inst., Belgrade, Yugoslavia
fYear
1996
Firstpage
84
Lastpage
91
Abstract
A normalization based pseudogradient algorithm has been proposed for learning in linear neural networks. Its WP1 convergence has been proved and practical efficiency has been demonstrated by simulation.
Keywords
"Supervised learning","Intelligent networks","Neural networks","Convergence","Algorithm design and analysis","Automatic control","Laboratories","Electronic mail","Computational modeling","Computer simulation"
Publisher
ieee
Conference_Titel
Neural Networks for Identification, Control, Robotics, and Signal/Image Processing, 1996. Proceedings., International Workshop on
Print_ISBN
0-8186-7456-3
Type
conf
DOI
10.1109/NICRSP.1996.542748
Filename
542748
Link To Document