Generalization by neural networks

The authors discuss the requirements of learning for generalization, where the traditional methods based on gradient descent have limited success. A stochastic learning algorithm based on simulated annealing in weight space is presented. The authors verify the convergence properties and feasibility...

Full description

Saved in:
Bibliographic Details
Published inIEEE transactions on knowledge and data engineering Vol. 4; no. 2; pp. 177 - 185
Main Authors Shekhar, S., Amin, M.B.
Format Journal Article
LanguageEnglish
Published IEEE 01.04.1992
Subjects
Algorithm design and analysis
Annealing
Backpropagation algorithms
Convergence
Curve fitting
Handwriting recognition
Neural networks
Noise shaping
Stochastic processes
Testing
Online AccessGet full text

Cover

More Information
Summary:The authors discuss the requirements of learning for generalization, where the traditional methods based on gradient descent have limited success. A stochastic learning algorithm based on simulated annealing in weight space is presented. The authors verify the convergence properties and feasibility of the algorithm. An implementation of the algorithm and validation experiments are described.< >
Bibliography:ObjectType-Article-2
SourceType-Scholarly Journals-1
ObjectType-Feature-1
content type line 23
ISSN:1041-4347
1558-2191
DOI:10.1109/69.134256