DocumentCode
820907
Title
Alternating minimization and Boltzmann machine learning
Author
Byrne, William
Author_Institution
Dept. of Electr. Eng., Maryland Univ., College Park, MD, USA
Volume
3
Issue
4
fYear
1992
fDate
7/1/1992 12:00:00 AM
Firstpage
612
Lastpage
620
Abstract
Training a Boltzmann machine with hidden units is appropriately treated in information geometry using the information divergence and the technique of alternating minimization. The resulting algorithm is shown to be closely related to gradient descent Boltzmann machine learning rules, and the close relationship of both to the EM algorithm is described. An iterative proportional fitting procedure for training machines without hidden units is described and incorporated into the alternating minimization algorithm
Keywords
iterative methods; learning systems; minimisation; neural nets; Boltzmann machine learning; alternating minimization; hidden units; information divergence; information geometry; iterative proportional fitting; learning rules; neural nets; Information geometry; Iterative algorithms; Machine learning; Machine learning algorithms; Minimization methods; Neural networks; Particle measurements; Stochastic processes; Symmetric matrices; Temperature;
fLanguage
English
Journal_Title
Neural Networks, IEEE Transactions on
Publisher
ieee
ISSN
1045-9227
Type
jour
DOI
10.1109/72.143375
Filename
143375
Link To Document