The high-order Boltzmann machine: learned distribution and topology

Author

Albizuri, F.X. ; Anjou, A.D. ; Grana, M. ; Torrealdea, J. ; Hernandez, M.C.

Author_Institution

Dept. of Comput. Sci. & Artificial Intelligence, Univ. of the Basqie Country, Sebastian, Spain

Volume

6

Issue

3

fYear

1995

fDate

5/1/1995 12:00:00 AM

Firstpage

767

Lastpage

770

Abstract

In this paper we give a formal definition of the high-order Boltzmann machine (BM), and extend the well-known results on the convergence of the learning algorithm of the two-order BM. From the Bahadur-Lazarsfeld expansion we characterize the probability distribution learned by the high order BM. Likewise a criterion is given to establish the topology of the BM depending on the significant correlations of the particular probability distribution to be learned

Keywords

Boltzmann machines; convergence; learning (artificial intelligence); pattern recognition; probability; topology; Bahadur-Lazarsfeld expansion; convergence; high-order Boltzmann machine; learning algorithm; neural networks; probability distribution; statistical pattern recognition; stochastic network; topology; Computer science education; Convergence; Educational institutions; Machine learning; Network topology; Neural networks; Pattern recognition; Probability distribution; Stochastic processes; Temperature;

fLanguage

English

Journal_Title

Neural Networks, IEEE Transactions on

Publisher

ieee

ISSN

1045-9227

Type

jour

DOI

10.1109/72.377984

Filename

377984