DocumentCode :
873895
Title :
Boltzmann Machines Reduction by High-Order Decimation
Author :
Farguell, Enric ; Mazzanti, Ferran ; Gomez-Ramirez, Eduardo
Author_Institution :
Eng. i Arquitectura La Salle, Univ. Ramon Llull, Barcelona
Volume :
19
Issue :
10
fYear :
2008
Firstpage :
1816
Lastpage :
1821
Abstract :
Decimation is a common technique in statistical physics that is used in the context of Boltzmann machines (BMs) to drastically reduce the computational cost at the learning stage. Decimation allows to analytically evaluate quantities that should otherwise be statistically estimated by means of Monte Carlo (MC) simulations. However, in its original formulation, this method could only be applied to restricted topologies corresponding to sparsely connected neural networks. In this brief, we present a generalization of the decimation process and prove that it can be used on any BM, regardless of its topology and connectivity. We solve the Monk problem with this algorithm and show that it performs as well as the best classification methods currently available.
Keywords :
Boltzmann machines; pattern classification; Boltzmann machines reduction; Monk problem; Monte Carlo simulations; high-order decimation; restricted topologies; sparsely connected neural networks; Boltzmann machines (BMs); decimation; neural networks; simulated annealing (SA); Algorithms; Computer Simulation; Feedback; Models, Theoretical; Neural Networks (Computer); Numerical Analysis, Computer-Assisted;
fLanguage :
English
Journal_Title :
Neural Networks, IEEE Transactions on
Publisher :
ieee
ISSN :
1045-9227
Type :
jour
DOI :
10.1109/TNN.2008.2003249
Filename :
4633685
Link To Document :
بازگشت