Efficient implementation of the Boltzmann machine algorithm

Author

DeGloria, A. ; Faraboschi, P. ; Olivieri, M.

Author_Institution

Dept. of Biophys. & Electr. Eng., Genoa Univ., Italy

Volume

4

Issue

1

fYear

1993

fDate

1/1/1993 12:00:00 AM

Firstpage

159

Lastpage

163

Abstract

The problem of optimizing the sequential algorithm for the Boltzmann machine (BM) is addressed. A solution that is based on the locality properties of the algorithm and makes possible the efficient computation of the cost difference between two configurations is presented. Since the algorithm performance depends on the number of accepted state transitions in the annealing process, a theoretical procedure is formulated to estimate the acceptance probability of a state transition. In addition, experimental data are provided on a well-known optimization problem travelling salesman problem to have a numerical verification of the theory, and to show that the proposed solution obtains a speedup between 3 and 4 in comparison with the traditional algorithm

Keywords

Boltzmann machines; parallel algorithms; probability; simulated annealing; Boltzmann machine; neural nets; optimization; sequential algorithm; simulated annealing; state transition; state transitions; Annealing; Computational efficiency; Estimation theory; Hardware; Knowledge representation; Neural networks; Neurons; Runtime; Software algorithms; State estimation;

fLanguage

English

Journal_Title

Neural Networks, IEEE Transactions on

Publisher

ieee

ISSN

1045-9227

Type

jour

DOI

10.1109/72.182711

Filename

182711