ANALYSIS OF THE SIMULATED ANNEALING METHOD IN CLASSIC BOLTZMANN MACHINES
DOI:
https://doi.org/10.17770/etr1997vol1.1857Keywords:
Boltzmann machine, Recurrent networks, learning algorithm, simulated annealingAbstract
The paper analyses a model of a neural net proposed by Hinton et al (1985). They have added noise to a Hopfield net and have called it Boltzmann machine (BM) drawing an analogy with the behaviour of physical systems with noises. The concept of simulated annealing is analysed. The experiment aimed at testing the state of thermal equilibrium for a Boltzmann net with three neurons, specified threshold values and weights at two different temperatures, T=1 and T=0,25, is described.Downloads
References
Ackley D. H, Hinton G. E and Sejnowski T. J. A learning algorithm for Boltzmann machines. Cognitive Science, 9, 1985. - 147. - 169. p.
Alexander I., Morton H. An Introduction to Neural Computing. - London: Chapman & Hall, 1991.
Fausett L. Fundamentals of Neural Networks: Architectures, Algorithms and Applications. Prentice Hall International Inc., 1994.
Hopfield J. J. Neural networks and physical systems with emergent collective computational abilities. - USA: Proc. Natl. Acad. Sci., 79, 1982. - 2554. - 2558. p.
Hopfield J. J. Neurons with graded response have collective computational properties like those of the state neurons. - USA Proc. Natl. Acad. Sci, 81, 1984. - 3088 - 3092. p.
Kappen H. J. Deterministic learning rules for Boltzmann machines. Neural Networks, Vol.8, No.4, 1995. - 537 - 548. p.
Kirkpatrick S, Gelatt C. D. and Vecchi M. P. Optimization by simulated annealing. Science, 220, 1983. - 671- 680.p.
