|Norvig I 763
Boltzmann machines/AI Research/Norvig/Russell: Boltzmann machines (Hinton and Sejnowski, 1983(1), 1986(2)) [like recurrent networks esp. Hopfield networks; >Association/AI Research)] use symmetric weights, but include hidden units. In addition, they use a stochastic activation function, such that the probability of the output being 1 is some function of the total weighted input. Boltzmann machines therefore undergo state transitions that resemble a simulated annealing search
(…) for the configuration that best approximates the training set. It turns out that Boltzmann machines are very closely related to a special case of Bayesian networks evaluated with a stochastic simulation algorithm.
1. Hinton, G. E. and Sejnowski, T. (1983). Optimal perceptual inference. In CVPR, pp. 448–453.
2. Hinton, G. E. and Sejnowski, T. (1986). Learning and relearning in Boltzmann machines. In Rumelhart, D. E. and McClelland, J. L. (Eds.), Parallel Distributed Processing, chap. 7, pp. 282–317.
MIT Press._____________Explanation of symbols: Roman numerals indicate the source, arabic numerals indicate the page number. The corresponding books are indicated on the right hand side. ((s)…): Comment by the sender of the contribution. The note [Author1]Vs[Author2] or [Author]Vs[term] is an addition from the Dictionary of Arguments. If a German edition is specified, the page numbers refer to this edition.
Stuart J. Russell
Artificial Intelligence: A Modern Approach Upper Saddle River, NJ 2010