bluelogo.gif (1643 bytes)

home page

The Helmholtz Machine

Peter Dayan, Dept. of Computer Science, University of Toronto
Geoffrey E. Hinton, Dept. of Computer Science, University of Toronto
Radford M. Neal, Dept. of Computer Science, University of Toronto
Richard S. Zemel, The Salk Institute

Discovering the structure inherent in a set of patterns is a fundamental aim of statistical inference or learning. One fruitful approach is to build a parameterised stochastic generative model, independent draws from which are likely to produce the patterns. For all but the simplest generative models, each pattern can be generated in exponentially many ways. It is thus intractable to adjust the parameters to maximize the probability of the observed patterns, We describe a way of finessing this combinatorial explosion by maximising an easily computed lower bound on the probability of the observations. Our method can be viewed as a form of hierarchical self-supervised learning that may relate to the function of bottom-up and top-down cortical processing pathways.

In Neural Computation, vol. 7, pp. 1022-1037 (1995).
Download: [ps.gz]  [pdf]

Associated reference: A stochastic algorithm related to the Helmholtz Machine  is discussed in the following paper:  Hinton, G. E., Dayan, P., Frey, B. J., and Neal, R. M. (1995) The wake-sleep algorithm for unsupervised neural networks,  Science, vol. 268, pp. 1158-1161Download [abstract]   [ps] [pdf]

[home page]  [publications]