Geometry and Expressive Power of Conditional Restricted Boltzmann Machines
Skip to main content
eScholarship
Open Access Publications from the University of California

UCLA

UCLA Previously Published Works bannerUCLA

Geometry and Expressive Power of Conditional Restricted Boltzmann Machines

  • Author(s): Montufar, Guido
  • Ay, Nihat
  • Ghazi-Zahedi, Keyan
  • et al.

Published Web Location

http://www.jmlr.org/papers/v16/montufar15b.html
No data is associated with this publication.
Abstract

Conditional restricted Boltzmann machines are undirected stochastic neural networks with a layer of input and output units connected bipartitely to a layer of hidden units. These networks define models of conditional probability distributions on the states of the output units given the states of the input units, parametrized by interaction weights and biases. We address the representational power of these models, proving results their ability to represent conditional Markov random fields and conditional distributions with restricted supports, the minimal size of universal approximators, the maximal model approximation errors, and on the dimension of the set of representable conditional distributions. We contribute new tools for investigating conditional probability models, which allow us to improve the results that can be derived from existing work on restricted Boltzmann machine probability models.

Many UC-authored scholarly publications are freely available on this site because of the UC's open access policies. Let us know how this access is important for you.

Item not freely available? Link broken?
Report a problem accessing this item