MiS Preprint Repository

Delve into the future of research at MiS with our preprint repository. Our scientists are making groundbreaking discoveries and sharing their latest findings before they are published. Explore repository to stay up-to-date on the newest developments and breakthroughs.

MiS Preprint

Expressive Power of Conditional Restricted Boltzmann Machines

Guido Montúfar, Nihat Ay and Keyan Ghazi-Zahedi


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 on the minimal size of universal approximators of conditional probability distributions, the minimal size of universal approximators of deterministic functions, the maximal model approximation errors, and on the dimension of the set of representable conditional distributions. We contribute new tools for investigating conditional models and obtain significant improvements over the results that can be derived directly from existing work on restricted Boltzmann machine probability models.

Feb 14, 2014
May 13, 2014
MSC Codes:
68T05, 60K99, 97R40
02.50.Cw, 07.05.Mh
conditional restricted Boltzmann machine, universal approximation, Kullback-Leibler approximation error, expected dimension

Related publications

2015 Journal Open Access
Guido Montúfar, Nihat Ay and Keyan Ghazi-Zahedi

Geometry and expressive power of conditional restricted Boltzmann machines

In: Journal of machine learning research, 16 (2015), pp. 2405-2436