Boltzmann machines and energy-based models
read the original abstract
We review Boltzmann machines and energy-based models. A Boltzmann machine defines a probability distribution over binary-valued patterns. One can learn parameters of a Boltzmann machine via gradient based approaches in a way that log likelihood of data is increased. The gradient and Hessian of a Boltzmann machine admit beautiful mathematical representations, although computing them is in general intractable. This intractability motivates approximate methods, including Gibbs sampler and contrastive divergence, and tractable alternatives, namely energy-based models.
This paper has not been read by Pith yet.
Forward citations
Cited by 1 Pith paper
-
Universal Spin Models are Universal Approximators in Machine Learning
Universal spin models are universal approximators of probability distributions, yielding a unified recipe for universal approximation theorems in models such as restricted Boltzmann machines and deep belief networks.
discussion (0)
Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.