Restricted Boltzmann machines as models of interacting variables

From MaRDI portal
Publication:5033545

DOI10.1162/NECO_A_01420zbMATH Open1483.92011arXiv2103.15917OpenAlexW3185791989MaRDI QIDQ5033545FDOQ5033545


Authors: Nicola Bulso, Yasser Roudi Edit this on Wikidata


Publication date: 23 February 2022

Published in: Neural Computation (Search for Journal in Brave)

Abstract: We study the type of distributions that Restricted Boltzmann Machines (RBMs) with different activation functions can express by investigating the effect of the activation function of the hidden nodes on the marginal distribution they impose on observed binary nodes. We report an exact expression for these marginals in the form of a model of interacting binary variables with the explicit form of the interactions depending on the hidden node activation function. We study the properties of these interactions in detail and evaluate how the accuracy with which the RBM approximates distributions over binary variables depends on the hidden node activation function and on the number of hidden nodes. When the inferred RBM parameters are weak, an intuitive pattern is found for the expression of the interaction terms which reduces substantially the differences across activation functions. We show that the weak parameter approximation is a good approximation for different RBMs trained on the MNIST dataset. Interestingly, in these cases, the mapping reveals that the inferred models are essentially low order interaction models.


Full work available at URL: https://arxiv.org/abs/2103.15917




Recommendations




Cited In (8)





This page was built for publication: Restricted Boltzmann machines as models of interacting variables

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q5033545)