Reproduce “Restricted Boltzmann Machines as Models of Interacting Variables” on OpenResearch
Turn your favorite coding agents into research agents that review literature, develop hypotheses, and run experiments.
Universal app for Apple silicon and Intel. Requires macOS 11 or later.
About this paper
Nicola Bulso, Yasser Roudi
The authors derive an exact mapping from a restricted Boltzmann machine’s visible distribution, for binary visible units, to explicit one-variable, pairwise, and higher-order interactions. The mapping shows how hidden-unit activation and connectivity shape visible dependencies. In MNIST tests, the best-fitting activation depends on hidden-layer size: Linear leads below 400 units, while Exponential has highest likelihood above 400, among tested models.
Summary by alphaXiv.
Tip: change arxiv.org to autoarxiv.org in any arXiv abstract link to open the paper here.