Phase Diagram Of Restricted Boltzmann Machines And Generalised Hopfield Networks With Arbitrary Priors
2017 · Adriano Barra, Giuseppe Genovese, Peter Sollich, et al.
Abstract
Restricted Boltzmann Machines are described by the Gibbs measure of a bipartite spin glass, which in turn corresponds to the one of a generalised Hopfield network. This equivalence allows us to characterise the state of these systems in terms of retrieval capabilities, both at low and high load. We study the paramagnetic-spin glass and the spin glass-retrieval phase transitions, as the pattern (i.e. weight) distribution and spin (i.e. unit) priors vary smoothly from Gaussian real variables to Boolean discrete variables. Our analysis shows that the presence of a retrieval phase is robust and not peculiar to the standard Hopfield model with Boolean patterns. The retrieval region is larger when the pattern entries and retrieval units get more peaked and, conversely, when the hidden units acquire a broader prior and therefore have a stronger response to high fields. Moreover, at low load retrieval always exists below some critical temperature, for every pattern distribution ranging from th
Authors
(none)
Tags
Stats
Related papers
- Uniform Memory Retrieval With Larger Capacity For Modern Hopfield Models (2024)2.00
- Generative Semantic Hashing Enhanced Via Boltzmann Machines (2020)3.58
- Locality Preserving Markovian Transition For Instance Retrieval (2025)0.00
- Forestdsh: A Universal Hash Design For Discrete Probability Distributions (2019)0.00
- Topics In Random Matrices And Statistical Machine Learning (2018)0.00
- Sign-guided Bipartite Graph Hashing For Hamming Space Search (2024)0.00
- A Theoretical View On Sparsely Activated Networks (2022)0.00
- Generalizing Similarity In Noisy Setups: The DIBS Phenomenon (2022)0.00