A Deterministic and Generalized Framework for Unsupervised Learning with Restricted Boltzmann Machines
This work provides a generalized framework for unsupervised learning with RBMs, potentially benefiting researchers in machine learning and neural networks, though it appears incremental as it extends existing TAP methods to latent-variable and real-valued systems.
The authors tackled the problem of training and using Restricted Boltzmann Machines (RBMs) by developing a deterministic framework based on the Thouless-Anderson-Palmer (TAP) mean-field approximation, which allows for effective training and reveals unsupervised learning features not observable with sampling methods.
Restricted Boltzmann machines (RBMs) are energy-based neural-networks which are commonly used as the building blocks for deep architectures neural architectures. In this work, we derive a deterministic framework for the training, evaluation, and use of RBMs based upon the Thouless-Anderson-Palmer (TAP) mean-field approximation of widely-connected systems with weak interactions coming from spin-glass theory. While the TAP approach has been extensively studied for fully-visible binary spin systems, our construction is generalized to latent-variable models, as well as to arbitrarily distributed real-valued spin systems with bounded support. In our numerical experiments, we demonstrate the effective deterministic training of our proposed models and are able to show interesting features of unsupervised learning which could not be directly observed with sampling. Additionally, we demonstrate how to utilize our TAP-based framework for leveraging trained RBMs as joint priors in denoising problems.