A building block for hardware belief networks
Abstract
Belief networks represent a powerful approach to problems involving probabilistic inference, but much of the work in this area is software based utilizing standard deterministic hardware based on the transistor which provides the gain and directionality needed to interconnect billions of them into useful networks. This paper proposes a transistor like device that could provide an analogous building block for probabilistic networks. We present two proof-of-concept examples of belief networks, one reciprocal and one non-reciprocal, implemented using the proposed device which is simulated using experimentally benchmarked models.
Cite
@article{arxiv.1606.00130,
title = {A building block for hardware belief networks},
author = {Behtash Behin-Aein and Vinh Diep and Supriyo Datta},
journal= {arXiv preprint arXiv:1606.00130},
year = {2016}
}
Comments
Keywords: stochastic, sigmoid, phase transition, spin glass, frustration, reduced frustration, Ising model, Bayesian network, Boltzmann machine. 23 pages, 9 figures