SC16 Salt Lake City, UT

06. Training Restricted Boltzmann Machines Using a Quantum Annealer


Authors: Vaibhaw Kumar (Booz Allen Hamilton)Gideon P. Bass (Booz Allen Hamilton)Joseph S. Dulny (Booz Allen Hamilton)

Abstract: Machine learning and the optimization involved therein is of critical importance for commercial and military applications. Due to the extremely complex nature of many-variable optimization, the conventional approach is to employ a meta-heuristic technique to find suboptimal solutions. Quantum Annealing (QA) hardware offers a completely novel approach for obtaining significantly better or optimal solutions with considerably large speed-ups when compared to traditional computing hardware. In this presentation, we describe our development of new machine learning algorithms tailored for QA hardware. We train a Restricted Boltzmann Machine (RBM) using QA hardware as a sampler. We present our initial results obtained by training RBMs on model data sets. We also discuss strategies for scaling up, including enhanced embedding and partitioned RBMs, to overcome the limitation imposed by current QA hardware.

Poster: pdf
Two-page extended abstract: pdf


Poster Index