Generative Modeling for Machine Learning on the D-Wave

Los Alamos National Lab. (LANL), Los Alamos, NM (United States), Sunil Thulasidasan, USDOE Assistant Secretary for Human Resources and Administration · 2016

These are slides on Generative Modeling for Machine Learning on the D-Wave. The following topics are detailed: generative models; Boltzmann machines: a generative model; restricted Boltzmann machines; learning parameters: RBM training; practical ways to train RBM; D-Wave as a Boltzmann sampler; mapping RBM onto the D-Wave; Chimera restricted RBM; mapping binary RBM to Ising model; experiments; data; D-Wave effective temperature, parameters noise, etc.; experiments: contrastive divergence (CD) 1 step; after 50 steps of CD; after 100 steps of CD; D-Wave (experiments 1, 2, 3); D-Wave observations.

Read the paper · More papers on PaperTik