Abstract
Restricted Boltzmann Machine (RBM) is an energy-based, undirected graphical model. It is commonly used for unsupervised and supervised machine learning. Typically, RBM is trained using contrastive divergence (CD). However, training with CD is slow and does not estimate the exact gradient of the log-likelihood cost function. In this work, the model expectation of gradient learning for RBM has been calculated using a quantum annealer (D-Wave 2000Q), where obtaining samples is faster than Markov chain Monte Carlo (MCMC) used in CD. Training and classification results of RBM trained using quantum annealing are compared with the CD-based method. The performance of the two approaches is compared with respect to the classification accuracies, image reconstruction, and log-likelihood results. The classification accuracy results indicate comparable performances of the two methods. Image reconstruction and log-likelihood results show improved performance of the CD-based method. It is shown that the samples obtained from quantum annealer can be used to train an RBM on a 64-bit “bars and stripes” dataset with classification performance similar to an RBM trained with CD. Though training based on CD showed improved learning performance, training using a quantum annealer could be useful as it eliminates computationally expensive MCMC steps of CD.
Original language | English |
---|---|
Article number | 589626 |
Journal | Frontiers in Physics |
Volume | 9 |
DOIs | |
State | Published - Jun 29 2021 |
Funding
The United States Government retains and the publisher, by accepting the article for publication, acknowledges that the United States Government retains a non-exclusive, paid-up, irrevocable, worldwide license to publish or reproduce the published form of this manuscript, or allow others to do so, for United States Government purposes. The Department of Energy will provide public access to these results of federally sponsored research in accordance with the DOE Public Access Plan. This manuscript has been released as a pre-print at arXiv:2005.03247 (cs.LG) [47]. We are grateful for the support from Integrated Data Science Initiative Grants (IDSI F.90000303), Purdue University. SK would like to acknowledges funding by the U.S. Department of Energy (Office of Basic Energy Sciences) under Award No. DESC0019215. TH would like to acknowledge funding by the U.S. Department of Energy (Office of Basic Energy Science) under Award No. ERKCG12. This manuscript has been authored by UT-Battelle, LLC under Contract No. DE-AC05-00OR22725 with the U.S. Department of Energy.
Keywords
- D-wave
- RBM (restricted Boltzmann machine)
- bars and stripes
- classification
- image reconstruction
- log-likelihood
- machine learning
- quantum annealing