期刊
FRONTIERS IN PHYSICS
卷 9, 期 -, 页码 -出版社
FRONTIERS MEDIA SA
DOI: 10.3389/fphy.2021.589626
关键词
bars and stripes; quantum annealing; classification; image reconstruction; log-likelihood; machine learning; D-wave; RBM (restricted Boltzmann machine)
资金
- Integrated Data Science Initiative Grants, Purdue University [IDSI F.90000303]
- U.S. Department of Energy (Office of Basic Energy Sciences) [DE-SC0019215, ERKCG12]
- U.S. Department of Energy [DE-AC05-00OR22725]
This study calculates the model expectation of gradient learning for RBM using a quantum annealer, showing improved learning speed; compares the training and classification results of RBM trained using a quantum annealer with CD-based methods in terms of classification accuracies, image reconstruction, and log-likelihood results; samples from a quantum annealer can be used to train an RBM, but the CD-based method performs better in image reconstruction and log-likelihood results.
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.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据