Open AccessComparison of quantum and classical methods for labels and patterns in Restricted Boltzmann Machines
Author(s) -
Vivek Dixit,
Yaroslav Koshka,
Tamer Aldwairi,
M. A. Novotny
Publication year - 2021
Publication title -
journal of physics. conference series
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.21
H-Index - 85
eISSN - 1742-6596
pISSN - 1742-6588
DOI - 10.1088/1742-6596/2122/1/012007
Subject(s) - boltzmann machine , restricted boltzmann machine , adiabatic process , quantum annealing , quantum , computer science , exploit , artificial intelligence , simulated annealing , boltzmann constant , energy (signal processing) , generative model , algorithm , pattern recognition (psychology) , generative grammar , machine learning , deep learning , mathematics , quantum computer , physics , statistics , quantum mechanics , computer security
Classification and data reconstruction using a restricted Boltzmann machine (RBM) is presented. RBM is an energy-based model which assigns low energy values to the configurations of interest. It is a generative model, once trained it can be used to produce samples from the target distribution. The D-Wave 2000Q is a quantum computer which has been used to exploit its quantum effect for machine learning. Bars-and-stripes (BAS) and cybersecurity (ISCX) datasets were used to train RBMs. The weights and biases of trained RBMs were used to map onto the D-Wave. Classification as well as image reconstruction were performed. Classification accuracy of both datasets indicates comparable performance using D-Wave’s adiabatic annealing and classical Gibb’s sampling.