Training and Classification using a Restricted Boltzmann Machine on the D-Wave 2000Q

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 exact gradient of 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), which is much faster than Markov chain Monte Carlo (MCMC) used in CD. Training and classification results are compared with CD. The classification accuracy results indicate similar performance of both methods. Image reconstruction as well as log-likelihood calculations are used to compare the performance of quantum and classical algorithms for RBM training. It is shown that the samples obtained from quantum annealer can be used to train a RBM on a 64-bit `bars and stripes' data set with classification performance similar to a RBM trained with CD. Though training based on CD showed improved learning performance, training using a quantum annealer eliminates computationally expensive MCMC steps of CD.

Front. Phys., 29 June 2021

References in corpus (2)

• Realizable Hamiltonians for Universal Adiabatic Quantum Computers
• Learning RBM with a DC programming Approach

Cited by in corpus (16)

• Quantum computing for finance
• Massively Parallel Probabilistic Computing with Sparse Ising Machines
• Recent advances for quantum classifiers
• Basic Elements for Simulations of Standard Model Physics with Quantum Annealers: Multigrid and Clock States
• Training Deep Boltzmann Networks with Sparse Ising Machines
• Hybrid quantum-classical machine learning for generative chemistry and drug design
• Quantum Machine Learning for Finance
• Magnetic Phases of Spatially-Modulated Spin-1 Chains in Rydberg Excitons: Classical and Quantum Simulations
• A hybrid quantum-classical approach for inference on restricted Boltzmann machines
• Balanced k-Means Clustering on an Adiabatic Quantum Computer
• Online calibration scheme for training restricted Boltzmann machines with quantum annealing
• Hyperspectral image segmentation with a machine learning model trained using quantum annealer
• Quantum sequel of neural network training
• Diabatic quantum annealing for training energy-based generative models
• Solving Inequality-Constrained Binary Optimization Problems on Quantum Annealer
• Analog Quantum Approximate Optimization Algorithm