Quantum image denoising: a framework via Boltzmann machines, QUBO, and quantum annealing

Frontiers in Computer Science

Computer Science

Phillip Kerger¹  Ryoji Miyazaki² 

[1] Department of Applied Mathematics and Statistics, Johns Hopkins University, Baltimore, MD, United States;Quantum Artificial Intelligence Laboratory, NASA Ames Research Center, Moffett Field, CA, United States;Research Institute of Advanced Computer Science, Universities Space Research Association (USRA), Moffett Field, CA, United States;Secure System Platform Research Laboratories, NEC Corporation, Kawasaki, Japan;NEC-AIST Quantum Technology Cooperative Research Laboratory, National Institute of Advanced Industrial Science and Technology, Tsukuba, Japan;

关键词: denoising;    quantum annealing;    machine learning;    image processing;    quadratic unconstrained binary optimization;   

DOI  :  10.3389/fcomp.2023.1281100

 received in 2023-08-21, accepted in 2023-10-02,  发布年份 2023

来源: Frontiers

【 摘 要 】

We investigate a framework for binary image denoising via restricted Boltzmann machines (RBMs) that introduces a denoising objective in quadratic unconstrained binary optimization (QUBO) form well-suited for quantum annealing. The denoising objective is attained by balancing the distribution learned by a trained RBM with a penalty term for derivations from the noisy image. We derive the statistically optimal choice of the penalty parameter assuming the target distribution has been well-approximated, and further suggest an empirically supported modification to make the method robust to that idealistic assumption. We also show under additional assumptions that the denoised images attained by our method are, in expectation, strictly closer to the noise-free images than the noisy images are. While we frame the model as an image denoising model, it can be applied to any binary data. As the QUBO formulation is well-suited for implementation on quantum annealers, we test the model on a D-Wave Advantage machine, and also test on data too large for current quantum annealers by approximating QUBO solutions through classical heuristics.

【 授权许可】

Unknown   
Copyright © 2023 Kerger and Miyazaki.