Nonnegative/Binary Matrix Factorization for Image Classification using Quantum Annealing

Abstract

Classical computing has borne witness to the development of machine learning. The integration of quantum technology into this mix will lead to unimaginable benefits and be regarded as a giant leap forward in mankind's ability to compute. Demonstrating the benefits of this integration now becomes essential. With the advance of quantum computing, several machine-learning techniques have been proposed that use quantum annealing. In this study, we implement a matrix factorization method using quantum annealing for image classification and compare the performance with traditional machine-learning methods. Nonnegative/binary matrix factorization (NBMF) was originally introduced as a generative model, and we propose a multiclass classification model as an application. We extract the features of handwritten digit images using NBMF and apply them to solve the classification problem. Our findings show that when the amount of data, features, and epochs is small, the accuracy of models trained by NBMF is superior to classical machine-learning methods, such as neural networks. Moreover, we found that training models using a quantum annealing solver significantly reduces computation time. Under certain conditions, there is a benefit to using quantum annealing technology with machine learning.

arXiv comment11 pages, 8 figures

References in corpus (11)

• A Survey on Deep Learning in Medical Image Analysis
• Quantum Computing in the NISQ era and beyond
• Support vector machines on the D-Wave quantum annealer
• Quantum annealing versus classical machine learning applied to a simplified computational biology problem
• Nonnegative/binary matrix factorization with a D-Wave quantum annealer
• Reverse Annealing for Nonnegative/Binary Matrix Factorization
• Towards Feature Selection for Ranking and Classification Exploiting Quantum Annealers
• Completely Quantum Neural Networks
• Image classification using quantum inference on the D-Wave 2X
• Comparing the effects of Boltzmann machines as associative memory in Generative Adversarial Networks between classical and quantum sampling
• Image Analysis Based on Nonnegative/Binary Matrix Factorization

Cited by in corpus (3)

• Quantum autoencoders for image classification
• Collaborative filtering based on nonnegative/binary matrix factorization
• Generating gradients in the energy landscape using rectified linear type cost functions for efficiently solving 0/1 matrix factorization in Simulated Annealing