Efficient Quantum Image Classification Using Single Qubit Encoding

Easom-McCaldin, Philip, Bouridane, Ahmed, Belatreche, Ammar, Jiang, Richard and Almaadeed, Sumaya (2022) Efficient Quantum Image Classification Using Single Qubit Encoding. IEEE Transactions on Neural Networks and Learning Systems. ISSN 2162-237X (In Press)

Preview	Text (Advance online version) Efficient_Quantum_Image_Classification_Using_Single_Qubit_Encoding.pdf - Published Version Available under License Creative Commons Attribution 4.0. Download (6MB) | Preview
Preview	Text QML Classifier Paper Draft (Revised Version).pdf - Accepted Version Download (1MB) | Preview

Abstract

The domain of image classification has been seen to be dominated by high-performing deep learning (DL) architectures. However, the success of this field as seen over the past decade has resulted in the complexity of modern methodologies scaling exponentially, commonly requiring millions of parameters. Quantum computing (QC) is an active area of research aimed towards greatly reducing problems of complexity faced in classical computing. With growing interest towards quantum machine learning (QML) for applications of image classification, many proposed algorithms require usage of numerous qubits. In the noisy intermediate-scale quantum (NISQ) era, these circuits may not always be feasible to execute effectively, therefore we should aim to use each qubit as effectively and efficiently as possible, before adding additional qubits. This paper proposes a new single-qubit based deep quantum neural network for image classification that mimics traditional convolutional neural network techniques, resulting in a reduced number of parameters compared to previous works. Our aim is to prove the concept of the initial proposal by demonstrating classification performance of the single-qubit based architecture, as well as to provide a tested foundation for further development. To demonstrate this, our experiments were conducted using various datasets including MNIST, Fashion-MNIST and ORL face datasets. To further our proposal in the context of the NISQ era, our experiments were intentionally conducted in noisy simulation environments. Initial test results appear promising, with classification accuracies of 94.6, 89.5, and 82.5 achieved on subsets of MNIST, FMNIST and ORL face datasets, respectively. In addition, proposals for further investigation and development were considered, where it is hoped these initial results can be improved.

Actions (login required)

View Item

Downloads