Abstract
Quantum computing is expected to fundamentally change computer systems in the future. Recently, a new research topic of quantum computing is the hybrid quantum–classical approach for machine learning, in which a parameterized quantum circuit, also called quantum neural network (QNN), is optimized by a classical computer. This hybrid approach can have the benefits of both quantum computing and classical machine learning methods. In this early stage, it is of crucial importance to understand the new characteristics of quantum neural networks for different machine learning tasks. In this paper, we will study quantum neural networks for the task of classifying images, which are high-dimensional spatial data. In contrast to previous evaluations of low-dimensional or scalar data, we will investigate the impacts of practical encoding types, circuit depth, bias term, and readout on classification performance on the popular MNIST image dataset. Various interesting findings on learning behaviors of different QNNs are obtained through experimental results. To the best of our knowledge, this is the first work that considers various QNN aspects for image data.
Highlights
Quantum computing is a novel type of computing that is expected to fundamentally change future computer systems
We will explore how the performance of a quantum neural network (QNN) is affected by encoding choices and circuit depths
We evaluated different QNNs for the task of image classification
Summary
Quantum computing is a novel type of computing that is expected to fundamentally change future computer systems. Because quantum mechanics is a more general model of physics than classical mechanics, it leads to a more general model of computing, which has the ability to tackle problems that classical computing cannot [1]. Unlike classical computers, which utilize the binary bits 0 and 1 to store or manipulate information, quantum computers use quantum bits, known as “qubits”. Qubits are extremely sensitive to environmental disturbances, making them prone to errors [1]. To cope with this problem, the practical applications of noisy intermediate scale quantum (NISQ) devices are being investigated [2]. Quantum bit (or qubit) is a fundamental information unit used in quantum computers.
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Disclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.