Variational Quantum Neural Networks (VQNNS) in Image Classification

TL;DR

This paper explores Variational Quantum Neural Networks (VQNNs) for image classification, demonstrating their potential for faster training and comparable accuracy on datasets like MNIST and crack images.

Contribution

It introduces a VQNN architecture utilizing a variational circuit and quantum optimization, showing improved training speed over traditional QNNs.

Findings

VQNNs converge faster than QNNs in experiments.

VQNNs achieve decent accuracy on MNIST and crack datasets.

Quantum optimization enhances training efficiency.

Abstract

Quantum machine learning has established as an interdisciplinary field to overcome limitations of classical machine learning and neural networks. This is a field of research which can prove that quantum computers are able to solve problems with complex correlations between inputs that can be hard for classical computers. This suggests that learning models made on quantum computers may be more powerful for applications, potentially faster computation and better generalization on less data. The objective of this paper is to investigate how training of quantum neural network (QNNs) can be done using quantum optimization algorithms for improving the performance and time complexity of QNNs. A classical neural network can be partially quantized to create a hybrid quantum-classical neural network which is used mainly in classification and image recognition. In this paper, a QNN structure is made where a variational parameterized circuit is incorporated as an input layer named as Variational Quantum Neural Network (VQNNs). We encode the cost function of QNNs onto relative phases of a superposition state in the Hilbert space of the network parameters. The parameters are tuned with an iterative quantum approximate optimisation (QAOA) mixer and problem hamiltonians. VQNNs is experimented with MNIST digit recognition (less complex) and crack image classification datasets (more complex) which converges the computation in lesser time than QNN with decent training accuracy.