Lean classical-quantum hybrid neural network model for image classification

TL;DR

This paper presents a lean hybrid quantum-classical neural network for image classification that achieves high accuracy with fewer parameters and faster convergence, demonstrating the effectiveness of quantum algorithms in complex tasks.

Contribution

Introduction of a lightweight hybrid quantum-classical neural network with only four variational layers, reducing computational costs while maintaining high accuracy.

Findings

Achieves 100% accuracy on MNIST

Achieves 99.02% accuracy on FashionMNIST

Achieves 85.55% accuracy on CIFAR-10

Abstract

The integration of algorithms from quantum information with neural networks has enabled unprecedented advancements in various domains. Nonetheless, the application of quantum machine learning algorithms for image classification predominantly relies on traditional architectures such as variational quantum circuits. The performance of these models is closely tied to the scale of their parameters, with the substantial demand for parameters potentially leading to limitations in computational resources and a significant increase in computation time. In this paper, we introduce a Lean Classical-Quantum Hybrid Neural Network (LCQHNN), which achieves efficient classification performance with only four layers of variational circuits, thereby substantially reducing computational costs. Our experiments demonstrate that LCQHNN achieves 100\%, 99.02\%, and 85.55\% classification accuracy on MNIST, FashionMNIST, and CIFAR-10 datasets. Under the same parameter conditions, the convergence speed of this method is also faster than that of traditional models. Furthermore, through visualization studies, it is found that the model effectively captures key data features during training and establishes a clear association between these features and their corresponding categories. This study confirms that the employment of quantum algorithms enhances the model's ability to handle complex classification problems.