Lean classical-quantum hybrid neural network model for image classification

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.

18 pages,8 figures

References in corpus (18)

• Quantum Machine Learning
• Barren plateaus in quantum neural network training landscapes
• Quantum machine learning in feature Hilbert spaces
• Quantum advantage in learning from experiments
• Quantum Generative Adversarial Networks for Learning and Loading Random Distributions
• Quantum-enhanced machine learning
• Hybrid Quantum-Classical Convolutional Neural Networks
• Molecular prototypes for spin-based CNOT quantum gates
• Quantum machine learning for image classification
• Universal expressiveness of variational quantum classifiers and quantum kernels for support vector machines
• Benchmarking Adversarially Robust Quantum Machine Learning at Scale
• Variational quantum simulations of stochastic differential equations
• QAOA Performance in Noisy Devices: The Effect of Classical Optimizers and Ansatz Depth
• Classical versus Quantum: comparing Tensor Network-based Quantum Circuits on LHC data
• Stochastic Gradient Line Bayesian Optimization for Efficient Noise-Robust Optimization of Parameterized Quantum Circuits
• `Classical' quantum states
• Determining impact parameters of heavy-ion collisions at low-intermediate incident energies using deep learning with convolutional neural network
• Variational quantum state preparation for quantum-enhanced metrology in noisy systems