Quantum-Inspired Weight-Constrained Neural Network: Reducing Variable Numbers by 100x Compared to Standard Neural Networks

Abstract

Although quantum machine learning has shown great promise, the practical application of quantum computers remains constrained in the noisy intermediate-scale quantum era. To take advantage of quantum machine learning, we investigate the underlying mathematical principles of these quantum models and find that the quantum neural network with amplitude encoding is equivalent to a weight-constrained neural network. Motived by this discovery, we develop a classical weight-constrained neural network. We find that this approach can reduce the number of variables in a classical neural network by a factor of 135 while preserving its accuracy. In addition, we develop a dropout method to enhance the robustness of quantum machine learning models, which are highly susceptible to adversarial attacks. This technique can also be applied to improve the adversarial robustness of the classical weight-constrained neural network, which is essential for industry applications, such as self-driving vehicles. Our work offers a novel approach to reduce the complexity of large classical neural networks, addressing a critical challenge in machine learning.

13 pages, 12 figures

References in corpus (32)

• Supplementary information for "Quantum supremacy using a programmable superconducting processor"
• Quantum Machine Learning
• Supervised learning with quantum enhanced feature spaces
• Quantum support vector machine for big data classification
• Quantum Error Correction for Quantum Memories
• A Theory of Quantum Error-Correcting Codes
• Summary of ChatGPT-Related Research and Perspective Towards the Future of Large Language Models
• Power of data in quantum machine learning
• Efficient Learning for Deep Quantum Neural Networks
• Challenges and Opportunities in Quantum Machine Learning
• A rigorous and robust quantum speed-up in supervised machine learning
• Quantum advantage in learning from experiments
• Quantum Data Fitting
• Quantum machine learning: a classical perspective
• Quantum Generative Adversarial Networks for Learning and Loading Random Distributions
• The Expressive Power of Parameterized Quantum Circuits
• Opportunities and challenges for quantum-assisted machine learning in near-term quantum computers
• Large AI Models in Health Informatics: Applications, Challenges, and the Future
• Is quantum advantage the right goal for quantum machine learning?
• Quantum speedup for active learning agents
• Quantum-Inspired Support Vector Machine
• Quantum noise protects quantum classifiers against adversaries
• Quantum Adversarial Machine Learning
• Quantum-assisted Helmholtz machines: A quantum-classical deep learning framework for industrial datasets in near-term devices
• Quantum Vision Transformers
• Vulnerability of quantum classification to adversarial perturbations
• Quantum kernels for real-world predictions based on electronic health records
• Experimental exploration of five-qubit quantum error correcting code with superconducting qubits
• Realizing a quantum generative adversarial network using a programmable superconducting processor
• Tree tensor network classifiers for machine learning: from quantum-inspired to quantum-assisted
• Numerical evidence against advantage with quantum fidelity kernels on classical data
• Kernel-based quantum regressor models learn non-Markovianity