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

TL;DR

This paper introduces a classical weight-constrained neural network inspired by quantum models, significantly reducing variable count while maintaining accuracy, and enhances robustness against adversarial attacks.

Contribution

We establish a mathematical equivalence between quantum neural networks with amplitude encoding and weight-constrained neural networks, leading to a novel classical approach.

Findings

Reduced variable count by 135 times without accuracy loss

Developed a dropout method to improve adversarial robustness

Applicable to industry scenarios like self-driving vehicles

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.