Leveraging Quantum Layers in Classical Neural Networks

TL;DR

This paper investigates integrating quantum layers into classical neural networks to enhance learning, demonstrating potential benefits with limited qubits and providing a framework for future scalable quantum machine learning research.

Contribution

It introduces a methodology for constructing hybrid quantum-classical neural networks and evaluates their performance, highlighting the potential of quantum components in deep learning.

Findings

Quantum layers can improve feature transformation.

Limited qubits still offer meaningful benefits.

Open-source implementation available for further research.

Abstract

Hybrid quantum-classical neural networks represent a promising frontier in the search for improved machine learning models. This thesis explores the integration of quantum layers within classical convolutional neural network architectures, aiming to leverage quantum entanglement and feature mapping to enhance learning capabilities. A detailed methodology for constructing and training such hybrid models is presented, using PyTorch and Qiskit Machine Learning frameworks. Experiments investigate the performance impact of inserting quantum layers at different stages of the neural network pipeline. The results suggest that quantum components can introduce meaningful transformations even with a limited number of qubits, motivating further research into scalable quantum machine learning. The full implementation is made publicly available, and future work will focus on expanding experimental evaluations and publishing additional findings.