Quantum Convolutional Neural Networks with Interaction Layers for Classification of Classical Data

TL;DR

This paper introduces a quantum convolutional neural network with interaction layers that utilize three-qubit interactions, demonstrating improved classification performance on image and data sets, and exploring the network's expressibility and entangling capabilities.

Contribution

It presents a novel quantum convolutional network architecture with interaction layers based on three-qubit interactions, advancing quantum neural network design and performance.

Findings

Outperforms existing state-of-the-art methods on MNIST, Fashion MNIST, and Iris datasets.

Effectively classifies both binary and multiclass data.

Enhances understanding of multi-qubit interactions in quantum neural networks.

Abstract

Quantum Machine Learning (QML) has come into the limelight due to the exceptional computational abilities of quantum computers. With the promises of near error-free quantum computers in the not-so-distant future, it is important that the effect of multi-qubit interactions on quantum neural networks is studied extensively. This paper introduces a Quantum Convolutional Network with novel Interaction layers exploiting three-qubit interactions, while studying the network's expressibility and entangling capability, for classifying both image and one-dimensional data. The proposed approach is tested on three publicly available datasets namely MNIST, Fashion MNIST, and Iris datasets, flexible in performing binary and multiclass classifications, and is found to supersede the performance of existing state-of-the-art methods.