QuCNN : A Quantum Convolutional Neural Network with Entanglement Based Backpropagation

TL;DR

This paper introduces QuCNN, a quantum convolutional neural network that leverages entanglement-based backpropagation, adapting classical CNN concepts to quantum systems for potential quantum machine learning advancements.

Contribution

It presents the first quantum CNN model with entanglement-based backpropagation, enabling gradient computation within quantum systems using a novel single-ancilla qubit routine.

Findings

Successfully applied QuCNN to MNIST subset

Demonstrated gradient backpropagation in quantum neural networks

Validated quantum filter training against ideal states

Abstract

Quantum Machine Learning continues to be a highly active area of interest within Quantum Computing. Many of these approaches have adapted classical approaches to the quantum settings, such as QuantumFlow, etc. We push forward this trend and demonstrate an adaption of the Classical Convolutional Neural Networks to quantum systems - namely QuCNN. QuCNN is a parameterised multi-quantum-state based neural network layer computing similarities between each quantum filter state and each quantum data state. With QuCNN, back propagation can be achieved through a single-ancilla qubit quantum routine. QuCNN is validated by applying a convolutional layer with a data state and a filter state over a small subset of MNIST images, comparing the back propagated gradients, and training a filter state against an ideal target state.