Novel Data Encodings For Quantum Machine Learning - Enhancing the Quantum Feed-forward Neural Network for Improved Image Recognition

Aug 5, 2026

Quantum machine learning merges quantum computing with artificial intelligence to enable new solution strategies for learning tasks. Quantum image recognition has attracted strong research interest, yet common methods are constrained by limited qubit availability on current quantum hardware. This thesis introduces novel data encodings for a quantum feed-forward neural network, designed to represent richer information per pixel without additional qubits. Encodings are developed for continuous values and both binary and continuous three-channel representations. Extensive evaluations on multiple datasets show improved recognition performance, and the approach is extended to multi-class settings using classical quantum simulations.

LanguageEnglish

CategoryResearch & Report

FormatPDF

Pages95

Reading Time3 h 59 min

AccessFree to download

Introduction

Research objectives

Contributions

Background

Image representation

Datasets

Quantum computing

Quantum machine learning

Image classification in QML

Gradient descent optimisers

Methods

Quantum Feed-Forward Neural Network

Data encoding

Image representations

Pixel dataset

Tetrominoes

|
Faculty of Science and Technology
MASTER’S THESIS | | | --- | --- | | Study program/ Specialization: Master of Science in Data Science | Spring semester, 20.2..3...
Open / Restricted access | | Writer:
Emil Haavardtun | …………………………………………

(Writer’s signature) | | Faculty supervisor: Ferhat Özgur Catak
External supervisor(s): Shaukat Ali | | | Thesis title:
Novel Data Encodings For Quantum Machine Learning:
Enhancing the Quantum Feed-forward Neural Network for Improved Image Recognition | | | Credits (ECTS) : 30 | | | Key words:
QML, QNN, Image recognition, PQC, QFFNN, CIFAR-10, MNIST, Tetris | Pages: 79 + enclosure: 5
Stavanger, 2036.
Date/year | Faculty of Science and Technology Department of Electrical Engineering and Computer Science Novel Data Encodings For Quantum Machine Learning Enhancing the Quantum Feed-forward Neural Network for Improved Image Recognition Master’s Thesis in Data Science by Emil Haavardtun Internal Supervisors Ferhat Özgur Catak External Supervisors Shaukat Ali June 15, 2023 Preface This thesis is the culmination of my research and exploration. It has been submitted in partial fulfilment of a degree in Master of Science in Data Science at the University of Stavanger. The work herein is entirely my own. Abstract Quantum machine learning combines the realms of quantum computing with artificial intelligence, providing novel approaches to problem-solving. Quantum image recognition is one such problem that has attracted significant attention. However, many existing algorithms face a common challenge – current quantum hardware has limited available qubits. Based on the quantum machine learning framework anointed quantum feed-forward neural network, this thesis proposes novel data encodings for image recognition. By fully leveraging the capabilities of quantum computing, these new encodings represent more of each pixel’s information without requiring additional qubits. Specifically, the encodings are devised to characterise continuous pixel values, three-channel binary pixel values and three-channel continuous pixel values. In particular, the three-channel encodings enable the model to consider colours in images for increased performance. Through extensive evaluation of various datasets, the proposed encodings are demonstrated to enhance the performance of the quantum feed-forward neural network. Furthermore, the model is extended to the multi-class problem, further showcasing the improvement which the encodings provide. The work done herein is exploratory by nature, tested through classical simulations of quantum computers. As many quantum image recognition models utilise many of the same principles as the quantum feed-forward neural network, it is reasonable to imagine that the ideas and insight present in this thesis can be applied to such other models. Acknowledgements I would like to express my thanks to my friends and family for the help and support writing this thesis, both through constructive conversations and proofreading. Furthermore, I would like to thank my supervisor Shakut Ali and his colleagues for providing me with the idea and opportunity to work on this cool project. Contents Preface iii Abstract iv Acknowledgements v List of Figures ix List of Tables xi List of Algorithms xiii 1 Introduction 1 1.1 Introducing quantum computing . . . . . . . . . . . . . . . . . . . . . . . 1 1.2 Quantum computing in machine learning .................. 2 1.3 Quantum image recognition .......................... 2 1.4 Research objectives . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 3 1.5 Contributions . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 4 1.6 Structure . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 5 2 Background 7 2.1 Image representation . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 7 2.2 Datasets . . .

FAQs

What problem does the thesis address in quantum image recognition?

Many quantum image recognition methods are limited by the small number of qubits available on current quantum hardware. The thesis targets this constraint by designing data encodings that use information more efficiently.

What does the thesis propose for the quantum feed-forward neural network?

It proposes novel data encodings that represent continuous pixel values, three-channel binary pixel values, and three-channel continuous pixel values. The three-channel encodings are intended to capture color information for improved performance.

How are the proposed encodings validated?

The thesis evaluates the encodings on multiple datasets and demonstrates improved performance of the quantum feed-forward neural network. It also extends the model to a multi-class problem, and testing is performed via classical simulations of quantum computers.

Aug 5, 2026

Upload by Lucas Martin