Repository of DUTH

Quantum Machine Learning and applications (Master thesis)

Παντούσας, Αστέριος/ Pantousas, Asterios/ Quantum Computing and Quantum Technologies/ Κβαντική Υπολογιστική και Κβαντικές Τεχνολογίες

At a time when everyone is trying to ride the quantum wave, this thesis asks the critical question: Is Quantum Machine Learning actually useful, or just a fancy buzzword? Quantum Machine Learning (QML) emerges as a field where the seemingly bizarre laws of quantum mechanics meet the practical world of machine learning algorithms. We dive into the heart of QML, comparing it against classical Machine Learning (ML) algorithms to see if it can truly deliver what it promises. By implementing and testing both classical and quantum models using the Python language, Scikit Learn and Qiskit libraries, we aim to provide a more technical perspective of QML’s potential, limitations, and whether it is worth the hype. We will be judging performance based on key metrics such as accuracy, precision, recall, and computational efficiency. While acknowledging current hardware limitations, we will explore QML’s potential applications in healthcare sector. Spoiler alert: Reality may not be as entangled as we would like.