Quantum Machine Learning: From Theoretical Foundations to Real-World Applications

This thesis approaches QML from a theoretical point of view and then investigates the role of QML in classification tasks across two representative application areas. In the healthcare domain, handwriting-based features are employed for early screening of Alzheimer’s disease, exploring the ability of quantum kernel methods to improve diagnostic accuracy and resilience to noise. In the natural language processing domain, sentiment analysis is studied through hybrid neural networks that combine classical architectures with quantum layers, assessing whether quantum components can enhance performance in tasks traditionally dominated by deep learning. Together, these case studies illustrate both the promises and the current limitations of QML, offering insights into its potential impact on real-world problems and paving the way for future research.