Introduction to Quantum Machine Learning

3 Credits.

This course provides an advanced exploration to Quantum Machine Learning (QML), a paradigm that fundamentally differs from classical machine learning by leveraging superposition, entanglement, and interference to represent data, construct models, and perform optimization in high-dimensional quantum spaces. Students will study both fault-tolerant and near-term (NISQ) approaches, including variational quantum circuits, quantum kernel methods, QAOA, quantum annealing, HHL-based linear algebra techniques, and hybrid quantum-classical learning architectures. The course also examines current research topics shaping the field, including barren plateau theory, circuit expressivity and trainability, quantum advantage, scalability, and noise-aware system design. Emphasis is placed on both theoretical foundations and practical implementation challenges. Through a substantial implementation-driven project, students will design, benchmark, and analyze a quantum learning model, culminating in a research-style paper evaluating its theoretical basis, experimental performance, and real-world feasibility.