Quantum Machine Learning
The course covers the following topics:
- Introduction to Quantum Computing and Machine Learning; including state vectors, Hilbert space, quantum states, quantum entanglement and superposition, quantum gates, and quantum circuits.
- Quantum machine learning (QML) basics; including representing classical data on quantum systems, quantum data encoding and embedding, quantum data representation and quantum feature maps.
- Quantum Algorithms for Machine Learning; Quantum Classifiers, Quantum Kernel Methods, and Quantum Clustering.
- Quantum Variational Circuits, Quantum Neural Networks (QNNs), Quantum Convolutional Neural Networks (QCNNs), Quantum Federated Learning (QFL), Quantum Reinforcement Learning (QFL), Quantum Multimodal Learning.
- Challenges and future research directions in QML.
- Applications of QML in natural language processing, computer vision, healthcare, drug design, transportation, and intrusion detection.
Level:
Graduate level
Application code:
R3503
Entry requirements:
General entry requirements for third-cycle studies. At least 60 credits at second-cycle level in computer science, computer engineering, computer technology, electrical engineering or another area relevant to the third-cycle subject. Machine Learning 7.5 credits and Neural Networks 7.5 credits.
Selection rules:
Restricted admission
Start week:
week: 39
Instructional time:
Various times
Tuition fee:
Language of instruction:
Teaching is in English.
