Quantum Machine Learning

Aim

After completing the course the student should be able to:

• use relevant concepts and methods in quantum machine learning to formulate, structure and solve practical problems.
• infer the parameters in a number of common quantum machine learning models.
• evaluate and choose among models.
• implement quantum machine learning models and algorithms in a programming language.

Content

• Introduction to machine learning, and introduction to quantum computers, a brief introduction to quantum mechanics
• Representation of classical data in quantum systems, coding and embedding, quantum data representation and quantum feature map
• Quantum algorithms for machine learning, quantum classifiers, quantum mechanical kernel methods, quantum clustering
• Quantum variational circuits, quantum neural networks, quantum convolutional neural networks (QCNNs), quantum federated learning (QFL), quantum reinforcement learning (QRL), kvantmekanisk multimodal inlärning
• Research directions in the area
• Applications of QML in language models, computer vision, health care, medicin design, transport, and intrusion detection