Quantum machine learning

This two-day course on quantum machine learning provides an introduction to combining machine learning approaches with quantum technology.

The course covers the essential topics in machine learning through the fundamentals of statistics and probability, and introduces how quantum computing could be utilised in the field of machine learning. Educational examples are covered from both classical and quantum perspectives, highlighting the key differences between the approaches.

For highlighting limitations and strengths of classical and quantum approaches (in algorithms and machine learning), selected topics from theory of algorithms will also be covered. This course focuses specifically on gate-based quantum computing utilising the Qiskit quantum programming toolkit.

During the course, a Jupyter Notebook environment will be used for the hands-on sessions, which will be the main focus of the course instead of lectures.

Topics covered in the course

Day 1
Primer on principles of statistics and probability
Supervised and unsupervised learning
Fundamentals of support vector machines and neural networks
Essentials of theory of algorithms (classical and quantum)

Day 2
Quantum supervised learning
Quantum unsupervised learning
(Quantum) reservoir computing

Prerequisites

Basics of quantum computing, Python and Qiskit are highly recommended. If you are interested in attending this course, but do not have experiences with Qiskit, we encourage you to first attend our introductory course on quantum computing.

Additionally, basic notions of statistics and probability will be beneficial, however these basic notions will be explained as methods and approaches are introduced.

Learning outcomes

After this course, you will understand the fundamentals of machine learning and how it translates in quantum computing applications.

The course is targeted to students, researchers, and those in industry who have some quantum computing background (with little to no background in machine learning), and are interested in its machine learning applications.