Quantum machine learning
The main aim of quantum machine learning is to find efficient quantum algorithms for
the most challenging quantum machine learning problems. In this context,
unsupervised problems play an important role since they are mostly unsolved despite
the recent success of deep learning. Broader, quantum machine learning explores the
connections between machine learning and quantum physics. For instance, two
crucial research directions of quantum machine learning are the application of
quantum-mechanics tools to machine learning and the application of machinelearning
tools to describe entangled quantum states. These directions are essential to
understand the boundaries of classical computation and the benefits of quantum
processing.
In the course, we will present connections between quantum mechanics and machine
learning that are important for the application of noisy intermediate-scale quantum
devices to machine learning problems. The course is hands-on. We will provide
multiple notebooks to guide the students during the learning process and acquaint
them with available quantum computational tools. Part of the course will also be
devoted to the most prominent algorithms for universal quantum computers. In the
last two weeks, we will explore recent, more theoretical connections between
machine learning and quantum mechanics.
