This lecture delves into the modern methods of
machine learning (ML). In particular, methods of deep
learning and reinforcement learning are covered. Topics include theoretical foundations of deep learning
and reinforcement learning, architectures of artificial neural
networks, generative modeling, deep reinforcement
learning, automatic differentiation and relevant
optimization methods. Possible fields of application are
discussed, e.g. the processing of images or natural
language, anomaly detection or optimal control. For the
practical implementation of the concepts the course includes an introduction to the JAX library.
