After successful completion of the course, students are able to search the literature on their own, to write seminar papers using the LaTeX typesetting system, and to prepare and give presentations (45 minutes).

• Reinforcement learning: various methods
• Reinforcement learning: convergence proofs
• Reinforcement learning: function approximation
• Reinforcement learning: Atari, Go, etc.
• Artificial neural networks, deep learning
• Bayesian estimation (for PDE): numerical algorithms
• Bayesian estimation (for PDE): theory
• Image classification

Supervised machine learning, unsupervised machine learning, reinforcement learning.

Semianr paper and seminar presentation.

Linear algebra, analysis.