Knowledge of

• general aspects of AI, weak vs. strong AI

• history of AI

• aspects of symbolic AI (knowledge bases, logic, reasoning)

• representation learning

• advanced deep models (recurrent networks, graph networks)

• variational Bayesian methods (variational autoencoders)

• reinforcement learning

Skills to

• select appropriate methodology to solve AI problems

• implement selected AI algorithms

• design and train representation learning algorithms

• design and train reinforcement learning algorithms

Competences to

• reflect upon the capabilities and limitations of AI algorithms

• recognising and describing possible applications of AI methodology

• design, optimise and use advanced deep models

• apply the learned methodology to applications in analysis of real-world data such as images, sounds and text

• rigorously analyse AI learning algorithms