2-IKV-133  Fundamentals of Artificial Intelligence (2)

Evaluation during the course: project, interim project evaluation

Concluding evaluation: final test + project evaluation

Subject aim: Provide knowledge from artificial intelligence: complex decision making, learning, communication and language.

Brief curriculum of the subject:

Probabilistic language processing

- PCFG, IR systems

- machine translation: language model,  translation model

Decision making

- Markov decision processes (MDP), iteration of values, iteration of strategies

- partially observable Markov decision processes (POMDP).

Learning

- EBL, KBL, KBIL

- decision trees, ID3 algorithm

Statistical learning

- discrete models, continuous models, learning the structure of Bayesian nets

- expectation-maximization (EM) algorithm

- clustering, learning the structure of Bayesian nets with hidden parameters

- passive reinforcement learning (direct utility estimation, ADP, TD learning)

- active reinforcement learning (exploration, action value function)

Literature:

Stuart Russel, Peter Norvig: Artificial Intelligence. A Modern Approach, 2nd ed., Prentice Hall, 2003

Language in which the subject is taught: Slovak

Date of the last sheet revision: 9.8.2007