Artificial Intelligence (MSc)
People
Description
The course covers the most fundamental concepts, modeling approaches, and resolution methods of classical AI including intelligent agents' architectures, uninformed and informed search, adversarial search, integration of search and machine learning, bayesian networks, planning, constraint satisfaction programming, and state-of-the-art metaheuristic search methods (e.g., simulated annealing, genetic algorithms, genetic programming, probabilistic model-building genetic algorithms also known as estimation of distribution algorithms, multi-objective evolutionary algorithms, and ant colonies).
Objectives
This course introduces the students to basic problems, models, and techniques of Artificial Intelligence (AI) and enables them to model and solve specific AI problems.
Teaching mode
In presence
Learning methods
Lectures
Examination information
Evaluation will be based on a closed-book written test that comprises open questions and numerical problems.
Bibliography
- Luke, Sean. Essentials of metaheuristics: a set of undergraduate lecture notes. Second edition. United States]: Lulu Com, 2013. (Freely available at https://cs.gmu.edu/~sean/book/metaheuristics/)
- Russell, Stuart J., Norvig, Peter, Chang, Ming-wei. Artificial intelligence: a modern approach. Fourth edition. Hoboken, NJ: Pearson, 2021.
Education
- Master of Science in Artificial Intelligence, Lecture, 2nd year
- Master of Science in Computational Science, Lecture, Elective, 2nd year
- Master of Science in Informatics, Lecture, Artificial Intelligence, Elective, 1st year
- Master of Science in Informatics, Lecture, Artificial Intelligence, Elective, 2nd year