Artificial Intelligence

The goal of the course is to present advanced issues of artificial intelligence from the perspective of a computerized autonomous agent.

Objectives:

The goal of the course is to present advanced issues of artificial intelligence from the perspective of a computerized autonomous agent

Contents:

The first part covers basic methods of artificial intelligence – the logic of knowledge representation, inference rules and problem solving including: uniformed search, informed search with heuristic functions, constraint satisfaction problems and adversarial games.

The second part deals with practical planning and acting of an autonomous agent (i.e., situation space, plan space, plan decomposition, hierarchic decomposition, contingency planning), and with probabilistic reasoning.

The third part discusses agent design problems in the area of knowledge acquisition (learning from observations, in neural networks and reinforcement learning), and machine perception (image and speech understanding).

Textbooks:

• S. Russell, P. Norvig, Artificial Intelligence: A Modern Approach. Prentice Hall, Upper Saddle River, N.J., 2011, 2021 (selected chapters).
• Christopher M. Bishop: Pattern Recognition and Machine Learning. Springer Science-Business media, 2006. (Chapters: 1-5, 9, 12-14).
• D. Barber: Bayesian Reasoning and Machine Learning. Cambridge University Press, 2012-2020, (selected chapters) http://www.cs.ucl.ac.uk/staff/d.barber/brml/
• Charu C. Aggarwal: Neural Networks and Deep Learning. A Textbook. Springer International Publishing, 2018 (selected chapters)

After completing this course, the students will be able to:

• Produce and analyse logical and probabilistic knowledge inference rules, 
• Solve problems by state space search and planning.
• Acquire knowledge using active observation: supervised and unsupervised learning techniques, reinforcement learning.
• Solve classification- and decision problems.

50% continuous assessment, 50% from end-semester examination.

None