Students gain basic knowledge about the basic principles and techniques of computational (artificial) intelligence.

Understanding basic principles and techniques of computational intelligence and the ability to apply them in solving different types of problems.

Concepts, aims, techniques, environments, and areas of computational intelligence. Uniformed and informed search techniques applied to problems with or without adversaries. Stochastic environment modeling (Markov Decision Processes). Training intelligent agents with reinforcement learning. Basic principles of machine learning: supervised, unsupervised and semi-supervised learning; basic clustering and classification algorithms. Introduction to neural networks. Introduction to deep learning: convolutional and recurrent neural networks. Introduction to deep reinforcement learning. Introduction to genetic algorithms. Introduction to logic programming in Prolog.

Teaching methods include lectures, laboratory classes, homework assignments, and consultations. Lectures involve presenting the course materials using the necessary didactic tools while encouraging the students to participate actively. Laboratory classes (exercises) are realized through assignments that can be done independently or with the help of teaching assistants, as well as through homework assignments.