Objectives and outcomes
Getting acquainted with the ideas that emerged during research and development in artificial intelligence
during its fifty years of development. Understanding how to build artificially intelligent entities. Upon
completion of the course, students have a basic knowledge of artificial intelligence systems (AI). They
are able to determine what can be done with the AI approach. They can identify problems that need AI
approaches in order to be solved. Students know the characteristics of the considered AI methods. They
are prepared for professional subjects in the field of artificial intelligence and computer intelligence.
Lectures
Introduction to artificial intelligence. Traditional AI. The notion of an agent. Search, heuristics and game
links. Presentation of knowledge and procedures of automatic reasoning. Expert systems. Treatment of
uncertainty in knowledge and approximate reasoning. Introduction to training. Supervised and
unsupervised training. Introduction to neural networks. Perceptron and multilayer perceptron. Shallow
and deep networks. Autoencoders. Convolutional networks. Error learning networks. Recurrent
networks. Generative adversial networks. Application in natural language processing, speech
recognition, image recognition, robotics, medicine, bioinformatics, finance, business.
Practical classes
Implementation of algorithms covered in lectures. Implementation of the minimax algorithm in two-player games. Implementing the rules of forward chaining and backward chaining. Implementation of expert systems.