Artificial Intelligent Systems

Higher education teachers: Dobrišek Simon

Subject description

Required (pre)knowledge:

• The basics of linear algebra, multivariate analysis, optimization, statistics, probability theory, and computer programming.

Content (Syllabus outline):

• Introduction to artificial intelligent systems: artificial perception, artificial intelligence, soft computing, machine learning, autonomous agents, and ambient intelligence.
• Intelligent problem solving: problem decomposition and reduction, graph representation of problems, and graph search - exhaustive and heuristic search algorithms.
• Case study: assembly automation.
• Expert systems: expert system components and human interfaces, procedural and declarative knowledge, and reasoning process.
• Knowledge representation: production rules, fuzzy production rules, and representation based on the Petri nets.
• Inference: forward and backward chaining, fuzzy inference, and probabilistic inference.
• Case study: knowledge-based computer vision systems.
• Knowledge from experimental data: multivariate regression with artificial neural networks and support vector machines.
• Multi-agent systems: intelligent agent, multi-agent systems, agent communication language.
• Case study: FIPA-compliant multi-agent platforms.

Intended learning outcomes:

After completing this course, the student will be able to demonstrate knowledge and understanding of:

• construction of systems based on the use of the methods of artificial intelligence;
• modelling of specific human mental abilities (general problem solving, learning, and reasoning);
• graph search methods, the integration of human knowledge into artificial intelligent systems, and searching for regularities in data.

By the end of the course, students will have developed the following transferable skills:

• use of information technology: the use of open source development tools (OpenCV, WEKA, CLIPS, JADE), programming environments (Matlab, Netbeans), programming languages (Java, Prolog);
• problem solving: problem analysis, algorithm design, implementation and testing of a program.

Learning and teaching methods:

• Lectures
• Coursework
• Laboratory exercises and projects

Study materials

• S. J. Russell, P. Norvig: Artificial Intelligence: A Modern Approach, Prentice Hall, 2010.
• Mohri M., Rostamizadeh A., Talwalkar, A. : Foundations of Machine Learning, The MIT Press, 2012.
• N. Pavešić, Razpoznavanje vzorcev: uvod v analizo in razumevanje vidnih in slušnih signalov, (3. popravljena in dopolnjena izd., 2 zv.), Založba FE in FRI, 2012