Course details

Intelligent Systems

SIN Acad. year 2006/2007 Winter semester 5 credits

Current academic year

Introduction into intelligent systems theory, uncertain and incomplete information processing, intelligent systems modeling, model based development of intelligent systems, introduction to softcomputing, agent and multiagent architectures, learning and adaptive systems, reinforcement learning, planing and scheduling, multiagent systems and their applications,  robotic systems, perception, sensor systems, expert systems, datamining.

Guarantor

Janoušek Vladimír, doc. Ing., Ph.D. (DITS)

Language of instruction

Czech

Completion

Examination

Time span

  • 39 hrs lectures
  • 13 hrs projects

Department

Department of Intelligent Systems (UITS)

Subject specific learning outcomes and competences

Students acquire knowledge of principles of intelligent systems and so they will be able to design and construct such systems.

Learning objectives

To acquaint students with theory and principles of intelligent systems and with representative practical systems.

Prerequisite knowledge and skills

Artificial intelligence basics: Problem solving, state space search, problem decomposition, machine learning principles, statistical and structural pattern recognition. Fundamentals of computer vision. Base principles of natural language processing.

Study literature

    1. Russel, S., Norvig, P.: Artificial Intelligence, a Modern Approach, Pearson Education Inc., 2003, ISBN 0-13-080302-2
    2. Zeigler, B.P.: Theory of Modeling and Simulation, Academic Press; 2 edition (March 15, 2000), ISBN 978-0127784557
    3. Valeš, M.: Inteligentní dům. Brno, Vydavatelství ERA, 2006.
    4. Přibyl, P., Svítek, M.: Inteligentní dopravní systémy, Nakladatelství BEN, Praha 2001, ISBN 80-7300-029-6
    5. Automatizace. http://www.automatizace.cz/

Syllabus of lectures

  1. Introduction
  2. Intelligent systems modeling
  3. Model based development of intelligent systems
  4. Introduction to softcomputing
  5. Agent and multiagent architectures 
  6. Learning and adaptive systems
  7. Reinforcement learning
  8. Planing and Scheduling 
  9. Multiagent systems and their applications
  10. Robotic systems
  11. Perception, sensor systems
  12. Expert systems, datamining
  13. Summary

Progress assessment

Study evaluation is based on marks obtained for specified items. Minimimum number of marks to pass is 50.

Controlled instruction

  • Mid-term written test
  • Individuální project
Back to top