Artificial Intelligence

The course cannot be taken simultaneously with:

Advanced Artificial Intelligence (A5M33UIP)

The course is a substitute for:

Advanced Artificial Intelligence (A5M33UIP)

Lecturer:

Vladimír Mařík (gar.), Radek Mařík, Petr Pošík

Tutor:

Martin Macaš, Radek Mařík, Petr Pošík

Supervisor:

Department of Cybernetics

Synopsis:

The course is aimed at providing theoretically deeper knowledge in the area of Artificial Intelligence in the extent needed to study the branch of study Robotics. It is organized around several topics: pattern recognition and machine learning, theory of multi-agent systems and artificial life. The linkage between the theoretical and practical applications is rather stressed.

Requirements:

Syllabus of lectures:

1.Classification methods, Bayesian and non-Bayesian tasks

2.Adaboost, SVM classifiers

3.Graphical probabilistic and Markov models in machine learning

4.Theory of learning, problems of consistency, capacity, PAC

5.Learning of classification rules (AQ, CN2)

6.Sequential pattern recognition, Walds algorithm, extraction and synthesis of features, properties

7.Planning, representation of the planning problem, linear and non-linear planning

8.Methods of planning: TOPLAN, POPLAN, SATPLAN, GRAPHPLAN

9.Multi-agent systems: Reactive and deliberative agents, BDI architecture, reflection

10.Collective behavior of agents, distributed decision making, negotiation techniques, CNP, auction and voting techniques

11.Social knowledge, social behavior of agents, met-reasoning, coalition formation, team cooperation

12.Multi-agent planning and scheduling, industrial applications

13.Artificial life, principles, algorithms, applications

14.Applications

Syllabus of tutorials:

1.Introduction, definition of the course project

2.Bayesian and non-Bayesian tasks

3.Adaboost and SVM classifiers demos of tasks

4.Markov models and machine learning I

5.Markov models and machine learning II

6.AQ and CN2 systems, experiments I

7.AQ and CN2 systems, experiments II

8.Planning tasks

9.Planning - practical exercise

10.Aglobe Systems and its features, demo

11.Demos of multi-agent systems (Agentfly, ProPlant, MAST)

12.Agentification of systems, semantic information

13.Artificial life demos

14.Delivery of course project

Study Objective:

Study materials:

1. Wooldridge, M.: An Introduction to Multi-Agent Systems, John Wiley & Sons, 2002

2. Nilsson N.J. & Nilsson, N.J.: Artificial Intelligence: A New Synthesis. Elsevier Science, 1998

Note:

Time-table for winter semester 2011/2012:

Time-table is not available yet

Time-table for summer semester 2011/2012:

	06:00–08:0008:00–10:0010:00–12:0012:00–14:0014:00–16:0016:00–18:0018:00–20:0020:00–22:0022:00–24:00
Mon
Tue	roomKN:E-126 Pošík P. Mařík R. 12:45–14:15 (lecture parallel1) Karlovo nám. Trnkova posluchárna K5roomKN:E-132 Macaš M. Pošík P. 16:15–17:45 (lecture parallel1 parallel nr.101) Karlovo nám. Laboratoř PCroomKN:E-220 18:00–19:30 (lecture parallel1 parallel nr.102) Karlovo nám. Laboratoř BIO
Fri
Thu
Fri

The course is a part of the following study plans:

• Kybernetika a robotika - Robotika (compulsory course of the specialization)