Advanced Artificial Intelligence
Code | Completion | Credits | Range | Language |
---|---|---|---|---|
X33UIP | Z,ZK | 4 | 2+2s | Czech |
- Lecturer:
- Lenka Lhotská (gar.)
- Tutor:
- Lenka Lhotská (gar.), Demlová Uznáno
- Supervisor:
- Department of Cybernetics
- Synopsis:
-
The aim of the course is to provide an overview of advanced methods used at development of intelligent systems. The following topics are discussed: advanced methods of state space search, machine learning, data mining, nature inspired algorithms (PSO, ACO, evolutionary algorithms, artificial life), multiagent systems, and their applications.
- Requirements:
-
For successful completion of the course, it is necessary to present the results of the individual work to other students and explain the approaches used.
- Syllabus of lectures:
-
1. Nature of data, information and knowledge. Introduction to advanced methods of state space search.
2. Methods of state space search (island-driven search, hierarchical search, limited-horizon search, alpha-beta search, game strategies)
3. Machine learning - overview of classical methods
4. Multiple classifiers, ILP, relational logic
5. Operators of generalization and specialization, generalization theory
6. PAC learning, reinforcement learning
7. Application of machine learning to classification, prediction and other areas
8. Data mining - methods, visualization, applications, learning of associative rules
9. Distributed methods in learning and optimization
10. PSO, ACO, cellular automata, artificial immune systems, artificial life
11. Agent - definition, types and properties, models of architecture (BDI, 3bA), social behaviour
12. Coordination, cooperation and communication in multiagent systems
13. Models of cooperation (negotiations, market and auction mechanisms)
14. Planning, alliances, coalition formation, examples of applications
- Syllabus of tutorials:
-
1.-3. Advanced algorithms of state space search
4.-9. Machine learning - Weka, programming of designed algorithm, experiments with real data, comparison of results acquired using various algorithms
10.-11. Experiments with PSO, ACO
12.-14. Multiagent systems - JADE, work with existing systems, Aglobe platform
- Study Objective:
- Study materials:
-
[1] Wooldridge M., Jennings N.: Intelligent Agents: Theory and Practice. The
Knowledge Engineering Review, 10 (1995), No.2, pp. 115-1526
[2] Dorigo, M., V. Maniezzo, and A. Colorni. „The Ant System: optimization by a Colony of Cooperating Agents.“ IEEE Trans. Syst. Man Cybern. B 26 (1996): 29-41
[3] Russell, S., Norvig, P.: Artificial Intelligence, A Modern Approach,
Prentice Hall Series in AI. New Jersey, Englewood Cliffs, 1995
- Note:
- Time-table for winter semester 2011/2012:
- Time-table is not available yet
- Time-table for summer semester 2011/2012:
- Time-table is not available yet
- The course is a part of the following study plans:
-
- Computer Technology - Software Engineering- structured studies (compulsory elective course, compulsory elective course, S1 recommendation)
- Computer Technology - System Programming- structured studies (compulsory elective course, compulsory elective course, S1 recommendation)
- Computer Technology - Computer Graphics- structured studies (compulsory elective course)
- Computer Technology - Computer Network and Internet- structured studies (compulsory elective course, compulsory elective course, S1 recommendation)
- Computer Technology - Designing Digital Systems- structured studies (compulsory elective course)