Početna stranicaVisoka učilištaKorisničke stranice
Artificial Intelligence
Abbreviation: UMINTLoad: 30(L) + 15(E) + 0(LE) + 0(CE) + 0(PEE) + 0(FE) + 0(S) + 0(DE) + 0(P) + 0(FLE) + 0()
Lecturers in charge: prof. dr. sc. Bojan Jerbić
doc. dr. sc. Petar Ćurković
doc. dr. sc. Tomislav Stipančić
Lecturers: doc. dr. sc. Darko Chudy ( Lectures )
dr. sc. Tomislav Domazet-Lošo ( Lectures )
izv. prof. dr. sc. Mladen Kučinić ( Lectures )
doc. dr. sc. Petar Ćurković ( Exercises )
dr. sc. Bojan Šekoranja ( Exercises )
doc. dr. sc. Tomislav Stipančić ( Exercises )
dr. sc. Marko Švaco ( Exercises )
Course description: Course objectives:
Philosophy and phenomenology of artificial intelligence (AI). Possibilities and limits of formalised knowledge and thinking. Introduction to the methods of AI, with accent on realtime problem solving with lack of information, uncertainty and limited computer resources.

Enrolment requirements and required entry competences for the course:


Student responsibilities:
Attendance of lectures and exercises, exam.

Grading and evaluation of student work over the course of instruction and at a final exam:
Attendance of exercises and lectures is evaluated (10%), as well as sucess on final exam (90%).

Methods of monitoring quality that ensure acquisition of exit competences:
Coverage of quality:
immediately in the classroom, in direct communication with the students (student questions and discussion);
periodically, according to the processed education content, by grading of colloquiums and project;
exposition/discussing of results (scores) instructing students how to achieve better results.

Upon successful completion of the course, students will be able to (learning outcomes):
define artificial intelligence processes
identify a technical problem suitable for AI methods application
select, adapt, and implement an AI method to solve a given technical problem
create new AI methods

Lectures
1. Introduction. History. AI in mithology, science and application. Can computer think?
2. Expert systems. Problem solving. Image of knowledge.
3. Knowledge bases browsing. Logic conclusioning, First Order Logic. Predicative logic. Planning. Conclusioning by probability.
4. Programming languages and tools (PROLOG, LISP, C++,...).
5. Learning methods. Knowledge gaining.
6. Inductive and deductive learning methods. Reinforcement learning.
7. Biological models of learning. Brain based learning systems. Perception. Neural networks.
8. Neural networks.
9. Neural networks. Genetic algorithms.
10. Neural networks. Genetic algorithms.
11. Genetic algorithms.
12. Autonomous agents. Communication.
13. Intelligent behaviour. Social intelligence.
14. Artificial life. Chaos theory.
15. Psyhological foundations, emotions, iamgination, creativity. Application. Robotics and AI.

Exercises
1. Application of AI methods, examples.
2. Introduction to computer tools adjusted for implementation of AI methods.
3. Predicative logic programming and knowledge base using PROLOG.
4. Predicative logic programming and knowledge base using PROLOG.
5. Examples of simbolic programming in LISP.
6. Examples of simbolic programming in LISP.
7. Advanced computer tools application (MatLab, Mathematica, NNT) on examples of neural networks and genetic algorythms.
8. Advanced computer tools application (MatLab, Mathematica, NNT) on examples of neural networks and genetic algorythms.
9. Student work autonomous writing of intelligent programme for given problem (recognition, classification).
10. Student work autonomous writing of intelligent programme for given problem (recognition, classification).
11. Student work autonomous writing of intelligent programme for given problem (recognition, classification).
12. Student work autonomous writing of intelligent programme for given problem (recognition, classification).
13. Student work autonomous writing of intelligent programme for given problem (recognition, classification).
14. Recent research and developing projects of AI methods in robotics and solving of different engineering problems.
15. Recent research and developing projects of AI methods in robotics and solving of different engineering problems.
Lecture languages: hr
Compulsory literature:
1. Russell S. & Norvig P., AI: A Modern Approach, The Intelligent Agent Book, Sec. Ed., Prentice Hall, 2002.
2. Minsky M., The Society of Mind, Simon & Schuster, The MIT Press, Cambridge, 2000.
3. Munindar P. S., MULTIAGENT SYSTEMS - A Theoretical Framework for Intentions, Know-How, and Communications, Springer-Verlag, Lecture Notes in Computer Science, Vol. 799.
Recommended literature: - - -
Legend
L - Lectures
FLE - Practical foreign language exercises
-
E - Exercises
LE - Laboratory exercises
CE - Project laboratory
PEE - Physical education excercises
FE - Field exercises
S - Seminar
DE - Design exercises
P - Practicum
* - Not graded
Copyright (c) 2006. Ministarstva znanosti, obrazovanja i športa. Sva prava zadržana.
Programska podrška (c) 2006. Fakultet elektrotehnike i računarstva.
Oblikovanje(c) 2006. Listopad Web Studio.
Posljednja izmjena 2019-06-07