Curriculum.

Course title Basic of artificial inteligence
Code I122
Status Elective course
Level Elementary
Year 2nd Semester 3rd
ECTS 5
Lecturer Darko Dukić, Ph.D., Associate Professor, Stojanka Dukić, PhD.
Course objective The course goal is to familiarize students with methods, techniques, acchievements and appling of artificial intelligence.
Prerequisites None
Learning outcomes: After successfully completed course, student will be able to:

  1. Distinguish artificial intelligence from natural.

2.      Use Expert systems.

3.      Model system for multicriterial suboptimal deceison through various forms of knowledge views as well as knowledge base definition.

4.      Use agents and multi-agents systems.

5.      Use conclusion rules in indirect logic.

6.      Use of neural networks in deceison making.

Correlation of learning outcomes, teaching methods and evaluation
Teaching activity ECTS Learning outcome Students activity Methods of evaluation Points
min max
Class attendance 1,5 1-6 Class attendance Evidence list 0 0
Knowledge test:

preliminary exams or written/oral exam

2,5 1-6 Preparation for preliminary exams or written/oral exam Preliminary exams grade or written/oral exam grade 0 90
Seminar paper 1,0 1-6 Preparation and presentation of a seminar paper Seminar paper grade 0 10
Total 5,0 0 100
Consultations
Gained competencies After successfully completing the course the student will be able to distinguish artificial intelligence from natural as well as to describe and apply basic ideas of artificial intelligence.
Content (Course curriculum) Basic definitions and classifications of intelligence and artificial intelligence. Turing’s test. Expert systems (definition, architecture, application). Knowledge view, methods and techniques of knowledge view. Knowledge view formalism using semantic diagrams. Agents and multi-agents of intelligence systems. Fuzzy sets and properties. Operations on fuzzy sets. Fuzzy arithmetic. Fuzzy logic. Rules of conclusions in fuzzy logic. Conclusions on time relations in temporal rich domains. Neural networks.
Recommended reading 1. Russell S., Norvig P., Artificial Intelligence – A Modern Approach, 2nd Ed., Prentice Hall, 2003.

2. Haykin S., Neural Networks, Comprehensive Foundation, 2nd, Prentice Hall, 1999.

3. Zimmermann, H.J., Fuzzy Set Theory and Its Applications, 2nd. Ed., Kluwer Academic Publishers, 1991

Additional reading 1. Klir G.J.,. Fogler T.A, Fuzzy Sets, Uncertanity and Information, Prentice Hall, Englewood Cliffs, New York, 1988.

2. Kaufmann A., Gupta M.M., Introduction to Fuzzy Arithmetic, Theory and Applications, Van Nostrand Reinhold, New York, 1991.

Instructional methods Lectures (30), Laboratory exercises (30).
Exam formats Two preliminary exams during the semester or written/oral examination.
Language Croatian/English.
Quality control and successfulness follow up Students’ survey, lecturer and expert evaluation, student’s success on exams, international supervision.
Back to Top