Education Information System

Course Information

Course Information

Course Title	Code	Language	Type	Semester	L+U Hour	Credits	ECTS
Artificial Intelligence Systems	MEM388	Turkish	Compulsory	6. Semester	3 + 0	3.0	5.0

Prerequisite Courses
Course Level	Undergraduate
Mode of delivery	Face to face
Course Coordinator	Doç. Dr. Ferzan KATIRCIOĞLU
Instructor(s)
Goals	This is your lesson, but to educate students about the various lower branches of artificial intelligence.
Course Content	Artificial intelligence and expert systems, Artificial intelligence programming languages: Prolog, Artificial intelligence programming languages: Lisp, Game programming, Artificial neural networks, Artificial neural network applications: image processing, Artificial neural network applications: robot, Artificial neural network applications: system and character fuzzy logic, fuzzy logic applications: fuzzy-pid, ant colony optimization, CKO applications, Genetic Optimization, GO applications.

Learning Outcomes

#	Öğrenme Kazanımı
1	Having basic knowledge about artificial intelligence.
2	Problem solving with artificial intelligence methods.

Lesson Plan (Weekly Topics)

Week	Topics/Applications	Method
1. Week	Artificial intelligence and expert systems.	Interview
2. Week	Artificial intelligence and expert systems.	Interview
3. Week	Artificial intelligence programming languages: Prolog, Lisp	Interview
4. Week	Artificial intelligence programming languages: Prolog, Lisp	Interview
5. Week	Artificial intelligence programming languages: Prolog, Lisp	Interview
6. Week	Game programming	Interview
7. Week	Artificial neural networks.	Interview
8. Week	Artificial Neural Networks
9. Week	Artificial neural network applications: image processing	Interview
10. Week	Artificial neural network applications: robot	Interview
11. Week	Artificial neural network applications: system and character recognition	Interview
12. Week	Fuzzy logic, fuzzy logic applications: fuzzy-pid, ant column optimization	Interview
13. Week	Genetic Optimization	Interview
14. Week	Genetic Optimization	Interview

*Midterm and final exam dates are not specified in the 14-week course operation plan. Midterm and final exam dates are held on the dates specified in the academic calendar with the decision of the University Senate.

The Matrix for Course & Program Learning Outcomes

No	Program Requirements	Level of Contribution
No	Program Requirements	1	2	3	4	5
3	To gain the ability to identify, model, and solve engineering problems					✔

Relations with Education Attainment Program Course Competencies

Program Requirements	DK1	DK2
PY3	5	5

Recommended Sources

Ders Kitabı veya Notu	Ders Kitabı veya Ders Notu bulunmamaktadır.
Diğer Kaynaklar	Steven L.Tanimoto, The Elements of Artificial Intelligence: An Introduction Using LISP, Computer Science Press. James A.Freeman, David M.Skapura, Neural Networks, Algorithms, Applications and Programming Techniques, Addison Wesley, 1991. Chin-Teng Lin, C.S.G. Lee, Neural Fuzzy Systems, Prentice Hall, 1996.

ECTS credits and course workload

ECTS credits and course workload		Quantity	Duration (Hour)	Total Workload (Hour)
Sınavlar	Midterm 1	50	1	50
Sınavlar	Final	77.5	1	77.5
Total Workload				127.5
*AKTS = (Total Workload) / 25,5		ECTS Credit of the Course		25.5 5.0