Information Package / Course Catalogue
Advanced Artificial Intelligence
Course Code: MTK637
Course Type: Area Elective
Couse Group: Third Cycle (Doctorate Degree)
Education Language: Turkish
Work Placement: N/A
Theory: 3
Prt.: 0
Credit: 3
Lab: 0
ECTS: 8
Objectives of the Course

The purpose of this course is to introduce and to understand the significance of artificial intelligence in computer science, and the course aims to gain the ability of researching using modern approaches in this field in both theoretically and practically.

Course Content

Introduction to Artificial Intelligence, Knowledge representation, Production rules, inclusion hierarchies, prepositional and predicate calculus, Knowledge representation, Rules of inference, frames, semantic networks, constraints and syntactic approaches, Searching Algorithms, Learning Algorithms, Decision trees, Neural networks, Genetic algorithms, Expert systems, robotics, computer vision, natural language processing, speech recognition.

Name of Lecturer(s)
Learning Outcomes
1.Ability to have fundamental knowledge of artificial intelligence
2.Ability to design intelligent systems
3.Ability to use artificial intelligence techniques
4.To be able to gain the skill of interpreting some interrelations among these concepts
5.To be able to use mathematical concepts in solving certain types of problems
Recommended or Required Reading
1.Artificial Intelligence: A Modern Approach, Stuart Russell , Peter Norvig, 3rd edition, 2009
Weekly Detailed Course Contents
Week 1 - Theoretical
Introduction to AI
Week 2 - Theoretical
Programming languages
Week 3 - Theoretical
Knowledge representation: Production rules, inclusion hierarchies, prepositional and predicate calculus
Week 4 - Theoretical
Knowledge representation: Rules of inference, frames, semantic networks, constraints and syntactic approaches.
Week 5 - Theoretical
Searching: Hypothesis and test, depth-first search, breadth-first search
Week 6 - Theoretical
Searching: Heuristic search, optimal search
Week 7 - Theoretical
Searching: Game trees and adversarial search: minimax search and alpha-beta pruning
Week 8 - Theoretical
Learning: Decision trees
Week 9 - Theoretical
Learning: Neural nets, perceptrons, Midterm exam
Week 10 - Theoretical
Learning: Neural nets, perceptrons
Week 11 - Theoretical
Learning:Genetic algorithms
Week 12 - Theoretical
Expert systems, robotics, computer vision, natural language processing, speech recognition
Week 13 - Theoretical
Expert systems, robotics, computer vision, natural language processing, speech recognition
Week 14 - Theoretical
Expert systems, robotics, computer vision, natural language processing, speech recognition
Week 15 - Final Exam
Final exam
Assessment Methods and Criteria
Type of AssessmentCountPercent
Assignment1%5
Term Assignment1%5
Midterm Examination1%20
Final Examination1%70
Workload Calculation
ActivitiesCountPreparationTimeTotal Work Load (hours)
Lecture - Theory140342
Assignment1066
Term Project1066
Individual Work140570
Midterm Examination130232
Final Examination142244
TOTAL WORKLOAD (hours)200
Contribution of Learning Outcomes to Programme Outcomes
PÇ-1
PÇ-2
PÇ-3
PÇ-4
PÇ-5
PÇ-6
PÇ-7
PÇ-8
PÇ-9
PÇ-10
PÇ-11
PÇ-12
PÇ-13
PÇ-14
PÇ-15
OÇ-1
5
4
5
4
4
4
3
3
4
2
2
OÇ-2
4
4
4
5
4
5
OÇ-3
4
5
5
5
5
5
3
3
3
4
4
OÇ-4
4
5
5
5
5
5
3
3
3
3
3
OÇ-5
4
5
5
4
5
4
3
3
3
3
4
Adnan Menderes University - Information Package / Course Catalogue
2026