Türkçe | English

Course Catalog
Phone: +90 0462 3778353
Katalog Ana Sayfa
  Katalog Ana Sayfa  KTÜ Ana Sayfa   Katalog Ana Sayfa

YZM3012Artificial Intelligence3+1+0ECTS:5
Year / SemesterSpring Semester
Level of CourseFirst Cycle
Status Compulsory
Prerequisites and co-requisitesNone
Mode of Delivery
Contact Hours14 weeks - 3 hours of lectures and 1 hour of practicals per week
LecturerProf. Dr. Hamdi Tolga KAHRAMAN
Co-LecturerASSOC. PROF. DR. Hamdi Tolga KAHRAMAN,
Language of instructionTurkish
Professional practise ( internship ) None
The aim of the course:
The aim of this course is to implement various Artificial Intelligence (AI) methodologies, coding of AI methods in different programming languages. Modeling of various engineering problems by using AI techniques.
Learning OutcomesCTPOTOA
Upon successful completion of the course, the students will be able to :
LO - 1 : students learn the basic concepts of Artificial Intelligence1,4,81,
LO - 2 : students learn the Types and Applications of Artificial Intelligence1,4,81,
LO - 3 : students learn supervised learning methods1,4,81,
LO - 4 : students learn unsupervised learning methods1,4,81,
LO - 5 : students learn reinforcement learning methods1,4,81,
LO - 6 : students can develop the hybrid algorithms1,4,81,
CTPO : Contribution to programme outcomes, TOA :Type of assessment (1: written exam, 2: Oral exam, 3: Homework assignment, 4: Laboratory exercise/exam, 5: Seminar / presentation, 6: Term paper), LO : Learning Outcome

Contents of the Course
Introduction to Artificial Intelligence (AI): Definition of Intelligence; Definition, Aims, Importance and Limits of AI. Types and Applications of Artificial Intelligence Classification Problems and Probabilistic Classification (Naive Bayes) Classification Problems and Instance-based Classification (k-nn, decision trees) Meta-heuristic search algorithms, genetic algorithm, artificial bee colony Meta-heuristic search algorithms, symbiotic organism search Estimation Problems and Algorithms Artificial Neural Networks, Intuitive Prediction Algorithm Coding of Artificial Neural Networks
Course Syllabus
 WeekSubjectRelated Notes / Files
 Week 1Introduction to AI
 Week 2Artificial Intelligence Definition, History and Basics
 Week 3Types and Applications of Artificial Intelligence
 Week 4Classification Problems and Probabilistic Classification
 Week 5Classification Problems and Instance-Based Classification (KNN, decision trees)
 Week 6Clustering Algorithms
 Week 7Heuristic Search Algorithms Genetic Algorithm
 Week 8Heuristic Search Algorithms Artificial Bee Colony Algorithm, Symbiosis Organism Search
 Week 9Midterm exam
 Week 10Estimation Problems and Algorithms Artificial neural networks
 Week 11Estimation Problems and Algorithms Artificial neural networks
 Week 12Coding and Applying of Heuristic Estimation Algorithm in Engineering Problems
 Week 13Coding and Applying of Artificial Neural Network Algorithm in Engineering Problems
 Week 14Coding and Applying of Artificial Neural Network Algorithm in Engineering Problems
 Week 15Deep Neural Networks
 Week 16Final Exam
Textbook / Material
1Mitchell. T. M., Machine Learning, McGraw-Hill Science/Engineering/Math, 154-184, (1997).
2Artificial Intelligence: Foundations of Computational Agents, David Poole, Alan Mackworth, Cambridge University Press 2010.
3Introducing Artificial Intelligence, H. Brighton, H. Selina, Icon boks and totem boks, 2007.
Recommended Reading
1Mühendislikte Yapay Zeka Uygulamaları, Ufuk Kitabevi, Ağustos 2003.
2Yapay Sinir Ağları, Çetin ELMAS, Seçkin Yayınları, Ankara, 2003
Method of Assessment
Type of assessmentWeek NoDate

Duration (hours)Weight (%)
Mid-term exam 9 2 30
Practice 13 1 20
End-of-term exam 16 50
Student Work Load and its Distribution
Type of workDuration (hours pw)

No of weeks / Number of activity

Hours in total per term
Yüz yüze eğitim 3 14 42
Sınıf dışı çalışma 3 10 30
Arasınav için hazırlık 2 8 16
Arasınav 2 1 2
Uygulama 1 14 14
Dönem sonu sınavı için hazırlık 5 4 20
Dönem sonu sınavı 2 1 2
Total work load126