Information Package / Course Catalogue
Fundamentals of Artificial Intelligence
Course Code: ELTC151
Course Type: Area Elective
Couse Group: Short Cycle (Associate's Degree)
Education Language: Turkish
Work Placement: N/A
Theory: 2
Prt.: 0
Credit: 2
Lab: 0
ECTS: 2
Objectives of the Course

This course aims to provide students with information about artificial intelligence and its fundamental concepts and historical development; to introduce the basic approaches of machine learning and deep learning; to provide theoretical knowledge about supervised, unsupervised, and reinforcement learning methods and current deep learning architectures; and to raise awareness about the application areas of artificial intelligence and its ethical and legal responsibilities.

Course Content

The course covers fundamental concepts of artificial intelligence, its historical development, machine learning and deep learning approaches, basic neural network architectures, ethical and legal responsibilities, and artificial intelligence applications.

Name of Lecturer(s)
Learning Outcomes
1.Knowing the basic concepts of artificial intelligence and its historical development.
2.Knowing the application areas where artificial intelligence is widely used.
3.To learn about the ethical and legal responsibilities related to the use of artificial intelligence.
4.Understanding the concept of machine learning, basic machine learning algorithms, and their application areas.
5.Understanding the concept of deep learning, basic deep learning algorithms, and their application areas.
Recommended or Required Reading
1.Artificial Intelligence Problems - Methods - Algorithms, Seçkin Publishing, ISBN: 9753479859 (Assoc. Prof. Dr. Vasif V. Nabiyev)
2.Deep Learning with Python, Buzdağı Publishing, ISBN: 9786056902420 (François Chollet)
Weekly Detailed Course Contents
Week 1 - Theoretical
The concept of artificial intelligence.
Week 2 - Theoretical
Historical development of artificial intelligence.
Week 3 - Theoretical
Fundamental concepts of artificial intelligence.
Week 4 - Theoretical
Ethical and legal responsibilities in the use of artificial intelligence.
Week 5 - Theoretical
Introduction of machine learning.
Week 6 - Theoretical
Supervised learning. (Quiz)
Week 7 - Theoretical
Unsupervised learning.
Week 8 - Theoretical
Reinforcement learning. (Midterm Examination)
Week 9 - Theoretical
Introduction of artificial neural networks and deep learning.
Week 10 - Theoretical
Convolutional neural networks and applications.
Week 11 - Theoretical
Attention-based networks and applications.
Week 12 - Theoretical
Recurrent neural networks and applications. (Assignment)
Week 13 - Theoretical
Encoder–decoder neural networks and applications.
Week 14 - Theoretical
Generative adversarial networks and applications.
Assessment Methods and Criteria
Type of AssessmentCountPercent
Assignment1%5
Quiz1%5
Midterm Examination1%30
Final Examination1%60
Workload Calculation
ActivitiesCountPreparationTimeTotal Work Load (hours)
Lecture - Theory140228
Assignment1415
Quiz1415
Midterm Examination1516
Final Examination1516
TOTAL WORKLOAD (hours)50
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
OÇ-1
5
4
3
OÇ-2
5
4
3
OÇ-3
5
4
3
OÇ-4
5
4
3
OÇ-5
5
4
3
Adnan Menderes University - Information Package / Course Catalogue
2026