| Learning Outcomes |
PO |
MME |
| The students who succeeded in this course: |
|
|
| LO-1 |
Explains the basic concepts, history and current application areas of artificial intelligence. |
PO-12 Use the technical and modern tools required for applications related to unmanned aircraft technology.
|
Examination
|
| LO-2 |
Artificial intelligence analyzes problem-solving and search algorithms and applies them in different scenarios. |
PO-9 Have the ability to follow current developments in the field, research and share them with colleagues and teammates.
PO-12 Use the technical and modern tools required for applications related to unmanned aircraft technology.
|
Examination
|
| LO-3 |
Applies and evaluates artificial intelligence learning methods (supervised, unsupervised, reinforcement learning) to appropriate problems. |
PO-12 Use the technical and modern tools required for applications related to unmanned aircraft technology.
|
Examination
|
| LO-4 |
Designs artificial neural networks and deep learning structures within artificial intelligence models and develops applied examples. |
PO-12 Use the technical and modern tools required for applications related to unmanned aircraft technology.
|
Examination
|
| LO-5 |
Discusses the social, ethical and legal impacts of artificial intelligence technologies and develops a critical perspective. |
PO-12 Use the technical and modern tools required for applications related to unmanned aircraft technology.
|
Examination
|
PO: Programme Outcomes
MME:Method of measurement & Evaluation |
| Course Contents |
| Introduction to artificial intelligence, history and basic concepts; artificial intelligence application areas, strong and weak artificial intelligence, ethical issues; introduction to problem solving methods and search algorithms; heuristic search methods, artificial intelligence in games; knowledge representation, logical inference and rule-based systems; expert systems and sample applications; introduction to machine learning and types of learning; decision trees, Naive Bayes and performance metrics; introduction to artificial neural networks, perceptron and basic structures; introduction to deep learning, CNN and image processing applications; RNN, LSTM and natural language processing applications; reinforcement learning and its applications; current artificial intelligence technologies (GPT, Transformer, large language models); |
| Weekly Course Content |
| Week |
Subject |
Learning Activities and Teaching Methods |
| 1 |
Course introduction, introduction to artificial intelligence
/
History and development stages of artificial intelligence
/
Basic concepts: Intelligence, automation, learning |
Lecture, Question and Answer, Skill Development |
| 2 |
Artificial intelligence application areas (healthcare, defense, finance, industry, education, etc.)
The concept of strong and weak artificial intelligence
Ethical and social impacts |
Lecture, Question and Answer, Skill Development |
| 3 |
Problem solving and search methods
State space, search strategies
Informed and uninformed search algorithms |
Lecture, Question and Answer, Skill Development |
| 4 |
Heuristic search, A* algorithm
/
Depth-first / breadth-first search
/
Artificial intelligence in games (minimax, alpha-beta pruning) |
Lecture, Question and Answer, Skill Development |
| 5 |
Knowledge representation methods
/
Logical representation (propositional logic, predicate logic)
/
Rule-based systems and inference mechanisms |
Lecture, Question and Answer, Skill Development |
| 6 |
Expert systems
/
Knowledge base and inference engine
/
An example expert system design |
Lecture, Question and Answer, Skill Development |
| 7 |
Introduction to machine learning
/
Learning types: supervised, unsupervised, reinforcement learning
/
Simple algorithms: linear regression, k-NN |
Lecture, Question and Answer, Skill Development |
| 8 |
mid-term exam |
|
| 9 |
Decision trees and random forests
/ Naive Bayes classifier
/ Performance metrics such as accuracy, precision, and F1 score |
Lecture, Question and Answer, Skill Development |
| 10 |
Introduction to artificial neural networks
/
Perceptrons and feedforward networks
/
Activation functions |
Lecture, Question and Answer, Skill Development |
| 11 |
Introduction to deep learning
/
Convolutional Neural Networks (CNN)
/
Image processing applications |
Lecture, Question and Answer, Skill Development |
| 12 |
Recurrent Neural Networks (RNN, LSTM, GRU)
/
Natural Language Processing Applications
/
Chatbot Examples |
Lecture, Question and Answer, Skill Development |
| 13 |
Reinforcement learning
/
Q-learning, Deep Q-learning
/
Game and robotic applications |
Lecture, Question and Answer, Skill Development |
| 14 |
Current AI technologies (Large Language Models, GPT, Transformer structures)
/ Artificial Intelligence Projects in Industry
/ Artificial Intelligence Studies in Türkiye and the World |
Lecture, Question and Answer, Skill Development |
| 15 |
Examples of students' practical small projects
/
Final exam preparation |
Lecture, Question and Answer, Skill Development |
| 16 |
final exam |
|
| Recommend Course Book / Supplementary Book/Reading |
| 1 |
Goodfellow, I., Bengio, Y., & Courville, A. Derin Öğrenme (Türkçe çeviri). ISBN: 978-6058213296 |
| 2 |
Attila, A. Ş. (2022). Yapay Zekâ Teknolojisi ve Uygulamaları. Dikeyeksen Yayıncılık. |
| 3 |
Russell, S. J., & Norvig, P. (2021). Artificial Intelligence: A Modern Approach (4th ed.). Pearson. |
| Required Course instruments and materials |
| Computer, Projector |
