TÜRKÇE
ENGLISH
Information
| Unit | INSTITUTE OF NATURAL AND APPLIED SCIENCES |
| ELECTRICAL-ELECTRONICS ENGINEERING (MASTER) (WITH THESIS) (ENGLISH) | |
| Code | EE510 |
| Name | Gelişmiş Makine Öğrenmesi |
| Term | 2026-2027 Academic Year |
| Term | Spring |
| Duration (T+A) | 3-0 (T-A) (17 Week) |
| ECTS | 6 ECTS |
| National Credit | 3 National Credit |
| Teaching Language | Türkçe |
| Level | Belirsiz |
| Type | Normal |
| Mode of study | Yüz Yüze Öğretim |
| Catalog Information Coordinator | Doç. Dr. FATİH KILIÇ |
| Course Instructor |
The current term course schedule has not been prepared yet.
|
Course Goal / Objective
The aim of this course is to equip students with an advanced theoretical foundation in machine learning and its modern application areas, enabling them to design scientifically, ethically, and technically sound modeling solutions for complex data problems.
Course Content
This course covers advanced theoretical and applied aspects of machine learning. It addresses the mathematical foundations of machine learning, including linear algebra, probability, and optimization methods; and examines model complexity, generalization, and regularization concepts in detail. Supervised, unsupervised, and reinforcement learning approaches are discussed, along with deep learning architectures, natural language processing, and computer vision applications. Furthermore, students develop critical thinking and research skills through time series analysis, model interpretability, fairness and ethics issues, and the review of current research articles. The course is supported by end-to-end machine learning projects addressing real-world problems.
Course Precondition
There is no prerequisite for the course.
Resources
Ethem Apaydin, Introduction to Machine Learning, 2e. The MIT Press, 2010. Tom Mitchell, Machine Learning, McGraw Hill, 1997. Christopher M. Bishop, Pattern Recognition and Machine Learning, Springer, 2011.
Notes
“Hands-On Machine Learning with Scikit-Learn, Keras, and TensorFlow: Concepts, Tools, and Techniques to Build Intelligent Systems”, Aurélien Géron, O'Reilly Media (2019).
Course Learning Outcomes
| Order | Course Learning Outcomes |
|---|---|
| LO01 | Apply the mathematical and statistical foundations of machine learning to solve advanced problems. |
| LO02 | Analyze different learning paradigms (supervised, unsupervised, reinforcement, and deep learning) and select appropriate methods. |
| LO03 | Develop suitable modeling, optimization, and validation strategies for various data types. |
| LO04 | Implement advanced machine learning models, evaluate their performance, and manage generalization issues. |
| LO05 | Critically evaluate current literature and develop end-to-end solutions considering ethics, interpretability, and real-world constraints. |
Relation with Program Learning Outcome
| Order | Type | Program Learning Outcomes | Level |
|---|---|---|---|
| PLO01 | Bilgi - Kuramsal, Olgusal | Being able to specialize in at least one of the branches that form the foundations of electrical-electronic engineering by increasing the level of knowledge beyond the undergraduate level. | 3 |
| PLO02 | Bilgi - Kuramsal, Olgusal | To comprehend the integrity of all the subjects included in the field of specialization. | 3 |
| PLO03 | Bilgi - Kuramsal, Olgusal | Knowing and following the current scientific literature in the field of specialization | 4 |
| PLO04 | Bilgi - Kuramsal, Olgusal | To be able to comprehend the interdisciplinary interaction of the field with other related branches. | 2 |
| PLO05 | Bilgi - Kuramsal, Olgusal | Ability to do theoretical and experimental work | 3 |
| PLO06 | Bilgi - Kuramsal, Olgusal | To create a complete scientific text by compiling the information obtained from the research. | |
| PLO07 | Bilgi - Kuramsal, Olgusal | To work on the thesis topic programmatically, following the logical integrity required by the subject within the framework determined by the advisor. | |
| PLO08 | Bilgi - Kuramsal, Olgusal | To search for literature in scientific databases, particularly the ability to correctly and accurately scan databases and evaluate and categorize listed items. | 4 |
| PLO09 | Bilgi - Kuramsal, Olgusal | Knowledge of English at a level that can easily read and understand a scientific text written in English in the field of specialization | |
| PLO10 | Bilgi - Kuramsal, Olgusal | Compile information on his/her expertise in a presentation format and present it understandably and effectively. | 3 |
| PLO11 | Bilgi - Kuramsal, Olgusal | Ability to write a computer program in a familiar programming language, generally for a specific purpose, specifically related to the field of expertise. | |
| PLO12 | Bilgi - Kuramsal, Olgusal | Being able to guide and take the initiative in environments that require solving problems related to the field | 2 |
| PLO13 | Yetkinlikler - İletişim ve Sosyal Yetkinlik | Ability to communicate with people in an appropriate language | 2 |
| PLO14 | Yetkinlikler - Öğrenme Yetkinliği | To be able to produce projects, policies, and processes in the field of expertise and to evaluate these elements | |
| PLO15 | Yetkinlikler - Öğrenme Yetkinliği | Ability to research new topics based on existing research experience | 4 |
Week Plan
| Week | Topic | Preparation | Methods |
|---|---|---|---|
| 1 | Introduction and Course Overview | Review the syllabus and basic machine learning concepts. | Öğretim Yöntemleri: Anlatım, Soru-Cevap, Tartışma |
| 2 | Mathematical Foundations I: Linear Algebra and Probability | Revise vectors, matrices, and basic probability concepts. | Öğretim Yöntemleri: Anlatım, Soru-Cevap, Tartışma |
| 3 | Mathematical Foundations II: Optimization and Learning Theory | Study derivatives, gradients, and basic optimization methods. | Öğretim Yöntemleri: Anlatım, Soru-Cevap, Tartışma |
| 4 | Model Complexity, Regularization, and Generalization | Read about bias-variance tradeoff and overfitting. | Öğretim Yöntemleri: Anlatım, Soru-Cevap, Tartışma |
| 5 | Advanced Supervised Learning and Ensemble Methods | Review regression and classification algorithms. | Öğretim Yöntemleri: Anlatım, Soru-Cevap, Tartışma |
| 6 | Unsupervised Learning and Representation Learning | Study clustering and dimensionality reduction methods. | Öğretim Yöntemleri: Soru-Cevap, Anlatım, Tartışma |
| 7 | Deep Learning Fundamentals | Learn basics of neural networks. | Öğretim Yöntemleri: Anlatım, Soru-Cevap, Tartışma |
| 8 | Mid-Term Exam | Review all previous topics. | Ölçme Yöntemleri: Yazılı Sınav |
| 9 | Natural Language Processing and Transformer Models | Study basic NLP concepts and attention mechanism. | Öğretim Yöntemleri: Anlatım, Soru-Cevap, Tartışma |
| 10 | Computer Vision and Deep Visual Models | Review CNNs and image processing basics. | Öğretim Yöntemleri: Anlatım, Soru-Cevap, Tartışma |
| 11 | Time Series and Sequential Models | Study time series analysis and RNN/LSTM. | Öğretim Yöntemleri: Anlatım, Soru-Cevap, Tartışma |
| 12 | Reinforcement Learning and Decision Processes | Learn Markov decision processes and reward systems. | Öğretim Yöntemleri: Soru-Cevap, Anlatım, Tartışma |
| 13 | Model Interpretability, Fairness, and Ethics | Read about AI ethics and model interpretability. | Öğretim Yöntemleri: Anlatım, Soru-Cevap, Tartışma |
| 14 | Future Trends and Project Presentation | Explore recent ML research trends. | Öğretim Yöntemleri: Anlatım, Soru-Cevap, Tartışma |
| 15 | Project Presentation and Review | Prepare your project and practice presentation. | Ölçme Yöntemleri: Sözlü Sınav, Performans Değerlendirmesi, Proje / Tasarım |
| 16 | Term Exams | Review all course materials. | Ölçme Yöntemleri: Yazılı Sınav |
| 17 | Term Exams | Complete missing topics and revise. | Ölçme Yöntemleri: Yazılı Sınav |
Student Workload - ECTS
| Works | Number | Time (Hour) | Workload (Hour) |
|---|---|---|---|
| Course Related Works | |||
| Class Time (Exam weeks are excluded) | 14 | 3 | 42 |
| Out of Class Study (Preliminary Work, Practice) | 16 | 5 | 80 |
| Assesment Related Works | |||
| Homeworks, Projects, Others | 1 | 24 | 24 |
| Mid-term Exams (Written, Oral, etc.) | 1 | 2 | 2 |
| Final Exam | 1 | 2 | 2 |
| Total Workload (Hour) | 150 | ||
| Total Workload / 25 (h) | 6,00 | ||
| ECTS | 6 ECTS | ||