TÜRKÇE
ENGLISH
Information
| Unit | INSTITUTE OF NATURAL AND APPLIED SCIENCES |
| COMPUTER ENGINEERING (MASTER) (WITHOUT THESIS) | |
| Code | CENGT003 |
| Name | Machine Learning |
| Term | 2022-2023 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 | Yüksek Lisans Dersi |
| Type | Normal |
| Mode of study | Yüz Yüze Öğretim |
| Catalog Information Coordinator | |
| Course Instructor |
The current term course schedule has not been prepared yet.
|
Course Goal / Objective
At the end of this course, the student will learn the basics behind modern machine learning methods. knowledge of working principles and how, why and when they work will be; the ability to use this knowledge in the development of various learning models will win.
Course Content
Curve fitting methods, classification, training models, support vector machines, decision trees, ensemble learning and random forests, dimension reduction, principal component analysis, model selection, unsupervised learning techniques
Course Precondition
Resources
Hands-on machine learning with Scikit-Learn, Keras and TensorFlow: Concepts, Tools, and Techniques to Build Intelligent Systems, Aurélien Géron, O'Reilly Media, 2019.
Notes
Course Learning Outcomes
| Order | Course Learning Outcomes |
|---|---|
| LO01 | Understanding the complexity of machine learning algorithms (regression, classification, clustering, and dimensional reduction) and their limitations. |
| LO02 | Choosing suitable machine learning algorithms for real-life applications. |
| LO03 | To be able to apply machine learning algorithms to problems with confidence and develop their own applications. |
| LO04 | Do machine learning experiments using real-world data. |
| LO05 | Measuring model quality using relevant performance/error metrics for each application. |
Relation with Program Learning Outcome
| Order | Type | Program Learning Outcomes | Level |
|---|---|---|---|
| PLO01 | Belirsiz |
Week Plan
| Week | Topic | Preparation | Methods |
|---|---|---|---|
| 1 | Introduction, machine learning methods and challenges, trial and validation | Öğretim Yöntemleri: Anlatım |
|
| 2 | End-to-end machine learning project: data collection, cost function, data visualization | Öğretim Yöntemleri: Anlatım |
|
| 3 | End-to-end machine learning project: data preparation, model selection, training, optimization | Öğretim Yöntemleri: Anlatım |
|
| 4 | Classification | Öğretim Yöntemleri: Anlatım |
|
| 5 | Model training I | Öğretim Yöntemleri: Anlatım |
|
| 6 | Model training II | Öğretim Yöntemleri: Anlatım |
|
| 7 | Support vector machines | Öğretim Yöntemleri: Anlatım |
|
| 8 | Mid-Term Exam | Ölçme Yöntemleri: Yazılı Sınav |
|
| 9 | Decision trees | Öğretim Yöntemleri: Anlatım |
|
| 10 | Ensemble learning and random forests | Öğretim Yöntemleri: Anlatım |
|
| 11 | Dimensionality Reduction | Öğretim Yöntemleri: Anlatım |
|
| 12 | Unsupervised learning techniques I - clustering | Öğretim Yöntemleri: Anlatım |
|
| 13 | Unsupervised (unsupervised) learning techniques II – Gaussian mixtures (density estimation) | Öğretim Yöntemleri: Anlatım |
|
| 14 | Examples I | Öğretim Yöntemleri: Anlatım |
|
| 15 | Examples II | Öğretim Yöntemleri: Anlatım |
|
| 16 | Term Exams | Ölçme Yöntemleri: Yazılı Sınav |
|
| 17 | Term Exams | Ölçme Yöntemleri: Yazılı Sınav |