Computer Engineering (Master) (with Thesis) (English) | |||||
Master | TR-NQF-HE: Level 7 | QF-EHEA: Second Cycle | EQF-LLL: Level 7 |
Course Code: | COE5021 | ||||
Course Name: | Machine Learning | ||||
Semester: |
Fall Spring |
||||
Course Credits: |
|
||||
Language of instruction: | English | ||||
Course Condition: | |||||
Does the Course Require Work Experience?: | Yes | ||||
Type of course: | Departmental Elective | ||||
Course Level: |
|
||||
Mode of Delivery: | Face to face | ||||
Course Coordinator: | Doç. Dr. EMİR SEYYEDABBASİ | ||||
Course Lecturer(s): | Femilda Josephin Joseph Shobana Bai | ||||
Course Assistants: |
Course Objectives: | This course aims to provide a comprehensive introduction to computational approaches for addressing diverse learning tasks. Key topics encompass supervised learning and unsupervised algorithms, ensemble learning methods, and artificial neural networks. Participants will gain practical insights into the applications of these techniques, supported by essential concepts such as data pre-processing, and an understanding of issues related to bias and variance in machine learning models. Through theoretical foundations and hands-on applications, students will develop the skills necessary to navigate and implement various computational approaches in real-world scenarios. |
Course Content: | This course provides a comprehensive overview of machine learning, covering both supervised and unsupervised learning approaches. It begins with an exploration of supervised learning, addressing regression problems and classification problems, including logistic regression, K-Nearest Neighbor, decision trees, handling imbalanced datasets, random forests, and techniques like cross-validation. The course delves into exploratory data analysis and data pre-processing techniques essential for effective machine learning. It then progresses to advanced topics such as hyperparameter tuning, dimensionality reduction, and unsupervised learning. Ensemble learning methods, particularly boosting techniques, are covered, along with an in-depth study of artificial neural networks, including perceptrons and multi-layer networks. |
The students who have succeeded in this course;
1) Gain proficiency in both regression and classification problems, implementing and interpreting algorithms such as logistic regression, K-Nearest Neighbor, and decision trees. 2) Competence in addressing imbalanced datasets, coupled with skills in exploratory data analysis and effective data pre-processing techniques. 3) Develop an understanding of and the ability to apply advanced techniques, including hyperparameter tuning, dimensionality reduction, and unsupervised learning approaches. 4) Knowledge acquisition in boosting techniques within ensemble learning, accompanied by practical skills in designing and evaluating ensemble models. 5) In-depth comprehension of artificial neural networks, covering perceptrons and multi-layer networks, along with practical proficiency in designing, training, and evaluating neural network models. |
Week | Subject | Related Preparation |
1) | Introduction to Machine Learning | Lecture Notes |
2) | Supervised Learning - Regresion Problem | Lecture Notes |
3) | Supervised Learning - Classification Problem - Logistic Regression - K-Nearest Neighbor | Lecture Notes |
4) | Exploratory Data Analysis Data Pre-processing | Lecture Notes |
5) | Supervised Learning - Decision Tree - Handling imbalanced dataset | Lecture Notes |
6) | Supervised Learning - Random Forest - Cross Validation and its types | Lecture Notes |
7) | Supervised Learning - Naive Bayes and Support Vector Machines | Lecture Notes |
8) | Midterm | Lecture Notes |
9) | Supervised Learning - Hyper parameter tuning Dimensionality Reduction | Lecture Notes |
10) | Unsupervised Learning | Lecture Notes |
11) | Ensemble Learning Methods - Boosting Techniques | Lecture Notes |
12) | Artificial Neural Networks Perceptrons | Lecture Notes |
13) | Artificial Neural Networks Multi-layer Networks | Lecture Notes |
14) | Artificial Neural Networks Multi-layer Networks | Lecture Notes |
Course Notes / Textbooks: | • Introduction to Machine Learning, Ethem Alpaydın (3rd Edition), 2014, MIT Press • Understanding Machine Learning: From Theory to Algorithms, Shai Shalev-Shwartz, Shai Ben-David (1st Edition), 2014, Cambridge University Press • Learning from Data, Yaser S. Abu-Mostafa, Malik Magdon-Ismail, Hsuan-Tien Lin (1st Edition), 2012, AMLBook • Machine Learning Refined: Foundations, Algorithms, and Applications, Jeremy Watt, Reza Borhani, Aggelos K. Katsaggelos (1st Edition), 2016, Cambridge University Press |
References: | • Machine Learning: a Probabilistic Perspective, Kevin P. Murphy (1st Edition), 2012, MIT Press • Machine Learning, Tom Mitchell (1st Edition), 1997, McGraw Hill Press • A Course in Machine Learning10, Hal Daume III (2nd Edition), 2017 • Introduction to Machine Learning, Alex Smola, S.V.N. Vishwanathan (1st Edition), 2008, Cambridge University Press • Machine Learning: the Art and Science of Algorithms that Make Sense of Data, Peter Flach (1st Edition), 2012, Cambridge University Press • Bayesian Reasoning and Machine Learning, David Barber (1st Edition - Rev. 2020), 2012, Cambridge University Press • The Hundred-Page Machine Learning Book, Andriy Burkov, 2019 • Machine Learning Mastery with Python, Jason Brownlee, 2016 • Reinforcement Learning: an Introduction, Richard S. Sutton, Andrew G. Barto (2nd Edition - Rev. 2020), 2018, MIT Press • Artificial Intelligence - With an Introduction to Machine Learning17, Richard E. Neapolitan, Xia Jiang (2nd Edition), 2018, CRC Press • Machine Learning Yearning, Andrew Ng (1st Edition), 2020, deeplearning.ai • Machine Learning - The New AI, Ethem Alpaydin (1st Edition), 2016, MIT Press |
Course Learning Outcomes | 1 |
2 |
3 |
4 |
5 |
|||||||
---|---|---|---|---|---|---|---|---|---|---|---|---|
Program Outcomes | ||||||||||||
1) Being able to develop and deepen their knowledge at the level of expertise in the same or a different field, based on undergraduate level qualifications. | ||||||||||||
2) To be able to use the theoretical and applied knowledge at the level of expertise acquired in the field. | ||||||||||||
3) To be able to interpret and create new knowledge by integrating the knowledge gained in the field with the knowledge from different disciplines. | ||||||||||||
4) To be able to solve the problems encountered in the field by using research methods. | ||||||||||||
5) Being able to independently carry out a work that requires expertise in the field. | ||||||||||||
6) To be able to develop new strategic approaches for the solution of complex and unpredictable problems encountered in applications related to the field and to produce solutions by taking responsibility. | ||||||||||||
7) To be able to critically evaluate the knowledge and skills acquired in the field of expertise and to direct their learning. | ||||||||||||
8) To be able to systematically transfer current developments in the field and their own studies to groups in and outside the field, in written, verbal and visual forms, by supporting them with quantitative and qualitative data. | ||||||||||||
9) To be able to communicate orally and in writing using a foreign language at least at the B2 General Level of the European Language Portfolio. | ||||||||||||
10) To be able to use information and communication technologies at an advanced level along with computer software at the level required by the field. | ||||||||||||
11) To be able to supervise and teach these values by observing social, scientific, cultural and ethical values in the stages of collecting, interpreting, applying and announcing the data related to the field. | ||||||||||||
12) To be able to use the knowledge, problem solving and/or application skills they have internalized in their field in interdisciplinary studies. |
No Effect | 1 Lowest | 2 Average | 3 Highest |
Program Outcomes | Level of Contribution | |
1) | Being able to develop and deepen their knowledge at the level of expertise in the same or a different field, based on undergraduate level qualifications. | |
2) | To be able to use the theoretical and applied knowledge at the level of expertise acquired in the field. | |
3) | To be able to interpret and create new knowledge by integrating the knowledge gained in the field with the knowledge from different disciplines. | |
4) | To be able to solve the problems encountered in the field by using research methods. | |
5) | Being able to independently carry out a work that requires expertise in the field. | |
6) | To be able to develop new strategic approaches for the solution of complex and unpredictable problems encountered in applications related to the field and to produce solutions by taking responsibility. | |
7) | To be able to critically evaluate the knowledge and skills acquired in the field of expertise and to direct their learning. | |
8) | To be able to systematically transfer current developments in the field and their own studies to groups in and outside the field, in written, verbal and visual forms, by supporting them with quantitative and qualitative data. | |
9) | To be able to communicate orally and in writing using a foreign language at least at the B2 General Level of the European Language Portfolio. | |
10) | To be able to use information and communication technologies at an advanced level along with computer software at the level required by the field. | |
11) | To be able to supervise and teach these values by observing social, scientific, cultural and ethical values in the stages of collecting, interpreting, applying and announcing the data related to the field. | |
12) | To be able to use the knowledge, problem solving and/or application skills they have internalized in their field in interdisciplinary studies. |
Semester Requirements | Number of Activities | Level of Contribution |
Homework Assignments | 4 | % 10 |
Presentation | 3 | % 5 |
Project | 2 | % 15 |
Midterms | 2 | % 30 |
Final | 2 | % 40 |
total | % 100 | |
PERCENTAGE OF SEMESTER WORK | % 60 | |
PERCENTAGE OF FINAL WORK | % 40 | |
total | % 100 |
Activities | Number of Activities | Preparation for the Activity | Spent for the Activity Itself | Completing the Activity Requirements | Workload | ||
Study Hours Out of Class | 10 | 8 | 80 | ||||
Presentations / Seminar | 3 | 5 | 15 | ||||
Project | 2 | 10 | 20 | ||||
Homework Assignments | 4 | 4 | 16 | ||||
Midterms | 2 | 6 | 12 | ||||
Final | 2 | 6 | 12 | ||||
Total Workload | 155 |