Obligation |
: |
Elective |
Prerequisite courses |
: |
ELE320 |
Concurrent courses |
: |
- |
Delivery modes |
: |
Face-to-Face |
Learning and teaching strategies |
: |
Lecture, Question and Answer, Problem Solving, Programming |
Course objective |
: |
This course provides an introduction to the theory and applications of machine learning. The goal is to provide students with a deep understanding of the subject matter and skills to apply these concepts to real world problems using Python as the programming language. |
Learning outcomes |
: |
A student who completes the course successfully has both theoretical and practical knowledge on machine learning, and he/she can apply her knowledge to real-world problems. She knows about classification, regression, clustering, supervised and unsupervised techniques in handling data, and can select between several models depending on performance metrics. |
Course content |
: |
Introduction to Machine Learning, Machine Learning Tools and Libraries in the Python Programming Language, k-Nearest Neighbors, Naïve Bayes Classifier, Maximum Likelihood Estimation, Decision Trees, Support Vector Machines, Perceptron, Neural Networks, Deep Learning, Auto-encoding and Self-supervision, Generative Adversarial Networks, Classification Performance Metrics, Model Selection, Dimension Reduction, Clustering, Regression, Ensemble Methods. |
References |
: |
Ethem Alpaydin, Introduction to Machine Learning, The MIT Press, 2020 Christopher Bishop, Pattern Recognition and Machine Learning, Springer, 2006. Edward Raff, Inside Deep Learning, Manning, 2022 |
Course Outline Weekly
Weeks |
Topics |
1 |
Introduction to Machine Learning |
2 |
Introduction to Python Programming: Machine Learning Tools and Libraries |
3 |
Nearest Neighbor Classifier, Naïve Bayes Classifier, Maximum Likelihood |
4 |
Classification Performance Metrics, Model Selection |
5 |
Linear Regression |
6 |
Dimension Reduction |
7 |
Clustering |
8 |
Decision Trees |
9 |
Midterm |
10 |
Support Vector Machines |
11 |
Neural Networks |
12 |
Deep Learning, Auto-encoding, Generative Adversarial Networks |
13 |
Ensemble Methods: Bagging, Boosting |
14 |
Project Presentations |
15 |
Final exam preparation |
16 |
Final exam |
Matrix Of The Course Learning Outcomes Versus Program Outcomes
Key learning outcomes |
Contribution level |
1 |
2 |
3 |
4 |
5 |
1. |
Possesses the theoretical and practical knowledge required in Electrical and Electronics Engineering discipline. | | | | | |
2. |
Utilizes his/her theoretical and practical knowledge in the fields of mathematics, science and electrical and electronics engineering towards finding engineering solutions. | | | | | |
3. |
Determines and defines a problem in electrical and electronics engineering, then models and solves it by applying the appropriate analytical or numerical methods. | | | | | |
4. |
Designs a system under realistic constraints using modern methods and tools. | | | | | |
5. |
Designs and performs an experiment, analyzes and interprets the results. | | | | | |
6. |
Possesses the necessary qualifications to carry out interdisciplinary work either individually or as a team member. | | | | | |
7. |
Accesses information, performs literature search, uses databases and other knowledge sources, follows developments in science and technology. | | | | | |
8. |
Performs project planning and time management, plans his/her career development. | | | | | |
9. |
Possesses an advanced level of expertise in computer hardware and software, is proficient in using information and communication technologies. | | | | | |
10. |
Is competent in oral or written communication; has advanced command of English. | | | | | |
11. |
Has an awareness of his/her professional, ethical and social responsibilities. | | | | | |
12. |
Has an awareness of the universal impacts and social consequences of engineering solutions and applications; is well-informed about modern-day problems. | | | | | |
13. |
Is innovative and inquisitive; has a high level of professional self-esteem. | | | | | |