Machine Learning (MAT407)
| Course Code | Course Name | Semester | Theory | Practice | Lab | Credit | ECTS |
|---|---|---|---|---|---|---|---|
| MAT407 | Machine Learning | 8 | 3 | 0 | 0 | 3 | 6 |
| Prerequisites | |
| Admission Requirements |
| Language of Instruction | French |
| Course Type | Elective |
| Course Level | Bachelor Degree |
| Course Instructor(s) | Gönenç ONAY gonay@gsu.edu.tr (Email) |
| Assistant | |
| Objective | The objective of this course is to provide students with a solid foundation in machine learning and deep learning. By covering both theoretical concepts and practical applications, students will learn to design, implement, and evaluate various machine learning models for solving real-world problems. |
| Content | The course content includes an introduction to machine learning, mathematical foundations, deep learning basics, training models, convolutional and recurrent neural networks, advanced models like GANs and autoencoders, natural language processing, and practical project work. |
| Course Learning Outcomes | Upon completion of the course, students will be able to understand the principles of machine learning and deep learning, apply various ML techniques to solve problems, implement models using Python and relevant libraries, and develop their own projects demonstrating their learning. |
| Teaching and Learning Methods | Python notebooks, slides, projects. |
| References |
https://udlbook.github.io/udlbook/ https://www.amazon.com/Hundred-Page-Machine-Learning-Book/dp/199957950X https://www.di.ens.fr/appstat/spring-2023/ |
Theory Topics
| Week | Weekly Contents |
|---|---|
| 1 | Overview of machine learning, types of learning, and applications. |
| 2 | Lineer and logistic regression. |
| 3 | Introduction to Python programming for ML, libraries (NumPy, Pandas). |
| 4 | Neural Networks Basics - Understanding neural networks, activation functions, and architecture. |
| 5 | Deep Learning Fundamentals - Introduction to deep learning, frameworks, and setting up the environment. |
| 6 | Training Deep Neural Networks - Techniques for training DNNs, avoiding overfitting, and regularization. |
| 7 | Convolutional Neural Networks (CNNs) - Basics of CNNs, applications in image recognition. |
| 8 | Midterm Exam - Assessment covering all previously seen topics |
| 9 | Recurrent Neural Networks (RNNs) - Introduction to RNNs, LSTM, and their applications. |
| 10 | Advanced Deep Learning Models - Exploring GANs, autoencoders, and reinforcement learning basics. |
| 11 | Deep Learning for Sequential Data - Time series analysis, RNNs for sequence data. |
| 12 | Natural Language Processing with Deep Learning - Techniques and models for NLP. |
| 13 | Project Discussions - Students present their projects, discussion, and feedback. |
| 14 | Project Presentations - Final presentation of projects, course wrap-up, and future directions. |
Practice Topics
| Week | Weekly Contents |
|---|
Contribution to Overall Grade
| Number | Contribution | |
|---|---|---|
| Contribution of in-term studies to overall grade | 2 | 60 |
| Contribution of final exam to overall grade | 1 | 40 |
| Toplam | 3 | 100 |
In-Term Studies
| Number | Contribution | |
|---|---|---|
| Assignments | 0 | 0 |
| Presentation | 1 | 30 |
| Midterm Examinations (including preparation) | 1 | 30 |
| Project | 0 | 0 |
| Laboratory | 0 | 0 |
| Other Applications | 0 | 0 |
| Quiz | 0 | 0 |
| Term Paper/ Project | 0 | 0 |
| Portfolio Study | 0 | 0 |
| Reports | 0 | 0 |
| Learning Diary | 0 | 0 |
| Thesis/ Project | 0 | 0 |
| Seminar | 0 | 0 |
| Other | 0 | 0 |
| Toplam | 2 | 60 |
| No | Program Learning Outcomes | Contribution | ||||
|---|---|---|---|---|---|---|
| 1 | 2 | 3 | 4 | 5 | ||
| 1 | understands principles of deductive reasoning; has experience to verify well-foundedness and exactness of mathematical statements in systematic ways; | X | ||||
| 2 | can properly state and use concepts and results of major mathematical interest; | X | ||||
| 3 | masters current computational techniques and algorithms; has a good ability in their use; can identify relevant tools, among those one has learned, suitable to solve a problem and is able to judge whether or not one is in possession of these tools; | X | ||||
| 4 | is able to express one’s mathematical ideas in an organised way both in written and oral forms; | X | ||||
| 5 | understands relations connecting substantial concepts and results; can switch from one viewpoint to another on mathematical objects (pictures, formulae, precise statements, heuristic trials, list of examples,...); | X | ||||
| 6 | has followed individually a guided learning strategy; has pursued steps toward the resolution of unfamiliar problems; | X | ||||
| 7 | has a theoretical and practical knowledge in computer science well adapted for learning a programming language; | X | ||||
| 8 | has investigated the relevance of modeling and using mathematical tools in natural sciences and in the professional life; is conscious about historical development of mathematical notions; | X | ||||
| 9 | has followed introduction to some mathematical or non-mathematical disciplines after one’s proper choice; had experience to learn selected subjects according to one’s proper arrangement; | X | ||||
| 10 | masters French language as well as other foreign languages, to a level sufficient to study or work abroad. | X | ||||
| Activities | Number | Period | Total Workload |
|---|---|---|---|
| Class Hours | 14 | 42 | 588 |
| Working Hours out of Class | 0 | 0 | 0 |
| Assignments | 0 | 0 | 0 |
| Presentation | 0 | 0 | 0 |
| Midterm Examinations (including preparation) | 1 | 3 | 3 |
| Project | 1 | 10 | 10 |
| Laboratory | 0 | 0 | 0 |
| Other Applications | 0 | 0 | 0 |
| Final Examinations (including preparation) | 0 | 0 | 0 |
| Quiz | 0 | 0 | 0 |
| Term Paper/ Project | 0 | 0 | 0 |
| Portfolio Study | 0 | 0 | 0 |
| Reports | 0 | 0 | 0 |
| Learning Diary | 0 | 0 | 0 |
| Thesis/ Project | 0 | 0 | 0 |
| Seminar | 0 | 0 | 0 |
| Other | 0 | 0 | 0 |
| Total Workload | 601 | ||
| Total Workload / 25 | 24,04 | ||
| Credits ECTS | 24 | ||