Machine Learning
azeytin@gsu.edu.tr
Content
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.
Course Content
Course content includes an introduction to machine learning, mathematical foundations, the deep relationship between optimization and machine learning, problems encountered in optimization and their solutions, training processes of different models, frequently encountered problems and their solutions, 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/
Weekly Contents
| Week | Weekly Contents |
|---|---|
| 1 | Overview of machine learning, types of learning, and applications. |
| 2 | Minimal reusable ML data pipeline and data leakage |
| 3 | Optimization foundations |
| 4 | Training = minimizing a loss |
| 5 | Gradient descent for univariate functions |
| 6 | Gradient descent for multivariate functions |
| 7 | Saddle point problem and higher order methods |
| 8 | Regularization |
| 9 | Model Toolbox I : Regression, forecasting and binary classification |
| 10 | Model Toolbox II : Multiclass classification, decision trees and random forests |
| 11 | Model Toolbox III : Gradient boosting with trees, XGBoost, LightGBM and Clustering / Segmentation |
Assessment System
| Activities | Number | Contribution |
|---|---|---|
| Contribution of in-term studies to overall grade | 1 | 50 |
| Contribution of final exam to overall grade | 1 | 50 |
| Total | 2 | 100 |
| Activities | Number | Contribution |
|---|---|---|
| Assignments | 0 | 0 |
| Presentation | 0 | 0 |
| Midterm Examinations (including preparation) | 1 | 50 |
| 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 |
| Make-up | 0 | 0 |
| Total | 1 | 50 |
ECTS
| 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 | ||