Course Unit Code | Course Unit Title | Type of Course Unit | Year of Study | Semester | Number of ECTS Credits | 190105000107 | FUNDAMENTALS OF MACHINE LEARNING | Elective | 4 | 7 | 6 |
|
Level of Course Unit |
First Cycle |
Objectives of the Course |
Introduce students to core machine learning concepts and techniques; cover supervised and unsupervised learning methods along with model evaluation, optimization, and regularization; and develop practical implementation skills through laboratory and coding assignments. |
Name of Lecturer(s) |
Dr. Öğr. Üyesi Fesih KESKİN |
Learning Outcomes |
1 | Supervised Learning Techniques: Formulate and implement linear/logistic regression and decision tree algorithms for real-world problems. | 2 | Model Evaluation & Regularization: Analyze and optimize model performance using cross-validation, metrics, and regularization methods. | 3 | Unsupervised Learning & Dimensionality Reduction: Apply clustering algorithms (K-Means, hierarchical) and PCA to extract insights from unlabeled data. |
|
Mode of Delivery |
Daytime Class |
Prerequisites and co-requisities |
Basic Linear Algebra
Probability & Statistics |
Recommended Optional Programme Components |
Weekly coding-focused labs and short homework assignments to reinforce theory |
Course Contents |
Introduction to machine learning and development environments; fundamental statistics and probability concepts; linear regression and least squares; logistic regression and classification problems; loss functions and optimization (gradient descent); model evaluation, cross-validation, and performance metrics; overfitting and regularization techniques; decision trees and random forests; ensemble methods (bagging, boosting); support vector machines; unsupervised learning: clustering algorithms (K-Means, hierarchical clustering); dimensionality reduction (PCA); introduction to neural networks and the backpropagation algorithm; advanced topics: overview of deep learning and example applications. |
Weekly Detailed Course Contents |
|
1 | Introduction: What is ML? Setup of Python/Scikit-Learn environment | | | 2 | Fundamental statistics & probability; data preprocessing (scaling, missing values) (lab) | | | 3 | Linear regression and least squares method (lab) | | | 4 | Logistic regression and binary classification (lab) | | | 5 | Loss functions & optimization: gradient descent and learning-rate selection (lab) | | | 6 | Model evaluation: train/test split, cross-validation, R², accuracy, ROC-AUC (lab) | | | 7 | Overfitting vs. underfitting; regularization techniques (L1, L2, dropout) (lab) | | | 8 | Midterm Exam | | | 9 | Decision trees & random forests: structure, hyperparameters, feature importance (lab) | | | 10 | Ensemble methods: bagging and boosting (AdaBoost, Gradient Boosting) (lab) | | | 11 | Support Vector Machines: kernel methods and parameter tuning (lab) | | | 12 | Unsupervised learning: K-Means and hierarchical clustering (lab) | | | 13 | Dimensionality reduction: Principal Component Analysis (PCA) (lab) | | | 14 | Introduction to neural networks: perceptrons, MLPs, and backpropagation (lab) | | | 15 | Final Exam | | | 16 | Final Exam | | |
|
Recommended or Required Reading |
Aurélien Géron, Hands-On Machine Learning with Scikit-Learn, Keras & TensorFlow
Christopher M. Bishop, Pattern Recognition and Machine Learning
Hastie, Tibshirani & Friedman, The Elements of Statistical Learning
Lecture notes, example code, and Kaggle datasets (provided by the instructor) |
Planned Learning Activities and Teaching Methods |
|
Assessment Methods and Criteria | |
Midterm Examination | 1 | 100 | SUM | 100 | |
Final Examination | 1 | 100 | SUM | 100 | Term (or Year) Learning Activities | 40 | End Of Term (or Year) Learning Activities | 60 | SUM | 100 |
| Language of Instruction | Turkish | Work Placement(s) | No mandatory internship. |
|
Workload Calculation |
|
Midterm Examination | 1 | 1 | 1 |
Final Examination | 1 | 1 | 1 |
Attending Lectures | 14 | 1 | 14 |
Practice | 5 | 3 | 15 |
Self Study | 16 | 5 | 80 |
Individual Study for Mid term Examination | 8 | 2 | 16 |
Individual Study for Final Examination | 8 | 4 | 32 |
Homework | 5 | 2 | 10 |
|
Contribution of Learning Outcomes to Programme Outcomes |
LO1 | 5 | 5 | 5 | 4 | 4 | 5 | 4 | 4 | 4 | 4 | 4 | 5 | 4 | LO2 | 5 | 4 | 4 | 5 | 4 | 5 | 5 | 5 | 4 | 5 | 5 | 5 | 5 | LO3 | 4 | 4 | 5 | 5 | 4 | 5 | 5 | 4 | 4 | 4 | 4 | 4 | 5 |
|
* Contribution Level : 1 Very low 2 Low 3 Medium 4 High 5 Very High |
|
|
Iğdır University, Iğdır / TURKEY • Tel (pbx): +90 476
226 13 14 • e-mail: info@igdir.edu.tr
|