TÜRKÇE
ENGLISH
Information
| Unit | FACULTY OF ENGINEERING |
| ELECTRICAL-ELECTRONIC ENGINEERING PR. (ENGLISH) | |
| Code | EEES420 |
| Name | Machine Learning Fundamentals |
| Term | 2026-2027 Academic Year |
| Semester | 8. Semester |
| Duration (T+A) | 3-0 (T-A) (17 Week) |
| ECTS | 4 ECTS |
| National Credit | 3 National Credit |
| Teaching Language | İngilizce |
| Level | Belirsiz |
| Type | Normal |
| Label | E Elective |
| Mode of study | Yüz Yüze Öğretim |
| Catalog Information Coordinator | Doç. Dr. FATİH KILIÇ |
| Course Instructor |
The current term course schedule has not been prepared yet.
|
Course Goal / Objective
The aim of this course is to introduce students to the fundamental concepts, methods, and algorithms of machine learning, both theoretically and practically. The course aims to equip students with knowledge and skills in supervised and unsupervised learning, regression, classification, clustering, dimensionality reduction, model evaluation, and artificial neural networks; and to enable them to develop machine learning–based solutions for real-world problems using the Python programming language and its related libraries (NumPy, Pandas, Scikit-learn, TensorFlow/Keras).
Course Content
This course covers the fundamental concepts, historical evolution of machine learning, and its relationship with artificial intelligence; types of learning including supervised, unsupervised, semi-supervised, and reinforcement learning; data preprocessing, exploratory data analysis, feature engineering, and data visualization techniques; linear and logistic regression, k-nearest neighbors (k-NN), Naive Bayes, decision trees, random forests, and ensemble learning methods (boosting, bagging, XGBoost); support vector machines (SVM) and kernel functions; clustering algorithms such as k-means, hierarchical clustering, and DBSCAN; dimensionality reduction techniques including principal component analysis (PCA) and t-SNE; the fundamental structure of artificial neural networks, forward/back propagation algorithms, and activation functions; an introduction to CNN- and RNN-based deep learning models along with transfer learning; and model evaluation metrics, hyperparameter optimization, cross-validation, and the bias-variance trade-off; within the term project, students develop an end-to-end machine learning project on real datasets using Python and its related libraries (NumPy, Pandas, Scikit-learn, TensorFlow/Keras).
Course Precondition
There is no prerequisite for the course.
Resources
Géron, A. (2022). Hands-On Machine Learning with Scikit-Learn, Keras, and TensorFlow (3rd ed.). O'Reilly Media. Alpaydın, E. (2020). Introduction to Machine Learning (4th ed.). MIT Press.
Notes
Bishop, C. M. (2006). Pattern Recognition and Machine Learning. Springer. James, G., Witten, D., Hastie, T., & Tibshirani, R. (2021). An Introduction to Statistical Learning with Applications in Python. Springer. Çevrimiçi belgeler: Scikit-learn, TensorFlow ve Keras resmi dokümantasyonu; Kaggle ve Coursera platform kaynakları.
Course Learning Outcomes
| Order | Course Learning Outcomes |
|---|---|
| LO01 | Explain the fundamental concepts, types, and application areas of machine learning. |
| LO02 | Apply data preprocessing, feature engineering, and data visualization techniques. |
| LO03 | Select and apply supervised learning algorithms (linear/logistic regression, decision trees, SVM, k-NN). |
| LO04 | Perform data analysis using unsupervised learning algorithms (k-means, hierarchical clustering, PCA). |
| LO05 | Explain the basic structure and working principles of artificial neural networks; develop simple deep learning models. |
| LO06 | Evaluate model performance using appropriate metrics (accuracy, precision, recall, F1, ROC-AUC). |
| LO07 | Analyze overfitting, underfitting, and the bias-variance trade-off. |
| LO08 | Develop end-to-end projects on real datasets using Python and machine learning libraries. |
Relation with Program Learning Outcome
| Order | Type | Program Learning Outcomes | Level |
|---|---|---|---|
| PLO01 | Bilgi - Kuramsal, Olgusal | Adequate knowledge in mathematics, science and engineering subjects pertaining to the relevant discipline; ability to use theoretical and applied knowledge in these areas in complex engineering problems. | 5 |
| PLO02 | Bilgi - Kuramsal, Olgusal | Ability to identify, formulate, and solve complex engineering problems; ability to select and apply proper analysis and modeling methods for this purpose. | 4 |
| PLO03 | Bilgi - Kuramsal, Olgusal | Ability to design a complex system, process, device or product under realistic constraints and conditions, in such a way as to meet the desired result; ability to apply modern design methods for this purpose. | 4 |
| PLO04 | Bilgi - Kuramsal, Olgusal | Ability to devise, select, and use modern techniques and tools needed for analyzing and solving complex problems encountered in engineering practice; ability to employ computer programming techniques, and information technologies effectively. | 4 |
| PLO05 | Bilgi - Kuramsal, Olgusal | Ability to design and conduct experiments, gather data, analyze and interpret results for investigating complex engineering problems or discipline specific research questions. | 4 |
| PLO06 | Bilgi - Kuramsal, Olgusal | Ability to work efficiently in intra-disciplinary and multi-disciplinary teams; ability to work individually. | |
| PLO07 | Bilgi - Kuramsal, Olgusal | Ability to communicate effectively, both orally and in writing; knowledge of a minimum of one foreign language; ability to write effective reports and comprehend written reports, prepare design and production reports, make effective presentations, | |
| PLO08 | Bilgi - Kuramsal, Olgusal | Recognition of the need for lifelong learning; ability to access information, to follow developments in science and technology, and to continue to educate him/herself. | |
| PLO09 | Bilgi - Kuramsal, Olgusal | Consciousness to behave according to ethical principles and professional and ethical responsibility; knowledge on standards used in engineering practice. | 2 |
| PLO10 | Bilgi - Kuramsal, Olgusal | Knowledge about business life practices such as project management, risk management, and change management; awareness in entrepreneurship, innovation; knowledge about sustainable development. | 3 |
| PLO11 | Bilgi - Kuramsal, Olgusal | Knowledge about the global and social effects of engineering practices on health, environment, and safety, and contemporary issues of the century reflected into the field of engineering; awareness of the legal consequences of engineering solutions. | |
| PLO12 | Bilgi - Kuramsal, Olgusal | Ability to apply the knowledge of electrical-electronics engineering to profession-specific tools and devices. | 4 |
| PLO13 | Bilgi - Kuramsal, Olgusal | Having consciousness about the scientific, social, historical, economical and political facts of the society, world and age lived in. |
Week Plan
| Week | Topic | Preparation | Methods |
|---|---|---|---|
| 1 | Introduction to machine learning: definition, historical evolution, relationship with artificial intelligence, and application areas | Reviewing the course syllabus; researching the difference between "machine learning" and "artificial intelligence"; reviewing daily-life machine learning applications (recommendation systems, face recognition, spam filters). | Öğretim Yöntemleri: Anlatım, Soru-Cevap, Tartışma |
| 2 | Types of machine learning (supervised, unsupervised, semi-supervised, reinforcement); Python and development environment setup (Anaconda, Jupyter, Google Colab) | Reviewing basic Python syntax (variables, loops, functions); installing the Anaconda distribution on a personal computer; exploring Jupyter Notebook and Google Colab platforms. | Öğretim Yöntemleri: Anlatım, Soru-Cevap, Tartışma |
| 3 | Data preprocessing: missing data, outliers, normalization, standardization, categorical data encoding; data manipulation with NumPy and Pandas | Reviewing basic statistical concepts (mean, median, standard deviation); preliminary reading on the basic functions of NumPy and Pandas libraries; examining a sample CSV dataset. | Öğretim Yöntemleri: Anlatım, Soru-Cevap, Tartışma |
| 4 | Exploratory data analysis (EDA) and data visualization (Matplotlib, Seaborn); feature engineering and feature selection | Researching basic plot types (histogram, scatter, boxplot) of Matplotlib and Seaborn libraries; reviewing concepts of correlation and distribution. | Öğretim Yöntemleri: Anlatım, Soru-Cevap, Tartışma |
| 5 | Linear regression: simple/multiple linear regression, least squares method, gradient descent | Reviewing fundamentals of linear algebra (vector, matrix, matrix multiplication); refreshing derivative and partial derivative topics; preliminary reading on the least squares method. | Öğretim Yöntemleri: Anlatım, Soru-Cevap, Tartışma |
| 6 | Logistic regression and classification fundamentals; sigmoid function, cost function, binary and multiclass classification | Reviewing concepts of probability and conditional probability; refreshing exponential and logarithmic functions; preliminary research on the sigmoid function. | Öğretim Yöntemleri: Anlatım, Soru-Cevap, Tartışma |
| 7 | k-Nearest Neighbors (k-NN) and Naive Bayes classifiers; distance metrics and probabilistic approaches | Examining the mathematical definitions of Euclidean and Manhattan distances; reviewing Bayes' theorem; reflecting on sample classification problems. | Öğretim Yöntemleri: Anlatım, Soru-Cevap, Tartışma |
| 8 | Mid-Term Exam | Comprehensive review of all topics covered in the first seven weeks; reviewing lecture notes, assignments, and laboratory applications; practicing with sample exam questions. | Ölçme Yöntemleri: Yazılı Sınav |
| 9 | Decision trees, random forests, and ensemble learning methods (boosting, bagging, XGBoost) | Preliminary research on the concepts of entropy and information gain; reviewing the basic logic of "tree" data structures; reading on the philosophy of ensemble learning. | Öğretim Yöntemleri: Anlatım, Soru-Cevap, Tartışma |
| 10 | Support vector machines (SVM); linear and nonlinear kernel functions | Reviewing linear algebra and the concept of hyperplane; researching the basic logic of optimization problems; introductory reading on kernel functions. | Öğretim Yöntemleri: Anlatım, Soru-Cevap, Tartışma |
| 11 | Unsupervised learning: k-means, hierarchical clustering, DBSCAN; clustering evaluation metrics | Reviewing distance and similarity metrics; researching the concept of "unlabeled data"; examining sample customer segmentation applications. | Öğretim Yöntemleri: Anlatım, Soru-Cevap, Tartışma |
| 12 | Dimensionality reduction: principal component analysis (PCA), t-SNE; feature extraction techniques | Reviewing eigenvalue and eigenvector concepts in linear algebra; refreshing the concept of variance; researching the high-dimensional data problem ("curse of dimensionality"). | Öğretim Yöntemleri: Anlatım, Soru-Cevap, Tartışma |
| 13 | Introduction to artificial neural networks: perceptron, multilayer networks, forward/back propagation, activation functions | Reading on the analogy between biological neurons and artificial neurons; reviewing linear algebra and derivatives; preliminary research on activation functions (ReLU, sigmoid, tanh). | Öğretim Yöntemleri: Anlatım, Soru-Cevap, Tartışma |
| 14 | Introduction to deep learning: fundamentals of CNN and RNN; implementation with TensorFlow/Keras; transfer learning concept | Reviewing fundamentals of image processing (pixel, channel, filter); exploring the websites of TensorFlow and Keras libraries; preliminary reading on pre-trained models. | Öğretim Yöntemleri: Anlatım, Soru-Cevap, Tartışma |
| 15 | Model evaluation, hyperparameter optimization, cross-validation; student project presentations | Completing the term project; reviewing the confusion matrix and performance metrics; preparing the presentation file and demo video. | Öğretim Yöntemleri: Anlatım, Soru-Cevap, Tartışma |
| 16 | Term Exams | Comprehensive review of all topics covered throughout the semester; special focus on topics covered after the midterm; practicing with solved sample questions. | Ölçme Yöntemleri: Yazılı Sınav |
| 17 | Term Exams | Comprehensive review of all topics covered throughout the semester; special focus on topics covered after the midterm; practicing with solved sample questions. | Ölçme Yöntemleri: Yazılı Sınav |
Student Workload - ECTS
| Works | Number | Time (Hour) | Workload (Hour) |
|---|---|---|---|
| Course Related Works | |||
| Class Time (Exam weeks are excluded) | 14 | 3 | 42 |
| Out of Class Study (Preliminary Work, Practice) | 14 | 2 | 28 |
| Assesment Related Works | |||
| Homeworks, Projects, Others | 1 | 20 | 20 |
| Mid-term Exams (Written, Oral, etc.) | 1 | 2 | 2 |
| Final Exam | 1 | 2 | 2 |
| Total Workload (Hour) | 94 | ||
| Total Workload / 25 (h) | 3,76 | ||
| ECTS | 4 ECTS | ||