Магистратура
2026/2027
Машинное обучение
Статус:
Курс по выбору (Аналитика данных и прикладная статистика / Data Analytics and Social Statistics)
Где читается:
Факультет социальных наук
Когда читается:
1-й курс, 3 модуль
Онлайн-часы:
40
Охват аудитории:
для своего кампуса
Язык:
английский
Кредиты:
3
Контактные часы:
24
Course Syllabus
Abstract
This course provides a comprehensive introduction to the development and application of modern machine learning methods, covering the complete lifecycle of a machine learning solution from problem formulation and data preparation to model deployment and monitoring. The course addresses supervised and unsupervised learning, including classification, regression, clustering, anomaly detection, ensemble methods, and dimensionality reduction. Particular attention is given to data preprocessing and feature engineering, model evaluation and validation, hyperparameter optimization, and the prevention of overfitting and data leakage. The course also introduces contemporary practices for developing reliable and interpretable machine learning systems, including model explainability, bias and fairness assessment, experiment tracking, reproducibility, testing, and version and configuration management. The theoretical and methodological foundations are complemented by practical implementation in Python using widely adopted machine learning libraries and tools, enabling students to design, evaluate, interpret, and maintain end-to-end machine learning solutions.
Learning Objectives
- To provide students with a theoretical understanding of the fundamental principles of machine learning, including supervised and unsupervised learning paradigms, model generalization, overfitting, validation, and the principles underlying major machine learning algorithms.
- To develop a systematic methodological approach to solving machine learning problems, including problem formulation, data preprocessing and feature engineering, algorithm and metric selection, model evaluation, hyperparameter optimization, interpretation, and assessment of model reliability.
- To develop practical skills in designing and implementing end-to-end machine learning solutions, using Python and contemporary machine learning tools to build, compare, optimize, and interpret models for classification, regression, clustering, and other data-driven tasks.
- To provide students with the knowledge and practical foundations required to develop reproducible and production-oriented machine learning systems, including experiment tracking, testing, version and configuration management, model deployment principles, and monitoring of data quality, drift, and model performance.
Expected Learning Outcomes
- Be able to apply the basic concepts from machine learning theory
- Be able to identify appropriately the type of a machine learning problem at hand, e.g. classification, regression, clustering
- Be able to differentiate between supervised and unsupervised learning methods, understand their benefits and limitations
- Be able to master theoretical understanding of key methods for supervised learning to apply decision trees, linear regression, logistic regression, quantile regression, variations of regression for non-Gaussian distributions of the target variable
- Be able to differentiate and correctly apply most common approaches to ensemble learning (random forests, gradient boosting, stacking, blending, etc.) as well as to explain their benefits and limitations
- Be able to identify and tackle issues related to overfitting and model instability
- Be able to apply basic tools and approaches to automated text processing as well as to incorporate text data into machine learning solutions
- Be able to systematize and prioritize best practices in experiment tracking and sustainable ML development
- Be able to identify and formulate machine learning problems, including classification, regression, clustering, and anomaly detection tasks.
- Be able to differentiate between supervised and unsupervised learning methods and select appropriate algorithms based on the characteristics of the problem and available data.
- Be able to preprocess data and perform feature engineering, including handling missing values, encoding categorical variables, feature scaling, feature selection, and prevention of data leakage.
- Be able to design, train, evaluate, and optimize machine learning models using appropriate validation strategies and hyperparameter optimization techniques.
- Be able to select and correctly interpret evaluation metrics for classification and regression problems, including ROC analysis, Precision-Recall analysis, and methods for handling imbalanced datasets.
- Be able to differentiate and correctly apply ensemble learning methods, including bagging, Random Forests, Gradient Boosting (XGBoost, CatBoost, LightGBM), stacking, and blending, while understanding their advantages and limitations.
- Be able to apply unsupervised learning techniques, including clustering, dimensionality reduction, and anomaly detection, and evaluate the quality of the obtained results.
- Be able to interpret machine learning models using both model-specific and model-agnostic explainability techniques, including feature importance, SHAP, LIME, Partial Dependence Plots, and Individual Conditional Expectation.
- Be able to identify potential sources of bias and fairness issues in machine learning models and understand the ethical considerations associated with their deployment.
- Be able to implement reproducible machine learning workflows using experiment tracking, version control, configuration management, testing, and documentation best practices.
- Be able to understand the principles of deploying machine learning models into production environments and apply fundamental approaches to monitoring model performance, data quality, concept drift, and automated model maintenance.
- Be able to develop complete machine learning solutions in Python using widely adopted libraries and tools following modern software engineering and machine learning best practices.
Course Contents
- Section 1: Introduction to Machine Learning
- Section 2: Model Evaluation and Hyperparameter Optimization
- Section 3: Ensemble Learning
- Section 4: Unsupervised Learning
- Section 5: Feature Engineering and Data Quality
- Section 6: Model Explainability and Responsible AI
- Section 7: Reproducible Machine Learning
- Section 8: Productionizing ML Systems – Monitoring and Maintenance
Interim Assessment
- 2026/2027 3rd module0.5 * Final project + 0.3 * Graded quizzes + 0.2 * Mid-term homework
Bibliography
Recommended Core Bibliography
- Alpaydin, E. (2014). Introduction to Machine Learning (Vol. Third edition). Cambridge, MA: The MIT Press. Retrieved from http://search.ebscohost.com/login.aspx?direct=true&site=eds-live&db=edsebk&AN=836612
- Kulkarni, S., Harman, G., & Wiley InterScience (Online service). (2011). An Elementary Introduction to Statistical Learning Theory. Hoboken, N.J.: Wiley. Retrieved from http://search.ebscohost.com/login.aspx?direct=true&site=eds-live&db=edsebk&AN=391376
- Mehryar Mohri, Afshin Rostamizadeh, & Ameet Talwalkar. (2018). Foundations of Machine Learning, Second Edition. The MIT Press.
- Miroslav Kubat. (2017). An Introduction to Machine Learning (Vol. 2nd ed. 2017). Springer.
Recommended Additional Bibliography
- Haroon, D. (2017). Python Machine Learning Case Studies : Five Case Studies for the Data Scientist. [Berkeley, CA]: Apress. Retrieved from http://search.ebscohost.com/login.aspx?direct=true&site=eds-live&db=edsebk&AN=1623520
- Mohammed, Mohssen Khan, Muhammad Badruddin Bashier, Eihab Bashier Mohammed. Machine Learning: Algorithms and Applications. Auerbach Publications © 2017 // https://library.books24x7.com/toc.aspx?bookid=117434
- Sarkar, D., Bali, R., & Sharma, T. (2018). Practical Machine Learning with Python : A Problem-Solver’s Guide to Building Real-World Intelligent Systems. [United States]: Apress. Retrieved from http://search.ebscohost.com/login.aspx?direct=true&site=eds-live&db=edsebk&AN=1667293