Course 2025-2026 a.y.

1. An introduction to statistical machine learning. Supervised learning; prediction accuracy vs model interpretability; assessment of model accuracy; methods for evaluating predictive uncertainty.

2. Review of regression and classification.

3. Bias-variance trade-off and shrinkage methods.

4. Resampling methods: cross-validation and bootstrap.

5. Nonlinear models: polynomial regression, regression and smoothing splines, generalized additive models.

6. Tree-based methods and their applications in survival analysis: regression and classification trees; bagging; random forests; support vector machines; kernel methods; boosting.

7. Large-scale hypothesis testing: FWER, Bonferroni, FDR, Benjamini-Hochberg, resampling-based methods.

8. Learning with directed and undirected graphical models. Identification of conditional independencies. Exact and approximate inference methods.

• Design and perform data-driven analyses for interpretation, prediction, and classification, addressing various aspects and subtleties of model selection.
• Understand and apply the bias-variance trade-off and shrinkage methods.
• Implement resampling methods for reliable model assessment.
• Identify and use tree-based and kernel-based algorithms.
• Explain principles of large-scale hypothesis testing and control of error rates.

• Formalize real-world problems as precise statistical questions.

• Make informed judgments by selecting appropriate machine learning tools.

• Assess statistical significance and uncertainty of analysis results

Lifelong Learning Skills

By the end of the course, students will be able to:

● Balance the trade-off between model complexity and performance in learning algorithms.

● Develop algorithms to address relevant and evolving learning problems.

● Adapt their analytical skills to ongoing data challenges and emerging technologies in health and biomedical sciences.

• Lectures

The course will be delivered primarily through face-to-face lectures on campus, combining theoretical explanations with practical examples and interactive discussions.

All Students: The assessment consists of a single final exam composed of two parts:

● A theoretical part to test understanding of foundational concepts.

● An applied part to evaluate practical problem-solving and implementation skills.

This structure ensures alignment with both knowledge and application-oriented learning outcomes.

The following books and resources will be used as primary and supplementary references:

● James, G., Witten, D., Hastie, T., Tibshirani, R. (2023). An Introduction to Statistical Learning (Python edition). Springer. (freely available in PDF format at https://www.statlearning.com/)

● Hastie, T., Tibshirani, R., Friedman, J. (2009). The Elements of Statistical Learning. Springer. (freely available in PDF format at https://hastie.su.domains/ElemStatLearn/)

● Murphy, K. (2022). Probabilistic Machine Learning: An Introduction. MIT Press. (freely available in PDF format at https://probml.github.io/pml-book/book1.html)

● Højsgaard, S., Edwards, D., & Lauritzen, S. (2012). Graphical models with R. Springer Science & Business Media.