CS-E4715 - Supervised Machine Learning (Autumn 2026)

• Co-teach with Jaakko Hollmen
• Part I: Theory
  • Introduction
  • Generalization error analysis & PAC learning
  • Rademacher Complexity & VC dimension
  • Model selection
• Part II: Algorithms and models
  • Linear models: perceptron, logistic regression
  • Support vector machines
  • Kernel methods
  • Neural networks (MLPs)
  • Ensemble methods
• Part III: Additional topics
  • Feature learning, selection and sparsity
  • Multi-class classification
  • Preference learning, ranking

CS-E4825 - Probabilistic Machine Learning (Spring 2027)

• Co-teach with Francesco Croce
• Lecture 1: Introduction
• Lecture 2: Bayesian networks
• Lecture 3: MV Gaussian, Bayesian linear models
• Lecture 4: ML-II, Laplace approximation, Gaussian mixtures
• Lecture 5: Expectation maximization
• Lecture 6: Variational inference
• Lecture 7: Model selection
• Lecture 8: Factor analysis
• Lecture 9: Bayes by backprop