Machine Learning 1 (Winter Term 2025/2026)

Overview

• Course consisting of:
  • Lectures (2 hours/week) in TRE/PHYS/E (Zellescher Weg 16) on Fridays, 09:20–10:50
  • Exercise group sessions (2 hours/week)
    • BAR/0218/U, Tuesdays, 16:40–18:10
    • APB/E001/U, Thursdays, 16:40–18:10
    • APB/E001/U, Fridays, 14:50–16:20
    • APB/E001/U, Fridays, 16:40–18:10
    • Online, Thursdays, 16:40–18:10
  • Self-study
  • Final examination
• Enrolment (OPAL). Additional rules for enrolment may apply, depending on the study program.

Contents

• Introduction
• Supervised learning
  • Introduction
  • Learning of binary decision trees
    • Hardness
    • Local search algorithm
  • Learning of linear functions
    • Logistic regression
    • Convexity
    • Gradient descent algorithm
  • Learning of composite functions (deep learning)
    • Compute graphs
    • Non-convexity
    • Forward-propagation algorithm and backward-propagation algorithm
    • Attention
    • Transformers
• Semi-supervised and unsupervised learning
  • Introduction
  • Partitioning (clustering)
    • Clique partition problem
    • Hardness
    • Local search algorithms
  • Ordering
    • Linear ordering problem
    • Hardness
    • Local search algorithms
  • Classifying
    • Multi-label classification problem
• Supervised structured learning
  • Introduction
  • Conditional graphical models
  • Message passing algorithms
  • Pseudo-Boolean optimization