Lecture: Foundations of Machine Learning and Data Mining

Lab class homepage

Lecturers: Ralf Möller, Rainer Marrone

Lecture + lab class: Thursday 12.45 - 14.15, Location: ES42, Rm 2589

Prerequisites:

Elementary knowledge in Computer Science and Mathematics as usual for a Master course.

Content (will be updated without notification):

• Introduction
• Learning from observations
  Inductive learning, introduction to learning decision trees
• Decision tree learning
  Information theory, information gain (ID3), extensions (C4.5), translating decision trees to rules
• Computational learning theory (PAC learning), incremental learning (version spaces)
• Uncertainty
• Wumpus example
• Bayesian networks
• Statistical Learning Methods
  1. Maximum-likelihood parameter learning
  2. Learning Bayesian networks structures
• Knowledge in learning
• Non-parametric learning
• Reinforcement learning

Acknowledgments:

Literature:

• Introducion to Machine Learning Ethem Alpaydin, MIT Press, 2004
• Artificial Intelligence: A Modern Approach (Second Edition), Stuart Russel, Peter Norvig, Prentice Hall, 2003
  Chapters 13-14, 18-21.

Previous exams