Statistical Learning Theory
- Understanding basic concepts from statistical learning theory.
- Being able to understand the connection between these models and many machine learning algorithms.
- Training of mathematical skills such as abstract thinking, formal thinking and problem solving; with emphasis on statistics.
- Calculate sizes of trainingsets for several machinelearning tasks in the context of PAC-learning (and hence calculate VC-dimensions)
- Deeper understanding of boosting algorithms and support vector machines.
- Knowledge of several paradigms in statistical learning theory to select models (Structural risk minimization, Maximal likelihood, Minimal Description Length, etc.)
- Theoretical understanding of several online learning algorithms and learning with expert advice.
- Understand the link between cryptography and computational limitations of statistical learning.
- Probably approximately correct learning
- Structural risk minimization and variants
- The time complexity of learning and cryptography
- Rademacher complexities
- Support vector machines and margin theory
- Mutliclass classification and DeepBoost
- Online learning
- Reinforcement learning
- 2021/2022 1st module
- 2021/2022 2nd module0.3 * Colloqium + 0.35 * Exam + 0.35 * Homework
- Mohri, M., Talwalkar, A., & Rostamizadeh, A. (2012). Foundations of Machine Learning. Cambridge, MA: The MIT Press. Retrieved from http://search.ebscohost.com/login.aspx?direct=true&site=eds-live&db=edsebk&AN=478737
- Vitaly Kuznetsov, Mehryar Mohri, & Umar Syed. (n.d.). Multi-Class Deep Boosting.