Teaching, Tutorials, Notes

An overview of ALL courses offered by MLR is given on our MLR pages. Here I list material for my own lectures only.

Full slide collections and scripts:


Courses & Tutorials

WS 16/17 - Maths for Intelligent Systems
(Previous versions: WS 15/16)
WS 16/17 - Artificial Intelligence Bachelor Course
(Previous versions: WS 14/15, WS 15/16)

Introduction to Machine Learning (SS 16)

The Machine Learning course first covers basic regression and classification methods (e.g. Bayesian Kernel Ridge Logistic Regression...) and then focusses on Bayesian formulations of learning (Bayes nets, probabilistic inference)

In Stuttgart I plan to iterate the course every summer.

Previous versions are:

SS 15 - Optimization
(Previous versions: SS 14, SS 13)
WS 14/15 - Artificial Intelligence Bachelor Course

Introduction to Robotics (WS 14/15)

The Robotics course covers the basics of motion generation (kinematics, dynamics, planning, control) as well as state estimation (in mobile robotics).

In Stuttgart I plan to iterate the course every winter.

Previous versions are:

WS 14/15 - Hauptseminar: Machine Learning
SS 14 - Hauptseminar: Robotics
Bandits, Global Optimization, Active Learning, and Bayesian RL -- understanding the common ground [old version]
A brief (90mins) tutorial held first at the Machine Learning Summer School, Tübingen, Sep 2013; and later at the Autonomous Learning Summer School, Leipzig, Sep 2014. The aim is to introduce to various problems from the perspective of belief planning and discuss what optimal policies would be. Pointers to more in-depth literature are provided. See a video here.
WS 13/14 - Hauptseminar: Machine Learning
WS 13/14 - Foundations of Autonomous Systems
SS 13 - Hauptseminar: Topics in Robotics
ICML 2011 Tutorial on Machine Learning & Robotics
Machine Learning tutorial at the Interdisciplinary College 2011
The 3 basic lectures target an interdiciplinary audience (students from Computer Sci, Cog Science, Neuroscience, Psychology), covering basics in ML, Bayesian Modelling, and RL:
  • 1. Introduction
  • 2. Linear Models (non-linear features, regularization, cross-validation, `linear/polynomial/kernel Ridge/Lasso regression/logistic classification')
  • 3. Bayesian Modelling (Bayes, examples, regularization & prior, error & likelihood, MAP view on Ridge/Lasso regression, EM, Bayes Nets)
  • 4. Reinforcement Learning (Markov Decision Process, values, temporal difference, model-free vs. model-based, planning by probabilistic inference)
BCCN lecture Computational models of goal-directed behavior
slides exercise.
RLSS 09 - Inference & Planning
Lectures given at the Robot Learning Summer School (Lisbon, July 20-24 2009).
Slides: part 1, part 2
Part 1: Introduction to probabilistic inference \& learning
-- probabilities, joint distributions, graphical models -- inference, message passing -- learning, Expectation Maximization
Part 2: Planning by Inference
-- general idea of inference by planning -- Markov Decision Processes revisited -- Stochastic Optimal Control revisited
Summary & further reading
-- brief summary -- further reading -- food for thought
ICML 08 tutorial - Stochastic Optimal Control
Tutorial, held together with Bert Kappen on Saturday July 5 2008 in Helsinki, Finland as part of the 25th International Conference on Machine Learning (ICML 2008). See the tutorial web page.


Interesting Readings


Reference Material

Linear algebra references