Teaching
Please see the lab’s teaching page for this term’s offered courses at TUB.
Most of my material (LaTeX sources of slides and exercises) is now accessible on github. (See the tmp branch for yet non-polished sets of slides.)
Here you find full slide collections and scripts for my courses, and at the bottom of this page:
Full slide collections and scripts
Courses
- WS 20/21 - Optimization Algorithms
- (Previous versions: SS 14, SS 13)
- SS 20 - AI & Robotics: Research
- See general information here.
- SS 20 - AI & Robotics: Lab Course
- See general information here.
- WS 19/20 - Maths for Intelligent Systems
- (Previous versions:
WS 18/19,
WS 16/17,
WS 15/16)
- WS 19/20 - Artificial Intelligence Bachelor Course
- (Previous versions:
WS 18/19,
WS 16/17,
WS 15/16,
WS 14/15)
- Introduction to Machine Learning (SS 19)
- 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:
U Stuttgart: SS 16, SS 15, SS 14, SS 13
FU Berlin: SS 12, SS 11
TU Berlin: SS 09 (Introduction to Graphical Models)
- 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:
U Stuttgart: WS 13/14
FU Berlin: WS 12/13, WS 11/12, WS 10/11
WS 14/15 - Hauptseminar: Machine Learning
SS 14 - Hauptseminar: Robotics
WS 13/14 - Hauptseminar: Machine Learning
WS 13/14 - Foundations of Autonomous Systems
SS 13 - Hauptseminar: Topics in Robotics
Tutorials
- Brief Intro to Gaussian Processes
- SimTech ML Seminar, Feb 5 2020.
- 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.
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
- 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
- Pedro Domingos: A few useful things to know about machine learning. Communications of the ACM, 2012.
- Anil Ananthaswamy: I,
algorithm: A new dawn for artificial intelligence. A popular
science article in NewScientist, 2011. (another link)
- Pat Langley: The
changing science of machine learning. Editorial in Machine
Learning 82, 275-279, 2011.
- Thomas G. Dietterich et al.: Structured machine learning: the next ten years.
Machine Learning, 73, 3-23, 2008.
- Yoshua Bengio & Yann LeCun: Scaling
learning algorithms towards AI. Large-Scale Kernel Machines, 34,
2007.
- Rodney Douglas, Terry Sejnowski & others: Future
Challenges for the Science and Engineering of Learning. Report of
an NSF workshop, 2007.
- Tom Mitchell: The Discipline of
Machine Learning. Report CMU-ML-06-108, Carnegie Mellon
University, 2006.
- Leo Breiman: Statistical modeling: The two cultures. Statistical Science, 2001.
Reference Material
Linear algebra references
Probabilities & Machine Learning
Optimization
Recent Posts
pdf
Probabilities & Energy.
Die gängigen Erklärungen zu “Was ist Informatik?” – etwa von der
Gesellschaft für Infomatik,
der
TU Dresden,
oder auf Wikipedia –
machen es einem schwer, sic...