Fachbereich Informatik

64.360 Lecture: Algorithmic Learning

Room B-201 (Konrad-Zuse Hörsaal)
Schedule starting 11.04.2013
Monday and Wednesday, 08:30-10:00
Ulrike von Luxburg, Jianwei Zhang, Norman Hendrich
Contents The lecture introduces the basics of machine learning including supervised learning, unsupervised learning, and reinforcement learning algorithms.
Literature Marsland: Machine Learning - an Algorithmic Perspective, CRC Press, 2010
Rojas: Neural networks - a systematic introduction, Springer, 1996
Mitchell, T.M.: Machine learning, McGraw-Hill, 1997
Sutton and Barto: Reinforcement Learning - an introduction, MIT Press 1998
Additional references will be announced during the lecture.

Slides webpage at group ML

Note: the slides will again be updated a bit this year, please check from time to time for the latest version:
Reinforcement Learning 1
Reinforcement Learning 2
Reinforcement Learning 3

Exercises Assignment 11
Assignment 12
Assignment 13
The next (bonus) assignment will be posted on 08/July.

News I just realized that R.S. Sutton and A.G. Barto provide a nice PDF of their planned second edition of Reinforcement Learning: An Introduction for free via Dropbox. Please visit their book homepage, or just click here.
A RL paper was just nominated as the best IEEE TR robotics paper for 2012: Stulp, F. ; Theodorou, E.A. ; Schaal, S.: Reinforcement Learning With Sequences of Motion Primitives for Robust Manipulation, IEEE Transactions on Robotics 28-6, 2012, Digital Object Identifier: 10.1109/TRO.2012.2210294. (Access from Informatics network).