Future computer programs will contain a growing part of 'intelligent' software modules that are not conventionally programmed, but that are learned either from data provided by the user or from data that the program autonomously collects during its use.
In this spirit, the Machine Learning Lab deals with research on Machine Learning techniques and the integration of learning modules into larger software systems, aiming at their effective application in complex real-world problems. Application areas are robotics, control, forecasting and disposition systems, scheduling and related fields.
Research Areas: Efficient Reinforcement Learning Algorithms, Intelligent Robot Control Architectures, Learning in Multiagent Systems, (Un-)Supervised Learning, Deep Learning, Autonomous Robots, Industrial Applications, Clinical Applications
Particular thanks to all the students, colleagues and administrative staff, who have contributed to the success of the Machine Learning Lab in the recent years! Keep on learning!
Dr. Joschka Bödecker will temporarilly head the MLL lab and teach the courses in the upcoming summer term.
Wettbewerb Automatic Machine Learning
Wettbewerb Automatic Machine Learning 22.4.2015
Sieben Mitarbeiter der Gruppen „Automatisches Algorithmendesign“ von Dr. Frank Hutter und „Maschinelles Lernen“ von Prof. Martin Riedmiller haben in der ersten Phase des Wettbewerbs Automatic Machine Learning (AutoML) den ersten Platz erreicht.
Audi Autonomous Driving Cup
Audi Autonomous Driving Cup 27.3.2015
We're happy to be able to congratulate our students of Team FRUIT for reaching the finals and scoring an impressive third place at the first Audi Autonomous Driving Cup. In the competition hosted this week by the Audi AG in Ingolstadt, teams from ten universities were tasked with solving various aspects of autonomous driving.
System Design Project Competition
System Design Project Competition 17.2.2015
The annual final competition of the System Design Project will take place this Wednesday, February 18. First year students will compete with LEGO robots developed over the past semester to finish an unknown course as quickly as possible. This year, a livestream will be available as well, which you can watch here.