Text: Kathryn Ryan. New Rochelle, February 21, 2017.
Robotics researchers have developed a novel adaptive control approach based on online learning that allows for the correction of dynamics errors in real time using the data stream from the robot. The strategy is described in an article published in Big Data, a peer-reviewed journal from Mary Ann Liebert, Inc., publishers. The article is available free on the Big Data website until March 14, 2017.
The Heinz Maier-Leibnitz-Prize 2017 will be awarded May 3, 2017 in Berlin. Stay tuned for more information!
Bernhard Schölkopf joined the initiative "Latest Thinking"
Exoplanets are planets beyond our own solar system. Since they do not emit much light and moreover are very close to their parent stars they are difficult to detect directly. When searching for exoplanets, astronomers use telescopes to monitor the brightness of the parent star under investigation: Changes in brightness can point to a passing planet that obstructs part of the star’s surface. The recorded signal, however, contains not only the physical signal of the star but also systematic errors caused by the instrument. As Bernhard Schölkopf explains in this video, this noise can be removed by comparing the signal of the star of interest to those of a large number of other stars. Commonalities in their signals might be due to confounding effects of the instrument. Using machine learning, these observations can be used to train a system to predict the errors and correct the light curves.
Guest edited by Jeannette Bohg, Matei Ciocarlie, Javier Civera, Lydia E. Kavraki.
... new big data methods have the potential to allow robots to understand and operate in significantly more complex environments than was possible even in the recent past. This should lead to a qualitative leap in the performance and deployability of robotics in a wide array of practical applications and real settings.
An upcoming workshop in June 2017 will explore applications of probabilistic numerics.
A recent meeting at the Leibniz Centre for Computer Science highlights the ongoing significance of analytic nonparametric models for machine learning.
CYBATHLON Championship for Athletes with Disabilities
Zürich. On October 8, 2016, a collaboration of the research group "Brain-Computer-Interfaces" at the MPI-IS and the "Autonomous Systems Lab" at the TU Darmstadt will send a joint team into the Brain-computer-Interface Race at the Cybathlon 2016 in Zurich. The so called Athena-Minerva team consists mainly of computer science students of bachelor and master-level at the Technical University Darmstadt. They are interested in "Machine Learning", signal processing and especially for Brain-Computer-Interfaces (BCI). The team is headed by Moritz Grosse-Wentrup from MPI-IS and by Jan Peters, TU Darmstadt. The pilot is Sebastian Reul.