Institute News

Günter Enderle Best Paper Award

  • 28 April 2017

at Eurographics 2017

for the paper "Sparse Inertial Pose: Automatic 3D Human Motion Capture from Sparse IMUs"

Gerard Pons-Moll Michael Black


Local networking event for female researchers from Tübingen

  • 28 April 2017

Hosted this time by Jeannette Bohg

Jeannette Bohg


March for Science - Tübingen

  • 22 April 2017

Science, not Silence!

The Managing Directors encourage staff and supporters of the Max Planck Institute for Intelligent Systems to participate in March for Science events.


New Research School for Intelligent Systems

  • 07 March 2017

Call for Applications - Ph.D. positions

The International Max Planck Research School (IMPRS) for Intelligent Systems (IS) is starting in fall 2017. This new doctoral program will enroll about 100 Ph.D. students over the next six years. Apply now!


DOOMED - A new online learning approach from AMD in the spotlight

  • 01 March 2017

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.

Franzi Meier Daniel Kappler Nathan Ratliff Stefan Schaal


How Can We Use Machine Learning in the Search for Exoplanets?

  • 01 February 2017

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.

Bernhard Schölkopf


Big Data in Robotics

  • 02 January 2017

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.

Jeannette Bohg


Go-ahead for Cyber Valley

  • 15 December 2016

Science and industry form one of Europe's largest research partnerships in artificial intelligence

Intelligent systems will shape our future: they could drive us as autonomous cars, help us out in the home on a daily basis or perform medical services as tiny robots. An initiative by the Max Planck Society and the Max Planck Institute for Intelligent Systems in the Stuttgart-Tübingen area is bringing together partners from science and industry to establish Cyber Valley where systems can be developed that will be capable of performing such feats. Winfried Kretschmann, Minister-President of Baden-Württemberg, Theresia Bauer, Minister of Science in Baden-Württemberg and Martin Stratmann, President of the Max Planck Society, together with the other project participants, have launched the initiative on Thursday, 15 December 2016 in Stuttgart's Neues Schloss.

Matthias Tröndle


ICERM Seminar on Probabilistic Scientific Computing

  • 13 December 2016

An upcoming workshop in June 2017 will explore applications of probabilistic numerics.

Philipp Hennig


Dagstuhl Seminar on the Future of Learning with Kernels and Gaussian Processes

  • 03 December 2016

A recent meeting at the Leibniz Centre for Computer Science highlights the ongoing significance of analytic nonparametric models for machine learning.

Philipp Hennig