Header logo is
Institute News

Autos gehen die Augen auf - Cars open their Eyes

  • 07 January 2016

Perception is essential for Intelligence

Einen Wagen mit Chauffeur könnte es irgendwann für jeden geben, wenn nämlich ein Roboter das Steuer übernimmt. Damit Autos auch ohne großen technischen Aufwand autonom fahren können, müssen Computer unübersichtliche Verkehrssituation jedoch mindestens genauso gut beurteilen wie der Mensch.

Andreas Geiger Michael Black Osman Ulusoy Joel Janai


Middlebury Dataset awarded 2015 IEEE Mark Everingham Prize

  • 16 December 2015

The 2015 PAMI Mark Everingham Prize was awarded to the Middlebury Dataset (Daniel Scharstein, Richard Szeliski, and team) for a series of datasets and on-line evaluations, starting with the Stereo datasets in 2001, and extending to Optical Flow, MRF and others, which have inspired many other datasets. Michael Black was part of the team behind the Optical Flow dataset and evaluation.

Michael Black


Best Paper Award @ NIPS Workshop 2015

  • 12 December 2015

for Ruth Urner at the NIPS 2015 Workshop on "Transfer and Multitask Learning: Trends and New Perspectives".

Ruth Urner


Per Mikroschwimmer zur Magenwand

  • 11 December 2015

Ein mit Enzymen beschichteter Mikropropeller verflüssigt lokal die Magenschleimhaut, um sie zu durchdringen

Helicobacter pylori macht es vor. Das im menschlichen Magen häufig vorkommende Bakterium versteht es, sich auch durch die zähe Magenschleimhaut hindurchzubewegen. Zu diesem Zweck scheidet es Substanzen aus, die den pH-Wert ihrer Umgebung verändern und damit den gelartigen Schleim verflüssigen. Forscher des Max-Planck-Instituts für Intelligente Systeme in Stuttgart haben dieses Prinzip aufgegriffen und nach ihm ein künstliches Mikrovehikel geschaffen, das ebenfalls viskose Schleimhäute durchdringen kann. Die Forscher verbinden damit eine konkrete Hoffnung: Eines Tages könnten solche Schwimmer vielleicht pharmazeutische Wirkstoffe direkt an die Magenwand transportieren – und dort für eine effektive Aufnahme in die Blutbahn sorgen.

Debora Schamel Peer Fischer Jeong Hyeon-Ho


Köppen Award 2015 for Machine Learning in Climate Research

  • 09 December 2015

Excellent doctoral dissertation

Dr. Jakob Zscheischler is to receive this year’s Wladimir Peter Köppen Award. The Cluster of Excellence CliSAP selected the mathematician for his excellent doctoral dissertation submitted at the Swiss Federal Institute of Technology Zurich (ETH) in 2014. His work was rated trendsetting by the jurors who found its thematic and methodical approach particularly original. Jakob Zscheischler completed his dissertation in Germany at the German Max Planck Institute for Biogeochemistry in Jena and the Max Planck Institute for Intelligent Systems in Tübingen.

Jakob Zscheischler


NIPS Oral for Maren Mahsereci

  • 01 December 2015

PhD student will present her work on optimization for deep learning

Maren Mahsereci's paper on probabilistic line searches for stochastic optimization has been selected for a full oral presentation at the flagship conference of machine learning.

Maren Mahsereci Philipp Hennig


Inauguration of the Max Planck ETH Center for Learning Systems

  • 30 November 2015

Inauguration Ceremony in Tübingen

(From left to right): Prof. Dr. Bradley Nelson (ETH Zürich), Dr. Stefan Schaal (MPI for Intelligent Systems), Christine Schraner Burgener (Swiss Ambassador to Germany), Prof. Dr. Lino Guzella (President ETH Zürich), Prof. Dr. Martin Stratmann (President Max Planck Society), Theresia Bauer (Science Minister of Baden-Württemberg), Prof. Dr. Bernhard Schölkopf MPI for Intelligent Systems and Co-Director of the CLS), Prof. Dr. Thomas Hofmann (ETH Zürich, Co-Director of the CLS).


Learning Control Workshop

  • 11 November 2015

Researchers from ETH Zürich and MPI for Intelligent Systems come together to exchange ideas and discuss challenges for Learning Control

Albeit Learning Control is not uniquely defined, we understand Learning Control as the rather broad research area that lies at the intersection of Machine Learning and Automatic Control. This includes, but is not limited to data-driven approaches for control design, adaptive control, dual control, machine learning for control, online learning, active learning for control, reinforcement learning, and applications of learning control.

Melanie Zeilinger Ludovic Righetti Sebastian Trimpe


One of the best science videos of the year!

  • 03 November 2015

2nd prize at the "Fast Forward Science 2015" Competition

The movie "Light gets on your nerves" was financed and coordinated by the Max Planck Society and pictures the research of the Brain-Computer-Interfaces group at our institute.

Sebastian Weichwald Timm Meyer Moritz Grosse-Wentrup Bernhard Schölkopf Tatiana Fomina


Surprise at the nanoscale: Silicon atoms jump after contact with metal

  • 28 October 2015

Max Planck researchers from Stuttgart reveal unknown behaviour of semi-conductors at the nanoscale