Cordelia Schmid, an Inria research director, has received the Humboldt Research Award for her work on computer vision spanning more than 20 years.
She was nominated for this scientific award by Michael Black, the director of the Perceiving Systems department at the Max Planck Institute for Intelligent Systems in Tübingen, Germany. As the director of the LEAR team and then the Thoth team since 1 January 2016, Cordelia Schmid is particularly interested in visual recognition linking invariant image descriptors with learning methods. Her research enables a computer to learn not only to interpret all types of real images and videos, but also to recognize objects, actions and places by learning large image and video bases containing more than 100 million images. Cordelia Schmid figures among the world’s precursors and leaders in the field of modern visual recognition methods; she is also named in the “Highly Cited Researchers 2015” list (source: Thomson Reuters).
Autonomous Robots made in Tübingen
Als Haushaltshilfe, Pflegeassistent oder Katastrophenschützer taugen Roboter nur, wenn sie lernfähig sind und zumindest ansatzweise selbstständig handeln können. Stefan Schaal und die Mitarbeiter seiner Abteilung am Max-Planck-Institut für Intelligente Systeme in Tübingen bringen den Maschinen diese Flexibilität und Autonomie bei.
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.
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.
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.
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.
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).
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.