Header logo is al
Group News

First machine learning method capable of accurate extrapolation

  • 13 July 2018

Scientists develop new machine learning method that can make robots safer - New method provides simpler and more intuitive models of physical situations

Understanding how a robot will react under different conditions is essential to guaranteeing its safe operation. But how do you know what will break a robot without actually damaging it? A new method developed by scientists at the Institute of Science and Technology Austria and the Max Planck Institute for Intelligent Systems is the first machine learning method that can use observations made under safe conditions to make accurate predictions for all possible conditions governed by the same physical dynamics. Especially designed for real-life situations, their method provides simple, interpretable descriptions of the underlying physics. The researchers will present their findings tomorrow at this year’s prestigious International Conference for Machine Learning (ICML).

Georg Martius


Jia-Jie Zhu receives the Marie Curie Individual Fellowship

  • 27 June 2018

A prestigious junior scientist fellowship is awarded to the MPI-IS researcher

Jia-Jie Zhu Georg Martius


ICML 2018 paper accepted

  • 21 June 2018

Our Paper "Learning Equations for Extrapolation and Control" got excepted at ICML 2018! We are looking forward to present and discuss in Stockholm in July 10-15, 2018.

Georg Martius


CVPR Honorable Mention

  • 19 June 2018

The paper ' Efficient Optimization for Rank-based Loss Functions', on which Michal Rolinek was contributing to, received the CVPR Honorable Mention award.

Michal Rolinek


ALIFE 2018 paper accepted

  • 01 May 2018

Our paper 'Systematic self-exploration of behaviors for robots in a dynamical systems framework' was accepted for ALIFE 2018 and will be presented in Tokyo, July 2018.

Cristina Pinneri Georg Martius