Forum for Science, Industry and Business

Sponsored by:     3M 
Search our Site:

 

First machine learning method capable of accurate extrapolation

13.07.2018

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 robot needs to learn about his body and the environment. It tries a few different motions and uses the algorithm. It can then predict what will happen with larger movements and at higher speeds.

IST Austria/Birgit Rieger

A new method developed by scientists at the Institute of Science and Technology Austria (IST Austria) and the Max Planck Institute for Intelligent Systems (MPI 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).

In the past, machine learning was only capable of interpolating data—making predictions about situations that are “between” other, known situations. It was incapable of extrapolating—making predictions about situations outside of the known—because it learns to fit the known data as closely as possible locally, regardless of how it performs outside of these situations. In addition, collecting sufficient data for effective interpolation is both time- and resource-intensive, and requires data from extreme or dangerous situations.

But now, Georg Martius, former ISTFELLOW and IST Austria postdoc, and since 2017 a group leader at MPI for Intelligent Systems in Tübingen, Subham S. Sahoo, a PhD student also at MPI for Intelligent Systems, and Christoph Lampert, professor at IST Austria, developed a new machine learning method that addresses these problems, and is the first machine learning method to accurately extrapolate to unseen situations.

The key feature of the new method is that it strives to reveal the true dynamics of the situation: it takes in data and returns the equations that describe the underlying physics. “If you know those equations,” says Georg Martius, “then you can say what will happen in all situations, even if you haven’t seen them.” In other words, this is what allows the method to extrapolate reliably, making it unique among machine learning methods.

The team’s method sets itself apart in several other ways as well. First, the final approximations previously produced during machine learning were far too complex for a human to understand or work with. In the new method, the resulting equations are far simpler: “Our method’s equations are something you would see in a textbook—simple and intuitive,” says Christoph Lampert. The latter is another key difference: other machine learning methods give no insight into the relationship between conditions and results—and thus, no intuition on whether the model is even plausible.

“In every other area of research, we expect models that make physical sense, that tell us why,” adds Lampert. “This is what we should expect from machine learning, and what our method provides.” Finally, in order to guarantee interpretability and optimize for physical situations, the team based their learning method on a different type of framework. This new design is simpler than previous methods, which in practice means that less data is needed to give the same or even better results.

And it’s not all theory: “In my group, we’re actually working on developing a robot that uses this type of learning. In the future, the robot would experiment with different motions, then be able to use machine learning to uncover the equations that govern its body and movement, allowing it to avoid dangerous actions or situations,” adds Martius. While robots are one active area of research, the method can be used with any type of data, from biological systems to X-ray transition energies, and can also be incorporated into larger machine learning networks.

This project has received funding from the European Union’s Horizon 2020 research and innovation programme under the Marie Skłodowska-Curie grant agreement No 291734.

The research received funding from the ISTFELLOW program, a Marie Skłodowska-Curie COFUND grant co-funded by IST Austria and the European Union through the Horizon 2020 research and innovation programme. This program has since been succeeded by another COFUND grant, the ISTplus program, which is open for applications from qualified postdocs all over the world.

About IST Austria
The Institute of Science and Technology (IST Austria) is a PhD-granting research institution located in Klosterneuburg, 18 km from the center of Vienna, Austria. Inaugurated in 2009, the Institute is dedicated to basic research in the natural and mathematical sciences. IST Austria employs professors on a tenure-track system, postdoctoral fellows, and doctoral students. While dedicated to the principle of curiosity-driven research, the Institute owns the rights to all scientific discoveries and is committed to promote their use. The first president of IST Austria is Thomas A. Henzinger, a leading computer scientist and former professor at the University of California in Berkeley, USA, and the EPFL in Lausanne, Switzerland. The graduate school of IST Austria offers fully-funded PhD positions to highly qualified candidates with a bachelor's or master's degree in biology, neuroscience, mathematics, computer science, physics, and related areas. http://www.ist.ac.at

About MPI-IS
At the Max Planck Institute for Intelligent Systems we aim to understand the principles of Perception, Action and Learning in Intelligent Systems.
The Max-Planck-Institute for Intelligent Systems is located in two cities: Stuttgart and Tübingen. Research at the Stuttgart site of the Max Planck Institute for Intelligent Systems covers small-scale robotics, self-organization, haptic perception, bio-inspired systems, medical robotics, and physical intelligence. The Tübingen site of the institute concentrates on machine learning, computer vision, robotics, control, and the theory of intelligence.

Wissenschaftliche Ansprechpartner:

Georg Martius: gmartius@tuebingen.mpg.de
Christoph Lampert: chl@ist.ac.at

Originalpublikation:

S. S. Sahoo, C. H. Lampert, and G. Martius: "Learning equations for extrapolation and control". In Proceedings of the 35th International Conference on Machine Learning, ICML 2018, Stockholm, Sweden, 2018. PMLR, 2018.
http://proceedings.mlr.press/v80/sahoo18a.html
Arxiv Preprint: https://arxiv.org/abs/1806.07259

Weitere Informationen:

https://icml.cc/ Link to conference
http://cvml.ist.ac.at/ Link to Prof. Lampert's research group

Dr. Elisabeth Guggenberger | idw - Informationsdienst Wissenschaft

Further reports about: Intelligent Systems Learning MPI Max Planck Institute machine learning

More articles from Information Technology:

nachricht NIST-led team develops tiny low-energy device to rapidly reroute light in computer chips
15.11.2019 | National Institute of Standards and Technology (NIST)

nachricht Fraunhofer Radio Technology becomes part of the worldwide Telecom Infra Project (TIP)
14.11.2019 | Fraunhofer-Institut für Angewandte Informationstechnik FIT

All articles from Information Technology >>>

The most recent press releases about innovation >>>

Die letzten 5 Focus-News des innovations-reports im Überblick:

Im Focus: Machine learning microscope adapts lighting to improve diagnosis

Prototype microscope teaches itself the best illumination settings for diagnosing malaria

Engineers at Duke University have developed a microscope that adapts its lighting angles, colors and patterns while teaching itself the optimal...

Im Focus: Small particles, big effects: How graphene nanoparticles improve the resolution of microscopes

Conventional light microscopes cannot distinguish structures when they are separated by a distance smaller than, roughly, the wavelength of light. Superresolution microscopy, developed since the 1980s, lifts this limitation, using fluorescent moieties. Scientists at the Max Planck Institute for Polymer Research have now discovered that graphene nano-molecules can be used to improve this microscopy technique. These graphene nano-molecules offer a number of substantial advantages over the materials previously used, making superresolution microscopy even more versatile.

Microscopy is an important investigation method, in physics, biology, medicine, and many other sciences. However, it has one disadvantage: its resolution is...

Im Focus: Atoms don't like jumping rope

Nanooptical traps are a promising building block for quantum technologies. Austrian and German scientists have now removed an important obstacle to their practical use. They were able to show that a special form of mechanical vibration heats trapped particles in a very short time and knocks them out of the trap.

By controlling individual atoms, quantum properties can be investigated and made usable for technological applications. For about ten years, physicists have...

Im Focus: Images from NJIT's big bear solar observatory peel away layers of a stellar mystery

An international team of scientists, including three researchers from New Jersey Institute of Technology (NJIT), has shed new light on one of the central mysteries of solar physics: how energy from the Sun is transferred to the star's upper atmosphere, heating it to 1 million degrees Fahrenheit and higher in some regions, temperatures that are vastly hotter than the Sun's surface.

With new images from NJIT's Big Bear Solar Observatory (BBSO), the researchers have revealed in groundbreaking, granular detail what appears to be a likely...

Im Focus: New opportunities in additive manufacturing presented

Fraunhofer IFAM Dresden demonstrates manufacturing of copper components

The Fraunhofer Institute for Manufacturing Technology and Advanced Materials IFAM in Dresden has succeeded in using Selective Electron Beam Melting (SEBM) to...

All Focus news of the innovation-report >>>

Anzeige

Anzeige

VideoLinks
Industry & Economy
Event News

First International Conference on Agrophotovoltaics in August 2020

15.11.2019 | Event News

Laser Symposium on Electromobility in Aachen: trends for the mobility revolution

15.11.2019 | Event News

High entropy alloys for hot turbines and tireless metal-forming presses

05.11.2019 | Event News

 
Latest News

Scientists first to develop rapid cell division in marine sponges

21.11.2019 | Life Sciences

First detection of gamma-ray burst afterglow in very-high-energy gamma light

21.11.2019 | Physics and Astronomy

Research team discovers three supermassive black holes at the core of one galaxy

21.11.2019 | Physics and Astronomy

VideoLinks
Science & Research
Overview of more VideoLinks >>>