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 (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.
Learn more: First machine learning method capable of accurate extrapolation
The Latest on: Machine learning
[google_news title=”” keyword=”machine learning” num_posts=”10″ blurb_length=”0″ show_thumb=”left”]
via Google News
The Latest on: Machine learning
- Machine learning-powered robot streamlines genetic research processon April 26, 2024 at 9:26 pm
University of Minnesota Twin Cities researchers have constructed a robot that uses machine learning to fully automate a complicated microinjection process used in genetic research.
- Automated machine learning robot unlocks new potential for genetics researchon April 26, 2024 at 9:10 am
University of Minnesota Twin Cities researchers have constructed a robot that uses machine learning to fully automate a complicated microinjection process used in genetic research.
- 3 Machine Learning Stocks That Could Be Multibaggers in the Making: April Editionon April 26, 2024 at 6:59 am
InvestorPlace - Stock Market News, Stock Advice & Trading Tips After a calamitous week, United States equities seem to be back on the rise.
- 3 Machine Learning Stocks That Could Triple Your Money by 2030on April 26, 2024 at 3:58 am
InvestorPlace - Stock Market News, Stock Advice & Trading Tips Investing in machine learning (ML) stocks presents an enticing opportunity for ...
- Machine learning model predicts CIS to MS conversion risk: Studyon April 25, 2024 at 10:00 pm
A machine learning model can predict the risk of converting from clinically isolated syndrome (CIS) to multiple sclerosis (MS), per a study.
- Artificial intelligence, machine learning boost animal science researchon April 25, 2024 at 10:44 am
Science X is a network of high quality websites with most complete and comprehensive daily coverage of the full sweep of science, technology, and medicine news ...
- Machine learning and extended reality used to train welderson April 25, 2024 at 10:30 am
Ever since the ancient Egyptians hammered two pieces of gold together until they fused, the art of welding has continuously progressed.
- JFrog unveils MLflow integration to enhance machine learning model managementon April 25, 2024 at 6:15 am
Software supply chain company JFrog Ltd. today announced a new machine learning lifecycle integration between JFrog Artifactory and MLflow, an open-source software platform origin ...
- Machine learning and experimenton April 25, 2024 at 5:31 am
For more than 20 years in experimental particle physics and astrophysics, machine learning has been accelerating the pace of science, helping scientists tackle problems of greater and greater ...
via Bing News