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.
The Latest on: Machine learning
via Google News
The Latest on: Machine learning
Oracle puts GraphPipe into open source to standardize and deploy machine learning
on August 17, 2018 at 9:31 am
Oracle released a new tool, which is called GraphPipe, into open source in order to speed up real-world deployments of machine learning. GraphPipe, which Oracle has put into open source via GitHub, wa... […]
More efficient security for cloud-based machine learning
on August 17, 2018 at 8:01 am
A novel encryption method devised by MIT researchers secures data used in online neural networks, without dramatically slowing their runtimes. This approach holds promise for using cloud-based neural ... […]
Machine learning: How to create a recommendation engine
on August 17, 2018 at 3:26 am
For more information, visit informit.com/AI/Infoworld. What do Russian trolls, Facebook, and US elections have to do with machine learning? Recommendation engines are at the heart of the central feedb... […]
When Machine Learning Meets the Business World
on August 17, 2018 at 2:24 am
Insight for I&O leaders on deploying AIOps platforms to enhance performance monitoring today. Read the Guide. Businesses have always been at the forefront as early adopters of new technologies. Advanc... […]
Machine Learning in the World of Nuclear Physics [Video]
on August 16, 2018 at 10:19 pm
Insight for I&O leaders on deploying AIOps platforms to enhance performance monitoring today. Read the Guide. How does TensorFlow apply to nuclear physics? In this video, I chat with Ian Langmore to l... […]
Machine learning not ready for the cloud, yet
on August 16, 2018 at 7:39 pm
It stands to reason that many organizations interested in artificial intelligence and machine learning, which requires some sophisticated skills, will turn to cloud-based services to make it happen. H... […]
Simplifying machine learning lifecycle management
on August 16, 2018 at 7:24 pm
August 16, 2018 AEDC’s 16-foot supersonic wind tunnel test facility (source: Phil Tarver, Arnold Engineering Development Center, U.S. Air Force on Wikimedia Commons) Check out the great series of talk... […]
This Seattle Startup Uses AI And Machine Learning To Personalize Customer Experience, Marketing
on August 16, 2018 at 6:13 pm
With all the tools and channels available to help brands reach customers, it still seems like most brands out there are floundering in their efforts do so effectively. Your Customer Is The Star: A Boo... […]
Salesforce plans to open-source the technology behind its Einstein machine-learning services
on August 16, 2018 at 1:00 pm
Salesforce is open-sourcing the method it has developed for using machine-learning techniques at scale — without mixing valuable customer data — in hopes other companies struggling with data science p... […]
via Bing News