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
- Machine learning & Kafka KSQL stream processing — bug me when I’ve left the heater on on October 7, 2018 at 9:10 am
Continuous household power monitoring with a trained model to alert on unexpected power usage for time of day. Let my Google Home and Phone notify me when I’ve used more electricity than expected. […]
- Data Science Program at Argonne Looks to Machine Learning for New Breakthroughs on October 7, 2018 at 7:32 am
Over at Argonne, Nils Heinonen writes that four new projects for the ALCF Data Science Program (ADSP). These projects will utilize machine learning, deep learning, and other artificial intelligence me... […]
- Top Machine Learning Algorithms You Should Know to Become a Data Scientist on October 6, 2018 at 10:19 pm
Did you know that 50- 80% of your enterprise business processes can be automated with AssistEdge? Identify processes, deploy bots and scale effortlessly with AssistEdge. There are two ways to ... […]
- Deep Learning Is Great, But Use Cases Remain Narrow on October 5, 2018 at 11:41 am
However, despite the advantages that deep neural networks can bring for certain applications, the actual use cases for deep learning in the real world remain narrow, as traditional machine learning me... […]
- Symposium examines the potential of machine learning in health care on October 5, 2018 at 9:56 am
The excitement around machine learning in medicine has permeated the world of clinicians and researchers. While artificial intelligence is unlikely to replace medical professionals in the near future, ... […]
- Active Machine Learning Now Available in the VenioOne Platform on October 5, 2018 at 9:33 am
Super charge human reviewers with VenioOne's Continuous Active Learning and eliminate the tedious workflows of TAR 1.0. VenioOne CAL is now hitting its stride as a best of both worlds eDiscovery solut... […]
- Google to release DeepMind's StreetLearn for teaching machine-learning agents to navigate cities on October 5, 2018 at 7:57 am
Google is getting ready to release its StreetLearn dataset for training machine-learning models to navigate cities without a map. The StreetLearn environment relies on images from Google Street View a... […]
- A powerful machine learning system used by Microsoft has been released to the world on October 4, 2018 at 10:17 pm
A machine learning system that’s so advanced it’s been used to gain a new understanding of childhood asthma has been made available for everyone to use. Microsoft’s Infer.NET has been released on the ... […]
- Gergov: Machine learning, deep learning key to development on October 4, 2018 at 9:20 pm
Milko Gergov, a 45-year plastics veteran, is known for the IntelliMold process he developed in the early 1990s, which controls injection molding melt pressure and temperature using transducers. His mo... […]
via Bing News