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 as a Service (MLaaS) Global Research Report 2024: Market to Surpass $200 Billion by 2028 - Long-term Forecast to 2033on May 10, 2024 at 3:20 am
It will grow from $42.09 billion in 2023 to $57.88 billion in 2024 at a compound annual growth rate (CAGR) of 37.5%. The growth in ...
- New machine learning algorithm promises advances in computingon May 9, 2024 at 3:03 pm
Systems controlled by next-generation computing algorithms could give rise to better and more efficient machine learning products, a new study suggests.
- Machine learning tool flags undiagnosed immunodeficiency diseaseon May 9, 2024 at 6:00 am
A machine learning model can effectively sift through EHR data to rank patients' likelihood of having common variable immunodeficiency disease.
- Machine Learning Takes the Stage at TC Sessions: Robotics+AIon May 8, 2024 at 2:00 pm
The roots of machine learning go back at least to 1962, when Doug Engelbart of the Stanford Research Institute argued that computers could play a role in augmenting the human intellect. Outlandish at ...
- Machine learning aids in discovery of sperm whale ‘alphabet’on May 8, 2024 at 11:01 am
Researchers at MIT CSAIL and Project CETI believe that they have unlocked a kind of sperm whale alphabet with the aid of machine learning technologies.
- The Future Of SEO: How AI And Machine Learning Are Changing Searchon May 8, 2024 at 4:45 am
Despite the uncertainty about how search engines adjust to the new AI world, machine learning is revolutionizing—for the better—the way businesses approach SEO.
- From Beginner To Enthusiast: Top 5 Free Harvard Courses To Spark Your AI Journey With Machine Learning, Python And Moreon May 8, 2024 at 3:55 am
Ever thought about diving into the world of Artificial Intelligence (AI) but felt intimidated by the hefty price tags on courses? Well, Harvard University is offering a golden opportunity to get ...
- Machine learning helps to discover sperm whale ‘alphabet'on May 8, 2024 at 3:07 am
Researchers have cracked the code to a sperm whale ‘alphabet' after using machine learning technologies to understand vocalizations. In a… Continue reading Machine learning helps to discover sperm ...
- Machine learning engineer salary: How much do AI techs make?on May 7, 2024 at 4:02 pm
Machine learning engineers tend to be among the highest-paid employees in tech. Here’s how much they make and which companies pay the most.
via Bing News