TED Talks Daily - AI that connects the digital and physical worlds | Anima Anandkumar

Episode Date: July 9, 2024

“While language models may help generate new ideas, they cannot attack the hard part of science, which is simulating the necessary physics,” says AI professor Anima Anandkumar. She explains how her team developed neural operators — AI trained on the finest details of the real world — to bridge this gap, sharing recent projects ranging from improved weather forecasting to cutting-edge medical device design that demonstrate the power of AI with universal physical understanding.

TED Audio Collective. You're listening to TED Talks Daily, where we bring you new ideas to spark your curiosity every day. I'm your host, Elise Hu. Today, how AI is transforming scientific research, whether it's weather forecasting or drug discovery. Professor and AI innovator, Anima Anandkumar sheds light on the way scientists can use AI to capture a whole range of physical phenomena and why this could be crucial in the fight against climate change after a short break.

Support for this show comes from Airbnb. If you know me, you know I love staying in Airbnbs when I travel. They make my family feel most at home when we're away from home. As we settled down at our Airbnb during a recent vacation to Palm Springs, I pictured my own home sitting empty. Wouldn't it be smart and better put to use welcoming a family like mine by hosting it on Airbnb? It feels like the practical thing to do, and with the extra income, I could save up for renovations

to make the space even more inviting for ourselves and for future guests. Your home might be worth more than you think. Find out how much at Airbnb.ca slash host. Thank you. Ask bold questions like, why is Canada lagging in AI adoption? And how to catch up? Don't get left behind. Listen to Disruptors, the innovation era, and stay ahead of the game in this fast-changing world. Follow Disruptors on Apple Podcasts, Spotify, or your favorite podcast platform. I want to tell you about a podcast I love called Search Engine, hosted by PJ Vogt. Each week, he and his team answer these perfect questions, the kind of questions that,

when you ask them at a dinner party, completely derail conversation. Questions about business, tech, and society, like, is everyone pretending to understand inflation? Why don't we have flying cars yet? And what does it feel like to believe in God? If you find this world bewildering, but also sometimes enjoy being bewildered by it, check out Search Engine with PJ Vogt, available now wherever you get your podcasts. And now, our TED Talk of the day.

I grew up with parents who were engineers. They were among the first to bring computerized manufacturing to my hometown in India. Growing up as a young girl, I remember being fascinated how these computer programs didn't just reside within a computer, but touched the physical world and produced these beautiful and precise metal parts. Over the last two decades, as I pursued AI research, this memory continued to inspire me to connect the physical and digital worlds together. I am working on AI that transforms the way we do science and engineering. Scientific research and engineering design currently involves a lot of trial and error. Many long hours are spent in the lab doing experiments. So it's not just the great ideas that propel science forward. You need these experiments to validate findings

and spark new ideas. How can language models help here? What if I asked Chad Chippity to come up with a better design of an aircraft wing or a drone that flies under turbulent winds? It may suggest something. It may even draw something. But how do we know this is any good? We don't.

Language models hallucinate because they have no physical grounding. While language models may help generate new ideas, they cannot attack the hard part of science, which is simulating the necessary physics to replace the NAB experiments. In order to model scientific and physical phenomena, text alone is not sufficient. To get to AI with universal physical understanding, we need to train it on the data of the world we observe.

And not just that, also its hidden details. From the intricacies of quantum chemistry that happen at the smallest level, to molecules and proteins that influence how all biological processes work, to ocean currents and clouds that happen at planetary scales and beyond. We need AI that can capture

this whole range of physical phenomena. We need AI that can really zoom into the fine details in order to simulate these phenomena accurately. To capture the cloud movements and predict how clouds move and change in our atmosphere, we need to be able to zoom into the fine details of the turbulent fluid flow. Standard deep learning uses a fixed number of pixels. So if you zoom in, it gets blurry, and not all the details are captured.

We invented an AI technology called neural operators that represents the data as continuous functions or shapes and allows us to zoom in indefinitely to any resolution or scale. Neural operators allows us to train on data at multiple scales or resolutions and also allows us to incorporate the knowledge of mathematical equations to fill in the finer details when only limited resolution data is available. Such learning at multiple scales is essential for scientific understanding,

and neural operators enable this. With neural operators enable this. With neural operators, we can simulate physical phenomena such as fluid dynamics as much as a million times faster than traditional simulations. Last year, we used neural operators to invent a better medical catheter. A medical catheter is a tube that draws fluids out of the human body. Unfortunately, the bacteria tend to swim upstream against the fluid flow and infect the human. In fact, annually, there's more than half a million cases of such healthcare-related infections,

and this is one of the leading causes. Last year, we used neural operators to change the inside of the catheter from smooth to ridged. With ridges, now we have vortices created as the fluid flows. And we can hope to stop the bacteria from swimming upstream because of these vortices. But to get this correct, to stop the bacteria from swimming upstream because of these vortices. But to get this correct, we need the shape of the ridges to be exactly right. In the past, this would have been done by trial and error.

Design a version of the catheter, build it out, take it to the lab, observe a hypothesis if something went wrong, rinse and repeat and redesign again. But instead, we taught AI the behavior of the fluid flow inside the tube. And with it, our neural operator model was able to directly propose an optimized design. We 3D-printed the design only once to verify that it worked. The bacteria are not able to swim upstream, are instead being pushed out with the fluid flow. In fact, we measured the reduction in bacterial contamination by more than a hundredfold. So in this case, the neural operators were specialized to understand fluid flow in a tube.

What other applications can AI tackle and help us solve such pressing problems? And now, back to the episode. Can deep learning beat numerical weather models? A group of leading weather scientists asked this question in February 2021 in a Royal Society publication. They felt that AI was still in its infancy and that a number of fundamental breakthroughs would be needed for AI to become competitive with traditional weather models. And that would take years or even decades. Exactly a year later, we released ForecastNet. Using neural operators, we built the first fully AI-based weather model that is high resolution and is tens of thousands of times faster than traditional weather models. What used to take a big supercomputer can now run

on a gaming PC that you may have at home. This model is also running at the European Center for Medium-Range Weather Forecasting, one of the premier weather agencies of the world. And our AI model is not just tens of thousands of times faster than traditional models. It's also more accurate in many cases. On September 16th last year, Hurricane Lee hit the coast of Nova Scotia, Canada. A full 10 days earlier, our forecast net model correctly predicted that the hurricane would make landfall. But the traditional weather model

predicted the hurricane would skip the coast. Only five days later, on September 11th, did the traditional weather model correct its forecast to predict landfall. Extreme weather events such as Hurricane Lee will only increase further unless we take action on climate change, such as finding new, clean sources of energy. Nuclear fusion is one of them.

But unfortunately, there are still big challenges with it. The fusion reactor heats up the plasma to extremely high temperatures to get fusion started. And sometimes, this hot plasma can escape confinement and can damage the reactor. We train neural operators to simulate and predict the evolution of plasma inside the reactor. And with it, we can use this to predict disruptions before they occur and take corrective action in the real world. We are enabling the possibility of nuclear fusion becoming a reality.

So neural operators and AI broadly are enabling us to tackle hard scientific challenges, such as climate change and nuclear fusion. To me, this is just the beginning. So far, these AI models are limited to the narrow domains they're trained on. What if you had an AI model that could solve all and any scientific problem, from designing better drones, aircrafts, rockets,

and even better drugs and medical devices? Such an AI model would greatly benefit humanity. This is what we are working on. We are building a generalist AI model would greatly benefit humanity. This is what we are working on. We are building a generalist AI model with emergent capabilities that can simulate any physical phenomena and generate novel designs that were previously out of reach.

This is how we scale up neural operators to enable general intelligence with universal physical understanding. Thank you. Support for this show comes from Airbnb. If you know me, you know I love staying in Airbnbs when I travel. They make my family feel most at home when we're away from home. As we settled down at our Airbnb during a recent vacation to Palm Springs, I pictured my own home sitting empty. Wouldn't it be smart and better put to use welcoming a family like mine by hosting it on Airbnb? It feels like the practical thing to do, and with the extra income, I could save up for renovations to make the space even more inviting

for ourselves and for future guests. Your home might be worth more than you think. Find out how much at airbnb.ca slash host. That was Anima Anandkumar at TED 2024. If you're curious about TED's curation, find out more at TED.com slash curation guidelines. And that's it for today. TED Talks Daily is part of the TED Audio Collective. This episode was produced and edited by our team,

Martha Estefanos, Oliver Friedman, Brian Green, Autumn Thompson, and Alejandra Salazar. It was mixed by Christopher Faisy-Bogan. Additional support from Emma Taubner, Daniela Balarezo, and Will Hennessey. I'm Elise Hugh. I'll be back tomorrow with a fresh idea for your feed. Thanks for listening.

Looking for a fun challenge to share with your friends and family? TED now has games designed to keep your mind sharp while having fun. Visit TED.com slash games to explore the joy and wonder of TED Games.