acm-header
Sign In

Communications of the ACM

ACM TechNews

Better, Faster, Energy Efficient Predictions


The research combines artificial intelligence and computational science for accurate, efficient simulations of complex systems, including climate systems, tissue morphogenesis, and turbulence flows.

Credit: Harvard University John A. Paulson School of Engineering and Applied Sciences

Researchers at Harvard University's John A. Paulson School of Engineering and Applied Sciences (SEAS) have developed "intelligent alloys" that combine the power of computation with artificial intelligence to create models that complement predictive evolutionary simulations.

SEAS' Petros Koumoutsakos and Jane Bae computed turbulent flows by combining reinforcement learning and numerical methods, using machine learning (ML) agents that interact with mathematical equations.

"We take an equation and play a game where the agent is learning to complete the parts of the equations that we cannot resolve," Bae said. "The agents add information from the observations the computations can resolve and then they improve what the computation has done."

From Harvard University John A. Paulson School of Engineering and Applied Sciences (04/07/22) Leah Burrows
View Full Article

 

Abstracts Copyright © 2022 SmithBucklin, Washington, DC, USA


 

No entries found