Scientific AI’s Black Box is No Match for a 200-Year Old Method
Summary: Researchers explain the ability of deep neural networks to learn complex physics.
Source: Rice University
According to a recent study, Fourier analysis, a mathematical technique that dates back 200 years in computational physics can provide crucial information on how a type of artificial intelligence known as a deep neural networks learns to perform complex physics tasks like climate and turbulence modelling.
Source:
Scientific AI’s Black Box Is No Match for 200-Year-Old Method
Leave a Reply