Convolution, aggregation and attention based deep neural networks for accelerating simulations in mechanics

RT @Saurabh1715: We explore state-of-the-art neural network architectures such as Perceiver IO, MAgNET, and CNN U-NET for efficient learnin…

We explore state-of-the-art neural network architectures such as Perceiver IO, MAgNET, and CNN U-NET for efficient learning of highly non-linear deformations of solid bodies. In collaboration with Ian Sosa, @JLengiewicz, @stephanebordas. #DeepLearning #

New research on using convolution, aggregation, and attention-based deep neural networks for mechanics simulations is out! Congrats to our ESR @Saurabh1715 and the team @stephanebordas @JLengiewicz @MSCActions. DOI: https://t.co/MWGvYDe0P4 Code: https://

New Research: Convolution, aggregation and attention based deep neural networks for accelerating simulations in mechanics: Deep learning surrogate models are being increasingly used in accelerating scientific simulations as a… https://t.co/mYgHKfbu3K #Mate