Exciting #AI4science #DeepLearning architecture for super-resolution with continuous spatio-temporal outputs and PDE constraints to ensure validity. We tackle challenging problem of #turbulent #fluidsimulation Trained on 128 GPUs in <4 minutes @BerkeleyLab @Caltech @NVIDIAAI https://twitter.com/maxjiang93/status/1262796950610436096 …
-
-
I had been wondering about this since I came across this paper which draws out the relationships between convolutions and geometric multigrid, wish I had more time to dig into it https://arxiv.org/pdf/1901.10415.pdf … Anyway, congrats on a very interesting paper!
-
Very interesting point
@ColinJMcAuliffe. I recently read this article, https://arxiv.org/abs/1906.06925 , thought you might find it interesting. I know of a few groups (including my Ph.D. advisor's) working on this. - Show replies
New conversation -
Loading seems to be taking a while.
Twitter may be over capacity or experiencing a momentary hiccup. Try again or visit Twitter Status for more information.