Good progress being made. But I wonder if the results are real, i.e., how well can they be applied to unseen problems.https://twitter.com/AnimaAnandkumar/status/1319055677260611586 …
-
-
Replying to @parresianz
What do you mean? We solve for family of PDEs. These are evaluated on instances not seen during training.
1 reply 0 retweets 2 likes -
Replying to @AnimaAnandkumar
I was thinking of non-Newton fluids vs Newtonian. The PDE systems are not without constitutive models. Can a system trained on Newtonian behavior predict non-Newtonian behavior etc.
1 reply 0 retweets 1 like
Replying to @parresianz
This assumes a parametric family of PDEs
4:37 PM - 21 Oct 2020
0 replies
0 retweets
2 likes
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.