Our next session is in 10min! Tune in for talks by Frank Noe (@FrankNoeBerlin), Keno Fischer (@KenoFischer), Patrick Kidger (@PatrickKidger), and Deniz Bezgin!
Image from Differentiable Programming (@diffprogramming)

Dec 13, 2021 · 3:43 PM UTC

1
1
12
Cool talk by @FrankNoeBerlin about Differentiable Programming in Molecular Physics!
1
1
4
And @KenoFischer just finished his talk on Diffractor.jl: a next-generation, compiler-based AD system for Julia. Check out his code from today here bit.ly/3ymDjMr
NeurIPS talk.pdf

NeurIPS talk.pdf

GitHub Gist: instantly share code, notes, and snippets.

gist.github.com
1
1
4
@PatrickKidger spoke about Equinox: a library that brings more power to your model building in JAX! Check it out here github.com/patrick-kidger/eq…
GitHub - patrick-kidger/equinox: Elegant easy-to-use neural networks + scientific computing in JAX....

GitHub - patrick-kidger/equinox: Elegant easy-to-use neural networks + scientific computing in JAX....

Elegant easy-to-use neural networks + scientific computing in JAX. https://docs.kidger.site/equinox/ - patrick-kidger/equinox

github.com
1
1
4
Deniz Bezgin wrapped up the session describing a fully-differentiable compressible high-order computational fluid dynamics solver. See the paper here arxiv.org/abs/2112.04979
A fully-differentiable compressible high-order computational fluid...

A fully-differentiable compressible high-order computational fluid...

Fluid flows are omnipresent in nature and engineering disciplines. The reliable computation of fluids has been a long-lasting challenge due to nonlinear interactions over multiple spatio-temporal...

arxiv.org