 |
| A Differentiable Programming System to Bridge ML and Scientific Computing (arxiv.org) | ||
| recommended by 1 user | 2019 | 381 points by ChrisRackauckas | machine learning | original thread | | ||
| One user recommended this thread. What they said: |
| StefanKarpinski Jul 31, 2019 | on: Scientific AI: Domain Models with Integrated Machine… | context |
Hope it helps you solve some very hard problems :)
The Zygote package for Julia (part of the Flux ML framework) is the state of the art, see:
https://news.ycombinator.com/item?id=20477873
(This talk was given at JuliaCon last week.)
If you need any guidance or help getting started, you may want to join the Julia Slack: https://slackinvite.julialang.org/. There's a very active and helpful #machine-learning channel on there.