Papers of the day   All papers

A Differentiable Programming System to Bridge Machine Learning and Scientific Computing

Comments

michael_nielsen: I hope this is part of a trend exploring more and more in this direction. As @karpathy said, "gradient descent is a better programmer than you": https://arxiv.org/abs/1907.07587 https://t.co/FhxtH9YUe2

6 replies, 429 likes


Chris Rackauckas: #julialang is enabling scientific machine learning. Take at a the paper submitted to NeurIPS, which showcases quantum machine learning and neural stochastic differential equation (neural SDE) as applications. Many talks at #juliacon will explore this idea https://arxiv.org/pdf/1907.07587.pdf

3 replies, 62 likes


Donald Fischer: "Differentiable Programming (∂P) has the potential to be the lingua franca to unite scientific computing and machine learning. [...] Our ∂P system extends @JuliaLanguage with differentiable programming capabilities."

0 replies, 15 likes


Roger Luo 罗秀哲: Zygote paper is out with a VQE demo made with Yao! I'm looking forward to the talk. Nice work @MikeJInnes https://arxiv.org/abs/1907.07587

0 replies, 6 likes


Hacker News: ∂P: A Differentiable Programming System to Bridge ML and Scientific Computing https://arxiv.org/abs/1907.07587

1 replies, 6 likes


Hacker News 250: ∂P: A Differentiable Programming System to Bridge ML and Scientific Computing https://arxiv.org/abs/1907.07587 (http://news.ycombinator.com/item?id=20477873)

0 replies, 3 likes


Simon: If I hooked anyone with my @curry_on_conf talk (https://youtu.be/DCs0_T9BRp0) here is a great further read: https://arxiv.org/pdf/1907.07587.pdf It explains all the interesting bits I couldn't dive into! (How ML, Scientific Computing and AD all come together in #JuliaLang )

0 replies, 3 likes


Amir Saffari: A Differentiable Programming System to Bridge Machine Learning and Scientific Computing by Mike Innes, Alan Edelman, Keno Fischer, Chris Rackauckas, Elliot Saba, Viral B Shah, Will Tebbutt https://arxiv.org/abs/1907.07587

0 replies, 2 likes


Syoyo Fujita 🌸 RayWa(Ray and Peace): Ultra super cooooooooooooooooool!!!! 😍🤩🙏💪🥰😍🤩🙏💪🥰😍🤩🙏💪🥰😍🤩🙏💪🥰😍> A Differentiable Programming System to Bridge Machine Learning and Scientific Computing https://arxiv.org/abs/1907.07587

0 replies, 2 likes


Brendan Meade: I want to believe (in @JuliaLanguage): https://arxiv.org/abs/1907.07587

0 replies, 1 likes


Medford Group: Cool paper on automatic differentiation for scientific computing in @JuliaLanguage! https://arxiv.org/abs/1907.07587 @johnkitchin

0 replies, 1 likes


Irenes (many): Holy shit. The machines are coming for our job. (Okay, not *quite*. But on first read, it seems like a huge step. We didn't previously know that the field of differentiable programming existed.) https://arxiv.org/pdf/1907.07587.pdf

1 replies, 1 likes


Content

Found on Jul 19 2019 at https://arxiv.org/pdf/1907.07587.pdf

PDF content of a computer science paper: A Differentiable Programming System to Bridge Machine Learning and Scientific Computing