The simple essence of automatic differentiation · HackerPapers discussions

The simple essence of automatic differentiation — mentioned by sriku

Sun, 18 Sep 2022 23:38:18 GMT

https://arxiv.org/abs/1804.00746

Paper and discussion history. A mention is not an endorsement.

The simple essence of automatic differentiation — mentioned by dangirsh

Wed, 16 Dec 2020 05:02:56 GMT

Related: The Simple Essence of Automatic Differentiation - Conal Elliot - https://www.youtube.com/watch?v=ne99laPUxN4 - https://arxiv.org/abs/1804.00746

Paper and discussion history. A mention is not an endorsement.

The simple essence of automatic differentiation — HN submission

Mon, 17 Feb 2020 03:17:00 GMT

The simple essence of automatic differentiation – Conal Elliott (2018)

1 point; 1 discussion reply on HN. Paper and source history. A submission is not an endorsement.

The simple essence of automatic differentiation — mentioned by Myrmornis

Tue, 04 Dec 2018 06:48:28 GMT

> Meanwhile, the idea of ML models fundamentally being differentiable algorithms – often called differentiable programming – has caught on. > We need a language to write differentiable algorithms, and Flux takes Julia to be this language. Recently on HN there was some discussion of this paper by Conal Elliott on automatic differentiation in a pure functional language (Haskell): https://arxiv.org/abs/1804.00746 This is a rather large and vague question but I'm curious whether people have comments on the relative merits of Julia vs a pure functional language for supporting "differentiable…

Paper and discussion history. A mention is not an endorsement.