Backprop as Functor: A compositional perspective on supervised learning · HackerPapers discussions

Backprop as Functor: A compositional perspective on supervised learning — mentioned by tsmithe

Mon, 05 Apr 2021 18:42:41 GMT

In fact, the compositional structure underlying that of predictive coding [0,1] is abstractly the same as that underlying backprop [2]. (Disclaimer: [0,1] are my own papers; I'm working on a more precise and extensive version of [1] right now!) [0] https://arxiv.org/abs/2006.01631 [1] https://arxiv.org/abs/2101.10483 [2] https://arxiv.org/abs/1711.10455

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

Backprop as Functor: A compositional perspective on supervised learning — mentioned by joker3

Thu, 12 Sep 2019 18:21:54 GMT

Backprop as functor (https://arxiv.org/abs/1711.10455) is a paper that explores similar ideas.

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

Backprop as Functor: A compositional perspective on supervised learning — mentioned by formalsystem

Fri, 19 Apr 2019 21:58:11 GMT

You may be interested in this paper too https://arxiv.org/abs/1711.10455 I think given a language with AD you already don't need to have a separate language for graph building and my understanding is that's one of the goals for the Julia team and I've seen other nice looking packages for AD in other languages * https://fluxml.ai/2019/02/07/what-is-differentiable-programm... * http://diffsharp.github.io/DiffSharp/examples-inversekinemat... I'm also very excited about being able to design neural nets using ideas from functional programming. I love the Keras API but I don't think it's going to…

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

Backprop as Functor: A compositional perspective on supervised learning — HN submission

Wed, 12 Dec 2018 23:16:50 GMT

Backprop as Functor: A compositional perspective on supervised learning [pdf]

2 points; 0 discussion replies on HN. Paper and source history. A submission is not an endorsement.

Backprop as Functor: A compositional perspective on supervised learning — mentioned by danharaj

Mon, 26 Mar 2018 14:01:02 GMT

David Spivak has done lots of cool work on applying category theory to many concrete systems like databases [1]. Brendan Fong has worked on applying category theory to things that act like interconnected networks, such as electrical circuits. This fits into a larger ambitious program that John Baez is part of to use category theory to understand physical systems that are still much too complicated to understand with current mathematical tools, such as ecosystems. Fong's thesis is on my reading list [2]. The two authors are doing great research, like this investigation of the algebra of…

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

Backprop as Functor: A compositional perspective on supervised learning — mentioned by f00_

Wed, 21 Feb 2018 19:56:28 GMT

After reading "Backprop as Functor: A compositional perspective on supervised learning", it came to my attention that the spaCy backend (thinc) is built with higher order functions instead of a computational graph (unlike tensorflow, chainer, or pytorch) https://github.com/explosion/thinc#no-computational-graph--j... https://arxiv.org/abs/1711.10455 Could someone give me some more detail?

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

Backprop as Functor: A compositional perspective on supervised learning — mentioned by danharaj

Fri, 16 Feb 2018 23:18:34 GMT

https://arxiv.org/abs/1711.10455

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