The Principles of Deep Learning Theory · HackerPapers discussions

The Principles of Deep Learning Theory — HN submission

Mon, 23 Feb 2026 03:27:47 GMT

The Principles of Deep Learning Theory (2021)

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

The Principles of Deep Learning Theory — mentioned by adamnemecek

Mon, 27 Nov 2023 22:01:48 GMT

There is some yeah, there is a recent book on deep learning via renormalization https://arxiv.org/pdf/2106.10165.pdf. I have a discord https://discord.cofunctional.ai

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

The Principles of Deep Learning Theory — mentioned by quantum_mcts

Tue, 31 Jan 2023 20:32:37 GMT

"The Principles of Deep Learning" paper https://arxiv.org/abs/2106.10165 has a rather rigorous (based on Quantum Field Theory (QFT) mathematical apparatus) analysis of modern deep learning with the similar insight. They suggest that the learning happens in the critical regimes. And use running couplings, renormalization group and other fancy OFT math to derive some insights in the DL field. Here's a HN thread, by the way, https://news.ycombinator.com/item?id=31051540.

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

The Principles of Deep Learning Theory — mentioned by ly3xqhl8g9

Mon, 09 Jan 2023 19:57:41 GMT

Not sure if foundational (quite a tall order in such a fast-moving field), but for sure a nice introduction into neural networks, and even mathematics in general (for a teenager, because it's nice to see numbers in action beyond school-level algebra): → Harrison Kinsley, Daniel Kukiela, Neural Networks from Scratch, https://nnfs.io, https://www.youtube.com/watch?v=Wo5dMEP_BbI&list=PLQVvvaa0Qu... Somewhat foundational, if not in actuality, then in the intention to actually build a theory as in theory of gravitation, although not necessarily an introductory text: → Daniel A. Roberts, Sho Yaida…

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

The Principles of Deep Learning Theory — HN submission

Sat, 16 Apr 2022 11:41:04 GMT

The Principles of Deep Learning Theory

221 points; 139 discussion replies on HN. Paper and source history. A submission is not an endorsement.

The Principles of Deep Learning Theory — mentioned by mdp2021

Mon, 11 Apr 2022 16:19:41 GMT

Thank you alok-g, I would just correct the links: -- article: https://arxiv.org/abs/2106.10165 -- book: https://arxiv.org/pdf/2106.10165 -- your summary: https://news.ycombinator.com/item?id=27564506 (the link to the post is that "under" the date. You posted two identical links here)

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

The Principles of Deep Learning Theory — mentioned by r-zip

Tue, 12 Oct 2021 14:01:09 GMT

I'd recommend anyone interested in the NTK and its limitations to check out Greg Yang's work [1] and the recent book by Roberts, Yaida, and Hanin [2]. There's clearly a lot more work to be done on neural network scaling limits; the NTK is overly simplistic (though useful). 1: https://www.microsoft.com/en-us/research/people/gregyang/ 2: https://arxiv.org/abs/2106.10165

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

The Principles of Deep Learning Theory — HN submission

Tue, 10 Aug 2021 13:45:52 GMT

The Principles of Deep Learning Theory

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

The Principles of Deep Learning Theory — HN submission

Thu, 22 Jul 2021 01:56:09 GMT

The Principles of Deep Learning Theory

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

The Principles of Deep Learning Theory — mentioned by belter

Mon, 21 Jun 2021 11:01:27 GMT

https://arxiv.org/pdf/2106.10165.pdf

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

The Principles of Deep Learning Theory — HN submission

Mon, 21 Jun 2021 11:01:27 GMT

The Principles of Deep Learning Theory

4 points; 3 discussion replies on HN. Paper and source history. A submission is not an endorsement.