Position: Categorical Deep Learning is an Algebraic Theory of All Architectures · HackerPapers discussions

Position: Categorical Deep Learning is an Algebraic Theory of All Architectures — mentioned by bubblyworld

Sat, 31 Aug 2024 14:10:08 GMT

I was sure this was going to be a case of spraying jargon at investors, but they've actually produced an interesting paper in this direction (in collaboration with some DeepMind people): https://arxiv.org/abs/2402.15332

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

Position: Categorical Deep Learning is an Algebraic Theory of All Architectures — mentioned by taliesinb

Mon, 03 Jun 2024 16:54:37 GMT

Symbolica.ai | London, Australia | REMOTE, INTERNS, VISA We're trying to apply the insights of category theory, dependent type theory, and functional programming to deep learning. How do we best equip neural nets with strong inductive biases from these fields to help them reason in a structured way? Our upcoming ICML paper gives some flavor https://arxiv.org/abs/2402.15332 ; you can also watch https://www.youtube.com/watch?v=rie-9AEhYdY&t=387s ; but there is a lot more to say. If you are fluent in 2 or more of { category theory, Haskell (/Idris/Agda/...), deep learning }, you'll probably have…

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

Position: Categorical Deep Learning is an Algebraic Theory of All Architectures — HN submission

Wed, 10 Apr 2024 01:49:12 GMT

Categorical Deep Learning: An Algebraic Theory of Architectures

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

Position: Categorical Deep Learning is an Algebraic Theory of All Architectures — mentioned by knotthebest

Tue, 09 Apr 2024 21:45:26 GMT

Nothing particularly interesting to my knowledge. You should read this though, some people at Symbolica AI worked on it too: https://www.google.com/url?q=https://arxiv.org/abs/2402.1533...

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