(no title)
taliesinb | 1 year ago
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 a lot of fun with us!
Check out our open positions at https://jobs.gusto.com/boards/symbolica-ai-67195a74-31b4-405...
_lurker|1 year ago
ligthning|1 year ago
taliesinb|1 year ago
sbrother|1 year ago
Also: I could swear I saw you comment on something Mathematica related a long time ago. Is there a Wolfram connection here?
taliesinb|1 year ago
kibibu|1 year ago
tasuki|1 year ago