Self-Supervised Learning and Foundation Models

nadermx | karma 1370 | avg karma 2.95 · 2023-02-13 00:25:01

It's nice MIT offers lectures like this and the gilbert strands lectures. Any other ML/Math related lectures recomended?

mdp2021 | karma 6760 | avg karma 1.55 · 2023-02-13 03:29:29

The classic 6.034 of [Classic] Artificial Intelligence from the late Prof. Patrick Winston is "mandatory".

rgabrielsson | karma 17 | avg karma 5.67 · 2023-02-13 07:54:52

One trend I'm seeing: I think the math that is becoming more useful, if huge foundation models are taking over, is around comparing and understanding their embedding/latent spaces. Geometry, topology, optimal transport, alignment -- in favor of statistics and probability theory

aliqot | karma 4118 | avg karma 2.84 · 2023-02-13 01:02:33

I preferred the alternative title: "What happens when you pour gasoline on your own bias"

rgabrielsson | karma 17 | avg karma 5.67 · 2023-02-13 07:50:10

haha future will tell! :D