
Episode 15: Martín Arjovsky, INRIA, on benchmarks for robustness and geometric information theory
Generally Intelligent
How to Make a Machine Learning Machine
"It was kind of it for these part of historys. And then i started going into calsality and things like this, because i was very annoyed at the fact that nora nedwords didn't really work that well when they blow id out of distribution," she says. "After that, just because ia on the verge of burnging out, first. The second i felt like i knew quite a bit about the gun problem that i was interested in, and i was like, ok, maybe it's time for a switch."
00:00
Transcript
Play full episode
Remember Everything You Learn from Podcasts
Save insights instantly, chat with episodes, and build lasting knowledge - all powered by AI.