Generally Intelligent cover image

Episode 15: Martín Arjovsky, INRIA, on benchmarks for robustness and geometric information theory

Generally Intelligent

00:00

How to Get a 100 Percent Curacy in a Linear Problem?

The reason why this works, and the upwaiting your other data points does not, can be explained when you look at it in the lin case. If all you have is like, ten age cases, and you throw away a million data points,. Youre only wone a be stucged to solve improdems what there can be solved wit 20 data points. The same behavior that we observe also fornedworkson stuff. Like this is kind of like adding more data points than doe t the ones that you already have.

Transcript
Play full episode

The AI-powered Podcast Player

Save insights by tapping your headphones, chat with episodes, discover the best highlights - and more!
App store bannerPlay store banner
Get the app