The Robot Brains Podcast cover image

Ilya Sutskever explains the origins of deep learning

The Robot Brains Podcast

00:00

Neural Nets

neural nets can do whatever you want. You can personalize them in arbitrary ways. So almost anything is possible. And it seems implausible that the neural netwooks of the future will not have both vision and language, he says. But i think the robustness point is specially important in his eyes.

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