The Robot Brains Podcast cover image

Raluca Ada Popa: how to train AI and keep your data confidential

The Robot Brains Podcast

00:00

The Differential Privacy Aspect of Neural Networks

Hospitals would have to had agreed with that procedure. There's simple policies you can they can set and say, once the training is done, the result can be sent to Peter. But of course, the model itself could still remember some information about the data. And we've seen cases where models remember too much.

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