Data Skeptic cover image

Interpretable One Shot Learning

Data Skeptic

00:00

Learning From Text Only Is Not Necessary

Our guest today was su wang, an expert on narrative coherence. He argues that using information a cross wors is necessary because people don't say everything in text. The one mistake i see models make over and over again, even with a common sense knowledge impot," he says. "There'sa interpretable way to learn wor in beints"

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