Lex Fridman Podcast cover image

#306 – Oriol Vinyals: Deep Learning and Artificial General Intelligence

Lex Fridman Podcast

00:00

Tokenize Text Text in a Sequence?

Text mayt actually be a good driver to enhance the data, right? So then these connections might be made more easily. And also, i believe there's some new research or way in which you prepare the data. Tocanization is the entry point to make all the data look like a sequence. We break down anything into these puzzle pieces, and then we just model what whats this puzzle look like,. When you make it lay down in a line, so to speak, in a sequence.

Play episode from 37:45
Transcript

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