BI 171 Mike Frank: Early Language and Cognition
Brain Inspired
The Predictive Aspect of Large Language Models
You're on a recent review from the Dan Yaman's group, I believe in PNAS about that. And so you mentioned Federenko, she's also been on the podcast and we talked about her results and others that have correlated the predictive aspect of large language models to the predictive, next word prediction of our brains. So as a scientific strategy then, it was to understand commonalities and differences between models and use that as a basis for inference. That's very exciting. You can get some pretty good neural predefivity from unsupervised visual learning models.
00:00
Transcript
Play full episode
Remember Everything You Learn from Podcasts
Save insights instantly, chat with episodes, and build lasting knowledge - all powered by AI.
