Generally Intelligent cover image

Episode 20: Hattie Zhou, Mila, on supermasks, iterative learning, and fortuitous forgetting

Generally Intelligent

CHAPTER

Is the Model Doing Some Kind of Implicit Curriculum Learning While It's Being Trained?

When you train the individual neurons, learn to specialize to something. Is there any way to see inside what the model is doing? One of the first talks that ever attended on AI research talk was actually with Jason Yusinski who worked on the deep-vis toolbox. I would just blow away by that. This is so cool.

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.
App store bannerPlay store banner