The Jim Rutt Show cover image

EP 192 David Krakauer on Science, Complexity and AI

The Jim Rutt Show

CHAPTER

The History of Neural Nets

The history of neural nets, which lead to the world you're describing, were actually about deduction. And trying to understand how a brain might reason propositionally. Now they're using ridiculous stuff like ReLU, right? Because it's easily calculatable in a GPU that has got nothing to do with biological realism. Yet, yet somehow when you stack them up, they can do magical stuff.

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