The Jim Rutt Show cover image

EP 192 David Krakauer on Science, Complexity and AI

The Jim Rutt Show

CHAPTER

How to Use Deep Neural Networks for Parsimonious Science

The way the models work, I would, yes, the answer is no, right? These things are extraordinarily interwoven and ridiculously high dimension and unstructured. Whatever they've developed in terms of basins of attraction around semantics, let's say in the language case, are representationally, at least so far, impossible to extract. The question and other way to put it is within the Lottery Ticket model is their one winning ticket. And can we find it somewhere buried there in those models?Yeah, that was an interesting question. Okay, I would love to have an example of this. Give it Mandelbrot set and see what it comes up with. Well,

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