AI-powered
podcast player
Listen to all your favourite podcasts with AI-powered features
5min chapter
#71 - ZAK JOST (Graph Neural Networks + Geometric DL) [UNPLUGGED]
Machine Learning Street Talk (MLST)
Using the Convolution Theorem and Apon Transformation
Going bottom up can give you a surprising degree of global coherence and information. So why does it work so well, going bottom up? There's a paper that i read a long time ago, back when i was in the world of physics,. And his name is william bali, i probably missed pronouncing. He showed how most systems, an their complicated behaviour, can be explained by parawise interactions. It seems to me like a message passing in tes, which essentially are parwise interactions. You can capture quite a lot of information that models a system with just that. But there are some cases, so there are blind spots. This is related to the bottle neck
00:00
Transcript
Episode notes
Get the Snipd
podcast app
Unlock the knowledge in podcasts with the podcast player of the future.
AI-powered
Discover
highlights
Listen to the best highlights from the podcasts you love and dive into the full episode
Save any
moment
Hear something you like? Tap your headphones to save it with AI-generated key takeaways
Share
& Export
Send highlights to Twitter, WhatsApp or export them to Notion, Readwise & more
AI-powered
podcast player
Listen to all your favourite podcasts with AI-powered features
Discover
highlights
Listen to the best highlights from the podcasts you love and dive into the full episode