AI-powered
podcast player
Listen to all your favourite podcasts with AI-powered features
2min chapter
MLST #78 - Prof. NOAM CHOMSKY (Special Edition)
Machine Learning Street Talk (MLST)
Yani Episode 2 - Lacoon's Architecture
Lacoon introduces these latent variables of abnormalized energy to represent possible futures. It's analogous tebasian styl probablistic graphical models. The main change here is that the models become starcastic over the domain of the latent variable. Lacoon then regularizes the latent to stop formation leaking into the predictions and also to shrink, rap the representation around volumes of high density. He calls it daniel carnaman's style mode - thinking fast and slow.
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