AI-powered
podcast player
Listen to all your favourite podcasts with AI-powered features
1min chapter
061: Interpolation, Extrapolation and Linearisation (Prof. Yann LeCun, Dr. Randall Balestriero)
Machine Learning Street Talk (MLST)
A New Approach to Neural Networks - Randall's Other Recent Work
Neural networks can be entirely rewritten as compositions of linear functions arranged in polyhedra or cells in the input space. Its high resolution sliceendice into linear forms like a fruit ninge set loose on a marching cubes algaritm such as c means clustering, matched filter banks and vector quantitiation. If that doesn't shed light on francois chelet's characterization of neural networks as locally sensitive hash tables then i don't know what will.
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