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)
How Cold Can Extrapolate in Any Meaningful Way?
The neuron network is only capable of slicing and dicing the impet space with flat planes. The quickest way to make the neural network fit the data is to effectively linearize the data by applying a non linear transformation before it even gets in. But this idea that you don't need feature engineering and neuran networks, i think, is nonsense. It begs the question, how cold possibly extrapolate in any meaningful way? Riht, especially in the general setting.
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