2min chapter

Machine Learning Street Talk (MLST) cover image

061: Interpolation, Extrapolation and Linearisation (Prof. Yann LeCun, Dr. Randall Balestriero)

Machine Learning Street Talk (MLST)

CHAPTER

The Challenges of Deep Learning Models

The two key challenges in machine learning are, one, the curse of dimensionality, and, as a corollary of that, knowing what to ignore. What happens when you extrapla outside of the train data? And why does this notion of extrapolation even matter? A lot of human crafted domain knowledge goes into these models.

00:00

Get the Snipd
podcast app

Unlock the knowledge in podcasts with the podcast player of the future.
App store bannerPlay store banner

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

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