AI-powered
podcast player
Listen to all your favourite podcasts with AI-powered features
2min chapter
061: Interpolation, Extrapolation and Linearisation (Prof. Yann LeCun, Dr. Randall Balestriero)
Machine Learning Street Talk (MLST)
Is There a Difference in a 16 by 16 Patch for Mnist?
Mnis goes much more quickly to extra poration regime, a fixed dimensionality in pixer space. If we are looking at emnist, but with two 24 by two 24, a special dimension, then you will not have this a differe any more. And it might even reverse. Even though it the same dimension for both, it does not represent the same proportion of image that is present within that partner. It's funny, because we had the opposite intuition. So figure four. You're showing then, on mnist, that more of the variance is explained with fewer of the princis components on on mnis. As you say, as us, those pictures on
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