AI-powered
podcast player
Listen to all your favourite podcasts with AI-powered features
2min chapter
ICLR 2020: Yann LeCun and Energy-Based Models
Machine Learning Street Talk (MLST)
Is Cropping a Good Data Augmentation?
In the augmented data paper, they show that lik cropping works really well as a data augmentation. So you think that when you take the crops and then put them through the stame in coter that had just incoted the original data space, that the distance between the original data and the cropped image is closer than rotating all the images. I guess what i'm trying to get at is, like, so it's the key to designing a good augmentation for contrastive learning, to just throw it off a little bit. He could be something about the oteter dimensionality, how structured it is, the fact that there are just so many more pixls than there are
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