2min chapter

Machine Learning Street Talk (MLST) cover image

ICLR 2020: Yoshua Bengio and the Nature of Consciousness

Machine Learning Street Talk (MLST)

CHAPTER

The Training Distribution for Computer Vision Data Is Combinatorly Large

The training distribution for any computer vision datus is combinatorly large. You would never, ever have anything that even approaches the representative side of the distribution. But it is hard to come up with an image that has a zero probability under my training distribution. I don't see what's so special about having things having zero ability under the training distribution.

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