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 the Triplet Loss the Same as the Deep Face?
Deep face was the first paper that i was aware of that did something like this. It used the siamese network architecture. The challenge is negative mining strategy, because you want to come up with examples contrastof examples of things that are different. And if you think about it, there are just too many possible combinations. But you can always make these ncoters part of your energy function. So your energy function would actually become all of the blue and red stuff together. That's how you basically reform mulate.
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