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)
I'm a Bit Confused With Bert, Because It Has Two Objectives.
Bert has two objectives. The first one is to mask out some random words, and then i want you to reconstruct it. And the next thing is the next sentence prediction, which is completely different. That's not an auto acode. So you're switching between those two tasks dynamically. Wouldn't those two tasks build a completely different manifold internally? Maybe the next sentence Prediction task grabs all these intermediate tokens ad pushes them all up together in a way. I'm not sure, but maybe it's about forming. If i get to grab a whole bunch of points and move them together, maybe that helps. Then its moving individually, that mixi sasii thinkfee the analogy is
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