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)
The Self Supervised Learning Tasks
Self supervised learning doesn't help with the sample efficiency problem. It just means that some one else does it foryo. I think there are so many different areas of research that you can then pull apart, and its transfer learning. This is going to be a talk about energy base models. To me, it looks more like transfer learning from another thing. Ye, i think i that is self supervised. Ands you need a way of scheduling these tasks. Now it's curriculum learning. Oh, and then you have all these tasks. And now it's multi task learning. But don’t forget any of those tasks,. Now it's continual learning.
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