
Yann LeCun on his Start in Research and Self-Supervised Learning
The Gradient: Perspectives on AI
00:00
Reward Is Enough, Right?
Self-supervised learning is the idea of teaching a machine to predict from another part of its input. Jeff Hinton and I kind of worked on this in the early 1980s, sorry, called joint embedding or JEDI. It seemed to export in vision 2020, so I was thinking we could delve into it. But before that, if you could sort of recap, how would you define self-supervisedlearning?
Transcript
Play full episode