TalkRL: The Reinforcement Learning Podcast cover image

Aravind Srinivas 2

TalkRL: The Reinforcement Learning Podcast

00:00

Using Pre-Trained Self-Supervised Representations in Deep Learning?

It's difficult to not take advantage of self-supervised learning anywhere right now in deep learning. So just like that, I'm also leveraging that for my current research. CLIP you can consider the system's kind of like giant self-super supervised contrast learning done on like internet-scale data.

Transcript
Play full episode

The AI-powered Podcast Player

Save insights by tapping your headphones, chat with episodes, discover the best highlights - and more!
App store bannerPlay store banner
Get the app