Conferences - Seminars
Self-supervised learning: could machines learn like humans?
By Yann LeCun, VP & Chief AI Scientist, Facebook
Yann LeCun sees self-supervised learning as a potential solution for problems in reinforcement learning, as it has the advantage of taking both input and output as part of a complete system, making it effective for example in image completing, image transferring, time sequence data prediction, etc. While the model’s complexity increases with the addition of feedback information, self-supervised learning models significantly reduce human involvement in the process.
The conference will be available to watch on the EPFL Facebook page with Facebook Live.
Organization EPFL Presidency and APEL (Association des professeurs de l'EPFL)
Accessibility General public