TLDR: Meta learning requires unsupervised learning. We model context with structure latent space: as a concatenation of Gaussian and Dirichlet random variables. Learning categories in unsupervised way is critical for generalization. Paper: https://skillsworkshop.ai/uploads/1/2/1/5/121527312/meta-rl.pdf …
-
-
Show this threadThanks. Twitter will use this to make your timeline better. UndoUndo
-
-
-
Just ran into your other poster on implicit competitive regularization in GANS
Thanks. Twitter will use this to make your timeline better. UndoUndo
-
Loading seems to be taking a while.
Twitter may be over capacity or experiencing a momentary hiccup. Try again or visit Twitter Status for more information.