Any reason why you didn’t implement expected improvement? Is UCB definitely better?
Reminder: if you are doing hyperparameter tuning for Keras models, you should check out Keras Tuner. Latest addition: a Bayesian tunerhttps://github.com/keras-team/keras-tuner …
-
-
Thanks. Twitter will use this to make your timeline better. UndoUndo
-
-
-
Very interesting! Do you already have docu or sample code for the bayesian tuner? I couldn't find it on github. Cheers!
Thanks. Twitter will use this to make your timeline better. UndoUndo
-
-
-
Awesome
.Thanks. Twitter will use this to make your timeline better. UndoUndo
-
-
-
Interesting! This is the first time I come across it. Does http://tuner.search support data generation?
Thanks. Twitter will use this to make your timeline better. UndoUndo
-
-
-
Thanks. Twitter will use this to make your timeline better. UndoUndo
-
-
-
Is this related with one talk in google next about Bayesian optimization for deep learning architecture search and parameter tuning?
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.