Sigh yeah, devil is in the details...gradient clipping, high initial forget gate bias, orthogonal init is the usual raindance
-
-
awesome. Ok, now I'm feeling excited to compile a training corpus
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.