Looks like Geoff finally got his capsules to work 
https://nips.cc/Conferences/2017/Schedule?showEvent=9167 …
-
I don't think it's fine to only list experiments on toy datasets, and hide failures on more complicated cases.
As a scientist, you want to communicate as truthfully as possible what your algo does and doesn't do. Failures are interesting data points
-
-
I actually read their paper today. They do report (not so great) results on other datasets. IMO doesn't make it less valuable.
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.