Encounter this a lot (everyday) in biological data -- each sample/entity is different in a different way, so becomes hard to learn (not sure that's what you mean here by hardness).
Come to poster at generalization workshop today 5-6pm by @BeidiChen @animesh_garg @Anshumali_ carried out at @nvidiaai on role of angles in measuring hardness of examples for #deeplearning it correlates well with how humans perceive hard examplespic.twitter.com/EyOuJqShCs
-
-
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.