... update their probability of being sampled into a uniformly weighted training set for the next round. Does anyone do that?
-
-
-
(This seems appealing as a meta-algorithm because then the underlying algorithm doesn't have to deal with weights, and gets to use a sample)
- 1 more reply
New conversation -
-
-
You may appreciate this idea: http://link.springer.com/chapter/10.1007%2F3-540-31182-3_46 … co-evolving models with training (sub)sets
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.