Fun: trained an SVM on just a single example from each MNIST class. Straight away: 41% accuracy on held-out set.
-
... How many classes? Well if it's 2, you could report 59% accuracy and not be wrong, so...
-
-
So is it an ensemble of 2-class SVMs or is there some newer novel way of training a single SVM on > 2 classes nowadays?
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.