New working notes: "Reduced MNIST: how well can machines learn from small data?" http://cognitivemedium.com/rmnist
-
-
i was wondering the same... the next step in accuracy for RMNIST might be training some kind of RL agent that has access to a brush with a random width, or can produce images via something like sketchrnn
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.