With BPROP training I get 2.3% of errors in MNIST with just 1000 hidden units 2-layers net, no convolution layers. Pretty good AFAIK.
-
-
best it did is 2.26%, then started to overfit. But if you check MNIST official page, 1.4-1.5 seems reached by advanced setups.
Thanks. Twitter will use this to make your timeline better. UndoUndo
-
-
-
Thanks. Twitter will use this to make your timeline better. UndoUndo
-
-
-
p.s. very important: I’m talking about numbers that don’t transform the original data set in any way.
-
this should be the exact same as the setup you describe: https://gist.github.com/fchollet/ac238179b7752d24717368c45a8db2a7 … goes to 1.8-1.7, down to 1.4 when adding dropout.
- Show replies
New conversation -
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.