Every once in a while, a paper comes out claiming to get competitive results using only some form of greedy layer-wise training
-
But these papers never provide much evidence or explanations, and seem to take their own claims in strides, unaware of their enormity
For the record, DL works because of joint feature learning. You can't get anywhere close to competitive results without it, in some form
-
-
If you claim otherwise, do explain how your proposal overcomes the information loss problem, and provide overwhelming evidence. Think twice
Thanks. Twitter will use this to make your timeline better. UndoUndo
-
-
-
Remember the "SARM" paper that you called out? Gotta admit, that takes confidence, turned out you were right!
Thanks. Twitter will use this to make your timeline better. UndoUndo
-
-
-
While I'm on board with this, the brain appears to train locally. Not unjustified to explore, as long as claims are sensible
Thanks. Twitter will use this to make your timeline better. UndoUndo
-
-
-
could you explain more about "joint"? I mean I get your point of representation learning, but I am not sure about joint learning here
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.