Maybe a stack of bidirectional LSTMs with attention could read them for me
Deep learning is getting out of control. Out of ~500 ICLR submissions, there over 100 that I should probably read. Definitely won't happen.
-
-
-
you'd also need a neural lace so that the model can interface with and update your brain with what findings that it's read.
End of conversation
New conversation -
-
-
@peteskomoroch Did they write the paper on using deep learning on deep learning papers to generate new deep learning papers yet?Thanks. Twitter will use this to make your timeline better. UndoUndo
-
-
-
There is always the risk that this inflation produces a premature death because of lack of deepening. Too fast success -> fast death
Thanks. Twitter will use this to make your timeline better. UndoUndo
-
-
-
Some people would this call a bubble waiting to burst.
Thanks. Twitter will use this to make your timeline better. UndoUndo
-
-
-
Can you share you recommended papers list?
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.