thanks a lot!
-
-
Thanks. Twitter will use this to make your timeline better. UndoUndo
-
-
-
thoughts on how small we can go on training data & still get good (90+) results?
-
depends on the problem. With very simple problems (MNIST) you can go down to ~100 samples (10 per class)
End of conversation
New conversation -
-
-
Would you allow me publish a french translation of your article ? Best regards.
-
That's fine, as long as you include proper credit attribution and links to the original
- 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.