@fchollet do you find discriminative/generative distinction more useful?
Because in that case, what about supervised learning on synthetic datasets with no human in the loop? Isn't that technically unsupervised?
-
-
-
@davidjayharris Maybe more meaningful. Again, the line b/t the two is blurry (you can train a generative model using a discrimination task)
End of conversation
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.