Arguably, intelligence is not about learning the latent manifold of some data, it is about taking control of the process that generated it
The properties of modeling and the properties of generation need not be aligned.
-
-
I agree. But I tend to think of it in terms of GANs. In a NN can model P(x), a generator can sample from similar if not exact distribution.
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.