Arguably, intelligence is not about learning the latent manifold of some data, it is about taking control of the process that generated it
-
-
Huh.... Well, what do you know! On a slightly tangen, if generators can generalize to reality, discriminators must always lose in a GAN?
Thanks. Twitter will use this to make your timeline better. UndoUndo
-
-
-
well, reality can be understood as a computational process, and thus a neural network should do...
-
This opens up a bunch of questions on computability. Reality (Copenhagen interpretation) is probabilistic and very difficult to compute.
- 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.