Hypothesis (& one I’m pretty sure is true): adversarial examples will be a permanent problem in deep learning/ML. They exist because these systems do not have an underlying model that corresponds to their behavior.https://twitter.com/catherineols/status/1020458649825636352 …
-
-
Sure. By the simulation theorem, it can only be a partial model of the world. And I like the predictive brain stuff. But this doesn’t seem to bear on the adversarial examples question?
-
It is pretty clear that our mental model of the world is not a replica of the evolving state vector of the universe :)
- 1 more reply
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.