“Universal adversarial perturbations” seems most dramatic ML result in years; if so, not getting deserved attention https://arxiv.org/pdf/1610.08401v1.pdf …
-
-
Well, yes, but the dramatic result is that it’s independent of the image. And apparently similar perturbations work on many networks
-
And, as
@mattskala says, some of the perturbation maps work pretty well across many different architectures:pic.twitter.com/rZKnQu3egf
- 1 more reply
New conversation -
-
-
That's something they test. Somewhat specific, nonspecific enough to be interesting.
- 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.
. Banned in Sweden. SubGenius, Zhuangist, white-hat troll. Defrocked mathematician. Brain problems.