News for hackers. Stuff that matters.

A comment on Keras reimplementation of "One pixel attack for fooling deep neural networks". Parent comment

Re:Keras reimplementation of "One pixel attack for fooling d... by jgalt212 on Friday February 23, 2018 @08:49PM (#16451144)
not as massive as producing a bum model. And most of the overhead in ML is data acquisition, cleaning, normalization and tagging costs.
[ Parent | on HN ]

There are no comments on this comment yet.