News for hackers. Stuff that matters.
Re:Known Unknowns by throwawaymath on Sunday July 01, 2018 @01:10PM (#17436421)
> Humans can explain themselves. Many ML systems are not designed to provide any explanation, even poor ones.

In my opinion, the vast majority of self-reported reasons given by humans to explain their behavior are extremely poor, inconsistent and low-fidelity.

There are no comments on this comment yet.