News for hackers. Stuff that matters.
Re:Neural nets more accurate than humans at detecting sexual... by r_singh on Tuesday February 20, 2018 @04:40AM (#16419008)
If the test data does not have a 50/50 split (or something around that ratio), the headline is straight up lies.

Skewed test data is the most common problem with research, reminds me of this great video by Veritasium (Is most published research wrong?): https://www.youtube.com/watch?v=42QuXLucH3Q

There are no comments on this comment yet.