Re:Artificial intelligence predicts when heart will fail
by AndrewOMartin on Tuesday January 17, 2017 @08:07AM
(#13417106)
I might be referring to a different problem here, but often when ML gets something wrong, it gets it mind-bogglingly wrong.
Taking an extreme cartoon example, where a doctor might think a cancer is a cough, a computer might think the lamp is a patient.
If there is anyone familiar with this kind of data. Please chip in something about the nature of data. It will be helpful in appreciating the difficulty of the problem more.