News for hackers. Stuff that matters.

A comment on Deep learning outperformed dermatologists in melanoma image classification task. Parent comment

Re:Deep learning outperformed dermatologists in melanoma ima... by mehrdadn on Tuesday April 30, 2019 @02:43PM (#19790709)
> Most papers are false and a lot of them should never have passed review.

Do you mean this literally or is this a metaphor to illustrate the point? If you actually mean most papers are false it'd be nice to see a link on that!

[ Parent | on HN ]
Re:Deep learning outperformed dermatologists in melanoma ima... by michaelhoffman on Tuesday April 30, 2019 @02:46PM (#19790731)
John Ioannidis claims that "most published research is false" based on some rather dubious assumptions.

https://www.annualreviews.org/doi/abs/10.1146/annurev-statis...

[ Parent | on HN ]
Re:Deep learning outperformed dermatologists in melanoma ima... by DataWorker on Tuesday April 30, 2019 @04:47PM (#19791783)
I agree with him although the accuracy of that statement is partially based on how “published research” is defined. Operational definitions and measurement are themselves much of the problem.
[ Parent | on HN ]