News for hackers. Stuff that matters.

A comment on A Year in Computer Vision. Parent comment

Re:A Year in Computer Vision by hacker_9 on Monday November 27, 2017 @03:27AM (#15785697)
What? They do explain their results, and as you can see from the references section of any paper, other researchers read the published research and then build their new models using that information and continually refining the process.
[ Parent | on HN ]
Re:A Year in Computer Vision by reiinakano on Monday November 27, 2017 @03:49AM (#15785798)
Sure, they do their best to give an explanation after discovering it works, but nobody ever publishes the hundred other models they tried that don't work out.
[ Parent | on HN ]
Re:A Year in Computer Vision by _lpa_ on Monday November 27, 2017 @07:15AM (#15786733)
This is a problem in most areas of scientific research. There is no incentive to publish negative results, so no one does.
[ Parent | on HN ]
Re:A Year in Computer Vision by amelius on Monday November 27, 2017 @03:35AM (#15785737)
Yes, they explain it, but in a very hand-wavey way.
[ Parent | on HN ]