Re:Lessons from Optics, the Other Deep Learning
by vog on Monday February 12, 2018 @11:51AM
(#16359864)
As funny as this may sound, there's some deep value in this: We deeply need more incentives in the academic world to report non-findings like that. We have a strong publication bias towards positive results, which has already become a huge problem. Moreover, we should have a much stronger focus on repeatability of experiments.
[ Parent
| on HN ]
Re:Lessons from Optics, the Other Deep Learning
by jimbokun on Monday February 12, 2018 @07:07PM
(#16363603)
And maybe this is exactly the trick, make it low key and have a sense of humor about it.
Sounds like a site dedicate to "My Ass" results would be extremely popular with grad students and real world researchers. Being able to know "it's not just me" and maybe even avoid some of the stumbling blocks others have run into, or to not just blindly use some approach that happened to work for one experiment, but seems to fail for many others.
Re:Lessons from Optics, the Other Deep Learning
by vog on Tuesday February 13, 2018 @03:28AM
(#16365589)
> And maybe this is exactly the trick, make it low key and have a sense of humor about it.
I agree in general, but I'd also love to see those published as actual beautiful papers, not just ugly formatted websites. (Okay, the website in case isn't that bad. At least it's clearly structured and readable.)
These would be mostly short papers, for sure. But there could be a separate section in the journals for them - just like the "outtakes" section at the end of a movie.
Re:Lessons from Optics, the Other Deep Learning
by nurettin on Monday February 12, 2018 @11:41PM
(#16364815)
This particular non-finding is mainly about a possible error in tensorflow contrib package, which the author self-admittedly wasn't arsed enough to research into. Probably because of time concerns?