News for hackers. Stuff that matters.

A comment on Deep image prior 'learns' on just one image. Parent comment

Re:Deep image prior 'learns' on just one image by Mahn on Friday December 01, 2017 @08:39AM (#15823701)
> for some reason, the structure of the network means that the estimated output learns realistic features first, and then overfits to the noise afterwords.

Why does this happen? What characteristics does the network structure have that cause this effect?

[ Parent | on HN ]
Re:Deep image prior 'learns' on just one image by CardenB on Friday December 01, 2017 @11:17AM (#15824762)
I think the reason this paper is so interesting is that no one had any idea why this happens
[ Parent | on HN ]