Yeah, It is the interesting part. Because with sufficiently large inputs (even f... | Hacker News

Hacker Newsnew | past | comments | ask | show | jobs | submit

		ivanca on Nov 2, 2014 \| parent \| context \| favorite \| on: The Flaw Lurking in Every Deep Neural Net Yeah, It is the interesting part. Because with sufficiently large inputs (even from different sources) the networks are going to be looking for the same patterns.

streptomycin on Nov 2, 2014 [–]

But why would different structures of networks fit to different data result in exactly the same type of "overfitting"?

Guidelines | FAQ | Lists | API | Security | Legal | Apply to YC | Contact