Why do deep neural networks generalize so poorly to small image transformations? | Hacker News

Hacker News new | past | comments | ask | show | jobs | submit

login

		Why do deep neural networks generalize so poorly to small image transformations? (arxiv.org)
		1 point by ssivark on June 5, 2018 \| hide \| past \| favorite \| 1 comment

sharemywin on June 5, 2018 [–]

Is there a way to generate these variations and feed them into the network as training data?

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