> 2. You usually flatten right before the final layers. The newer trend appears ... | Hacker News

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

		Aeolos on Jan 30, 2017 \| parent \| context \| favorite \| on: Outrageously Large Neural Networks: The Sparsely-G... > 2. You usually flatten right before the final layers. The newer trend appears to be fully-convolutional networks even for classification, since they appear to overfit less, compared to flattening+dropout.

deepnotderp on Jan 30, 2017 [–]

Yup, but he asked me about where to use flatten, not whether to use flatten. But you're right, fully convolutional is the way to go in classification.

Consider applying for YC's Winter 2026 batch! Applications are open till Nov 10
Guidelines | FAQ | Lists | API | Security | Legal | Apply to YC | Contact