> These tricks make lightweight and dynamic convolutions several orders of magni... | Hacker News

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

singularity2001 on Feb 26, 2019 | parent | context | favorite | on: Myths in Machine Learning Research

> These tricks make lightweight and dynamic convolutions several orders of magnitude more efficient that standard non-separable convolutions.

Is that backed up by any data?

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