Mainly RNNs are much slower to train than transformers. | Hacker News

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

		ma2rten on July 25, 2019 \| parent \| context \| favorite \| on: An Introduction to Recurrent Neural Networks Mainly RNNs are much slower to train than transformers.

_pd19 on July 25, 2019 [–]

As well as stability issues, long range dependencies, etc..

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