Thanks for the link to this interesting paper. I think we're seeing some recapit... | Hacker News

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

webmaven on July 18, 2017 | parent | context | favorite | on: The Limitations of Deep Learning

Thanks for the link to this interesting paper.

I think we're seeing some recapitulation of those arguments WRT 'ensembles of DL models' approaches.

thundergolfer on July 18, 2017 [–]

I agree. Google has come out with some papers that are, to put it harshly, basic gluing together of DL models followed by loads of training on their compute resources.

webmaven on July 18, 2017 | [–]

Not just Google. The FractalNet paper comes to mind.

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