Theano started around 2007, long before DL got popular or the Imagenet competiti... | Hacker News

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

login

nafizh on April 2, 2021 | parent | context | favorite | on: Why machine learning struggles with causality

Theano started around 2007, long before DL got popular or the Imagenet competition where DL outperformed traditional methods by a long margin.

p1esk on April 2, 2021 [–]

The 2012 Imagenet results which jumpstarted DL did not benefit from Theano or Torch frameworks. Alex Krizhevsky had developed his own GPU accelerated framework (cuda-convnet), and it remained quite popular for a couple of years after the competition, until Theano and Torch caught up with it.

Consider applying for YC's Spring batch! Applications are open till Feb 11.
Guidelines | FAQ | Lists | API | Security | Legal | Apply to YC | Contact