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

There's a corollary I use with respect to ML

  You don't need math to train good models.
  You do need math to know why your models are wrong.


If you have any other favorite snarky tidbits I'd love to hear them. Do you blog?




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

Search: