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

  > It is interesting that things still train even when various parts are pretty wrong — as long as the sign is right most of the time, progress is often made.
https://forums.fast.ai/t/how-to-do-reproducible-models-and-u...


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

Search: