If they are building an algorithm which overfits to training data, their algorit... | Hacker News

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

login

squigs25 on June 4, 2015 | parent | context | favorite | on: Computer Scientists Are Astir After Baidu Team Is ...

If they are building an algorithm which overfits to training data, their algorithm will lose performance on in the actual validation test.

It is NOT like looking at leaked answers. It's like re-reading the textbook more than everyone else. Definitely an unfair advantage however.

varelse on June 4, 2015 [–]

You misunderstand. They're using repeated attempts on the test set to improve their network. That is equivalent to training on the test set and that is unequivocably cheating.

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