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

Is this approach provably guaranteed to come up with an accurate solution?


You can come up with a probablistic notion of accuracy, but I'm not sure proving guaranteed accuracy on a deep ANN is possible even in principle. Am I misunderstanding the question?




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

Search: