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

I wonder if anyone has tried to approach the problem from the other end: start with the hand-tuned network and randomize just some of the weights (or all of the weights a small amount), and see at what point the learning algorithm can no longer get back to the correct formulation of the problem. Map the boundary between almost-solved and failure to converge, instead of starting from a random point trying to get to almost-solved.



Consider applying for YC's Spring batch! Applications are open till Feb 11.

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

Search: