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

Yeah, it's straightforward to reproduce the results of the paper whose conclusion they criticize, "Understanding deep learning requires rethinking generalization", without any (explicit) regularization or anything else that can be easily described as a "soft preference for simpler solutions".



Join us for AI Startup School this June 16-17 in San Francisco!

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

Search: