News for hackers. Stuff that matters.
Re:Intel Prepares to Graft Google’s Bfloat16 onto Processors by blipblap on Sunday July 21, 2019 @12:36AM (#20489963)
Is there a principled way to not overfit? Or is the best we can do not overtraining or reducing the precision of the calculations?
Re:Intel Prepares to Graft Google’s Bfloat16 onto Processors by nabla9 on Sunday July 21, 2019 @08:23AM (#20491035)
regularization, dropout, early stopping etc.