News for hackers. Stuff that matters.
Re:How TensorFlow outdid itself in handling Overfitting in D... by kuu on Thursday July 18, 2019 @06:53AM (#20468513)
It's interesting to see all the techniques listed but there is no indication about when and how use any of them. Is it better to start by dropout or by regularization? Can I use both? (These are rhetorical questions...)

And as another commenter said, this is not unique from TF.

There are no comments on this comment yet.