News for hackers. Stuff that matters.
Re:Improving Deep Learning Performance with AutoAugment by nafizh on Tuesday June 19, 2018 @06:22PM (#17350765)
Don't exactly remember the paper, but many of the claims in the paper you mentioned were seemed to be proven false. As such, augmentation like this should, if any, reduce overfitting.
Re:Improving Deep Learning Performance with AutoAugment by mlthoughts2018 on Tuesday June 19, 2018 @10:13PM (#17352017)
Could you provide a link to where the Bengio paper was “disproven”?

I would be quite surprised to learn that, especially for the experimental result they have with the low-pass Fourier filter on the training set, and also because the Bengio paper is quite recent.

Re:Improving Deep Learning Performance with AutoAugment by jjn2009 on Tuesday June 19, 2018 @07:13PM (#17351047)
I agree, as long as you do out of sample testing correctly then using this as a benchmark for finding the correct transformations to perform should reduce overfitting.

That said I can see how if done incorrectly you could easily end up overfitting instead.