News for hackers. Stuff that matters.
Re:Show HN: Neural Network Visualizer Classifying Handwritin... by scotty79 on Tuesday May 17, 2016 @03:34PM (#11716613)
> Most networks gained a large percentage of their final accuracy in just one epoch. And it usually was the case that a higher accuracy in the first epoch meant a higher final accuracy.

This sounds to me like learning was just crawling to local optimum not actually exploring or making any breakthrough in understanding of the domain.

There are no comments on this comment yet.