News for hackers. Stuff that matters.
Re:Using Neural Networks to Evaluate Handwritten Mathematica... by zodiac on Monday May 30, 2016 @11:33AM (#11801762)
I'm very surprised that this worked with the small amount of training data he provided! (he "provided the algorithm ten images containing hand written digits..." - if we generously estimate that each image has 10 training images, that's only 100 training examples)
Re:Using Neural Networks to Evaluate Handwritten Mathematica... by wforfang on Monday May 30, 2016 @12:05PM (#11801908)
Author here: I'm equally surprised it worked so well with such little training data. Each image contained 1 example of each character (18 total characters * 10 images = 180 examples). Having said that, I don't think it would generalize well to other people's handwriting until I provided a (lot) more training data.
Re:Using Neural Networks to Evaluate Handwritten Mathematica... by zodiac on Monday May 30, 2016 @01:33PM (#11802264)
Did you use any regularization? Did you train until the training accuracy converged?

I feel like the network has enough capacity to overfit 180 training samples

Re:Using Neural Networks to Evaluate Handwritten Mathematica... by wforfang on Monday May 30, 2016 @01:54PM (#11802326)
I experimented with a few regularization factors and ultimately settled on a lambda of 0.1. Rather than using a stopping criteria, I ran a fixed number of training iterations (~100) and just eyeballed the cost function results. Since my total training time was fairly brief (~2 minutes, tops), I had the luxury of designing the ANN somewhat heuristically.