Hacker News new | ask | show | jobs
by cglace 3725 days ago
Using all inputs and 6 layers of varying sizes. After about 500 iterations. http://i.imgur.com/x1MOpvl.jpg
1 comments
visarga 3724 days ago
Just 100 iterations, learning rate 0.03, activation tanh, regularization L2, rate 0.01. The network is 8,8,8 neurons per layer.
link