I\'m trying to learn about neural networks and coded a simple, back-propagation, neural network that uses sigmoid activation functions, random weight initialization, and learnin
If you want to consider Neuroevolution, you may check up the neuroevo gem. Run the specs to see it fit XOR in 15 iterations ([2,2,1] feed-forward network, XNES optimizer):
https://github.com/giuse/neuroevo/blob/master/spec/solver_spec.rb
Full disclosure: I'm the developer (hi there!).
I just recently began published my code and am looking for feedback.