Simple Neural Network can't learn XOR

Question

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

Answer 1

I had the same problem and the answer is - use higher values of learning speed. I use the following lSpeed = 12.8 / epoch and about 100 epoches for the NN with phi(x) = x/(1 + |x|)

Possible now your NN learn speed just do not have enough "power" to make the job.