my task is to learn simple neural network, input size 1, hidden layer size 8 and output size 1, a function f = {0->1,1->0,2->0,3->1}, but can learn the network to get satisfing result. I am using activation function, backpropagation and initial values in range (-1,1). But I cant get better result in supremum error norm than 0.5, never achieved under 0.5. What can I do wrong, thats only 4 examples to learn, why is so hard to learn that naetwork? 2 years ago I tried to learn XOR in similar way and also had same problem.


Your Answer

By clicking “Post Your Answer”, you agree to our terms of service, privacy policy and cookie policy

Browse other questions tagged or ask your own question.