Hands-On Neural Network Programming with C#

Forward propagation

The following is our code for a basic forward propagation process:

private void ForwardPropagate(params double[] inputs){  var i = 0;  InputLayer?.ForEach(a =>a.Value = inputs[i++]);  HiddenLayers?.ForEach(a =>a.ForEach(b =>b.CalculateValue()));  OutputLayer?.ForEach(a =>a.CalculateValue());}

To do ForwardPropagation, we basically sum all the inputs from each synapse and run the result through our Sigmoid function to get an output. The CalculateValue function does this for us.