Step 2:
New steps are shown in green
function [W1, W2] = BackpropXOR(W1,W2,X,D);
alpha=0.9; %learning rate
[R C]=size(X); %Get the number of rows and columns of the input matrix X
%R = number of training trials. C = number of input nodes
%Lets also start a loop which can take each row of the training data and calculates updated weights.for k=1:R %each row is a training trials.
What goes in here? See next step.end; % for k=1:R