Implemented NOR function

logistic_regression/lab2_lr_ex3a.m

@@ -8,7 +8,6 @@
 % after normalising we add the bias
 %X=[ones(size(X,1),1),X];
 
-X=[ones(size(X,1),1),X,X(:,1).*X(:,2),X(:,1).^2,X(:,2).^2];
 theta=ones(1,size(X,2));
 
 % for question 7, modify the dataset X to have more features (in each row)
@@ -18,6 +17,7 @@ theta=ones(1,size(X,2));
 	% here append x_2 * x_2 (remember that x_1 is the bias)
 
 	% here append x_3 * x_3 (remember that x_1 is the bias)
+X=[ones(size(X,1),1),X,X(:,1).*X(:,2),X(:,1).^2,X(:,2).^2];
 
 % initialise theta
 alpha = 0.05;

neural_networks/NeuralNetwork.m

@@ -86,9 +86,9 @@ classdef NeuralNetwork < handle
                         test_errors=[test_errors, NeuralNetwork.get_error(test_set_input,test_set_output,nn)];
                     end
                 end
-                %if mod(i , 10) == 0
-                %    display([ 'cost = ',num2str(error)])
-                %end
+                if mod(i , 10) == 0
+                    display([ 'cost = ',num2str(error)])
+                end
                 if exist('is_iris')
                     if is_iris
                         if mod(i, 100) == 0

neural_networks/xorExample.m

@@ -7,13 +7,13 @@ training_set_input = [
 ];
 
 training_set_output = [
+    1;
     0;
-    1;
-    1;
-    0
+    0;
+    1
 ];
 
-[errors,nn,training_errors,test_errors] = NeuralNetwork.train(training_set_input,training_set_output,2,10000,1.0);
+[errors,nn,training_errors,test_errors] = NeuralNetwork.train(training_set_input,training_set_output,2,10000, 7.0);
 NeuralNetwork.test_xor(training_set_input,training_set_output,nn);
 figure()
 plot(errors)