Y[i,((y[i]-1)%num_labels)] = 1;
y = Y;
# Unroll parameters
nn_params = np.concatenate((Theta1.flatten(),Theta2.flatten()),axis=2)
results5 = [-9.2783e-003,8.8991e-003,-8.3601e-003,7.6281e-003,-6.7480e-003]
J,grad = ANN.costFunction(nn_params, input_layer_size, hidden_layer_size, num_labels, X, y)
print grad[0:5],results5
print grad
#test if the sigmoid grad is working properly
print ANN.sigmoidGrad(0)
print ANN.sigmoidGrad(np.zeros((3,3)))
input_layer_size = 400; # 20x20 Input Images of Digits
hidden_layer_size = 25; # 25 hidden units
num_labels = 10; # 10 labels, from 1 to 10
# (note that we have mapped "0" to label 10)
#load the precalculated weights to check cost function is working
theta1 = np.loadtxt(open("testfiles/Theta1.txt","rb"),delimiter=",")
theta2 = np.loadtxt(open("testfiles/Theta2.txt","rb"),delimiter=",")
X = np.loadtxt(open("testfiles/ann_test_data.txt","rb"),delimiter=",")
y = np.loadtxt(open("testfiles/ann_test_output.txt","rb"),delimiter=",")
m = X.shape[0]
# Add ones to the X data matrix
