theta = np.block([t.reshape(t.size, order='F') for t in Theta])
sample_nn = NeuralNetwork(X_s, y_s, Theta, sample_dims)
grads = sample_nn.cost_grad(theta)
n_grads = sample_nn.cost_grad_numerical(theta)
print('----------------------')
print('Analytical | Numerical')
print('----------------------')
for g, n_g in zip(grads, n_grads):
print(' {0: .4f} | {1: .4f}'.format(g, n_g))
diff = np.linalg.norm(n_grads - grads) / np.linalg.norm(n_grads + grads)
print('Relative difference: {0}'.format(diff))
print('========== Part 2.4: Regularized Neural Networks ==========')
Theta = [data['Theta1'], data['Theta2']]
theta = np.block([t.reshape(t.size, order='F') for t in Theta])
nn.update_lambda(3)
J = nn.cost(theta)
print('Regularized cost: {0:0.6f} (expected: 0.576051)'.format(J))
print('========== Part 2.5: Learning Parameters ==========')
Theta = [
nn.initialize_weights(layer_dims[i], layer_dims[i + 1], 0.12)
for i in range(len(layer_dims) - 1)
]
theta = np.block([t.reshape(t.size, order='F') for t in Theta])
nn.update_lambda(1)
J, theta = nn.optimize(theta)
p = nn.predict(theta)
print('Trained accuracy: {}'.format(np.mean(p == y) * 100))
