Apache Spark Deep Learning Cookbook

How to do it...

This section walks through the steps to create a sigmoid derivative function.

1. Just like the sigmoid function, create the derivative of the sigmoid function can with Python using the following script:

def sigmoid_derivative(x):    return sigmoid(x) * (1-sigmoid(x))

2. Plot the derivative of the sigmoid function alongside the original sigmoid function using the following script:

plt.figure(figsize=(6, 4), dpi= 75)plt.axis([-10,10,-0.25,1.2])plt.grid()X = np.arange(-10,10,1)Y = sigmoid(X)Y_Prime = sigmoid_derivative(X)c=plt.plot(X, Y, label="Sigmoid",c='b')d=plt.plot(X, Y_Prime, marker=".", label="Sigmoid Derivative", c='b')plt.title('Sigmoid vs Sigmoid Derivative')plt.xlabel('X')plt.ylabel('Y')plt.legend()plt.show()