Tanh function — ‘S’ shaped function similar to the Sigmoid function

Step by step implementation with its derivative

3 min readDec 1, 2021

In this post, we will talk about the Tanh activation function and its derivative. The shape of the Tanh function is very similar to the Sigmoid function but the output range is (-1, 1) unlike (0, 1) which is for the Sigmoid.

You can download the Jupyter Notebook from here.

Back to the previous post

Back to the first post

3.2 What is Tanh activation function and its derivative?

This is the definition of the Tanh function.

And it is very easy to find the derivative of the Tanh function.

This is the graph for the Tanh function and its derivative.

We can easily implement the Tanh function in Python.

import numpy as np                             # importing NumPy
np.random.seed(42)def tanh(x):                                   # Tanh
    return np.tanh(x)def tanh_dash(x):                              # Tanh Derivative
    return 1 - np.tanh(x)**2

Defining Tanh function and its derivative

Let us have a look at an example.

x = np.array([[0.2], [0.5], [1.2], [-2.3], [0]])
xtanh(x)tanh_dash(x)

Example for the Tanh function and its derivative

I hope now you understand how to implement the Tanh function and its derivative.

Watch the video on youtube and subscribe to the channel for videos and posts like this.
Every slide is 3 seconds long and without sound. You may pause the video whenever you like.
You may put on some music too if you like.

The video is basically everything in the post only in slides.