Build a Neural Network to Recognize HandWritten Digits

A practical step-by-step example with Keras and a convolution layer.

Photo by Universal Eye on Unsplash

In this article, I will explain how to build a Neural Network to recognize HandWritten digits.

We will use phyton and Keras (a high-level TensorFlow API) and different layers like a convolution layer or a pooling layer to build our model.

Also, we will use the mmist DataSet with a training set of 60,000 samples and a test set of 10,000 examples of HandWritten digits images.

Preparing DataSet

Importing libraries

The first step is to import the libraries needed to build and plot our neural network.

Loading the mmist DataSet

Generally, the most expensive step in any Machine Learning problem is obtaining the data and preparing it for use.
We will use the MNIST DataSet with a training set of 60,000 examples and a test set of 10,000 samples. The digits have been…