Understanding datasets

It is of the utmost importance that we properly understand the dataset that we are working on in order to produce the best results—in terms of execution time and space for the data—with the most efficient code. The dataset we will be using here is probably the most popular dataset when it comes to using neural networks with images—the MNIST database of handwritten digits.

The MNIST dataset of handwritten digits

This dataset was created by a team made up of Yann LeCun, Corinna Cortes, and Christopher J.C. Burges. It is a large collection of images of handwritten digits, containing 60,000 training samples and 10,000 testing samples. The dataset is publicly available for download at...