Now we will look at how to use feedforward networks to classify images. We will be using
notMNIST data. The dataset consists of images for nine letters, A to I.
NotMNIST dataset is similar to MNIST dataset but focuses on Alphabets instead of numbers (http://yaroslavvb.blogspot.in/2011/09/notmnist-dataset.html)
We have reduced the original dataset to a smaller version for the training so that you can easily get started. Download the ZIP files and extract them to the folder where the dataset is contained, https://1drv.ms/f/s!Av6fk5nQi2j-kniw-8GtP8sdWejs.
The pickle module of python implements an algorithm for serializing and de-serializing a Python object structure. Pickling is the process in which a Python object hierarchy is converted into a byte stream, unpickling is the inverse operation, where a byte stream is converted back into an object hierarchy. Pickling (and unpickling) is alternatively known as serialization, marshaling,  or flattening...