Colab allows anybody to write and execute arbitrary python code through the browser, and is especially well suited to machine learning, data analysis and education. More technically, Colab is a hosted Jupyter notebook service that requires no setup to use, while providing free access to computing resources including GPUs.
For this tutorial we will be utilizing colab to execute python code and packages in order to classify handwritten digits with a Neural Network. The MNIST dataset is an acronym that stands for the Modified National Institute of Standards and Technology dataset. It is a dataset of 60,000 small square 28×28 pixel grayscale images of handwritten single digits between 0 and 9. We will be training our neural netowrk from this dataset so that we can make predictions.
For this project we will be using Python 3, Google Colab and skorch, scikit-learn.