An artificial neural network is a network or circuit of artificial neurons, that is created for the purpose of recognizing underlying relationships in a set of data through a process that mimics the way the human brain operates.
Neural Networks are incredibly vast in their usecases. In this example, a deep sequential neural network was trained using supervised machine learning to be able to classify numbers written by humans.
How it works: All you need to do is draw a single number (0 through 9) in the box. The neural network will then attempt to classify the number you drew, and will provide a confidence level that its classification is correct.
For the best results, be sure to center your number, and draw it large enough so that it takes up the majority of the box.
At the moment, number recognition is the only tool available. This page will be expanded upon, and more tools will be made available in the future.