I recently had the chance to teach a very short (60min) crash course on the basics of deep learning for the fellows of the Data Science For Social Good summer program offered by Stanford Data Science.

This course is structured in two short notebooks; the first provides a brief introduction to the perceptron and gradient descent algorithms, while the second explains how these two methods are extended to form the basis for modern deep learning.

Each notebook is fully reproducible and can be completed in ~30min.

You can find a fully reproducible version of this course at: