# Posts tagged *machine-learning*

This is part 2 of a series of blog posts about implementing automatic differentiation. You can read part 1 here. In this post, we extend our automatic differentiation system to support higher order derivatives.

Like the previous post, some knowledge of calculus is required and Racket-y stuff will be explained as we go.

\[
\DeclareMathOperator{\expt}{expt}
\DeclareMathOperator{\mul}{mul}
\DeclareMathOperator{\add}{add}
\DeclareMathOperator{\derivative}{derivative}
\]

Automatic differentiation is a technique that allows programs to compute the derivatives of functions. It is vital
for deep learning and useful for optimization in general.
For me, it’s always been dark magic, but I recently thought of a nice way to implement it and made a little library. This
blog post takes you along the journey of discovering that implementation. Specifically, we will be implementing forward mode
automatic differentiation for scalar numbers.

This post requires some knowledge of differential calculus. You’ll need to know basic derivative rules, the chain rule,
and it’d help to know partial derivatives. If you’ve taken an introductory calculus course, you should be fine.

The code is in Racket. If you don’t know Racket, you should still be able to follow along. I’ll explain the Racket-y stuff.
Don’t let the parentheses scare you away!