Oliver is a Research Software Engineer at The Alan Turing Institute, the UK national institute for data science and artificial intelligence.
Automatic differentiation describes a family of algorithms for taking derivatives of functions implemented by computer programs. This technique offers the powerful ability to compute gradients of values exactly and efficiently, given a program as input, which has made it valuable anywhere that gradients are needed (for example, in machine learning). In this talk, I explore several approaches to automatic differentiation from a functional and language-oriented programming perspective, in Racket.
Slides