Video details loaded
HomeMIT 18.S096 Matrix Calculus For Machine Learning And Beyond, IAP 2023Lecture 5 Part 2: Forward Automatic Differentiation via Dual Numbers

Lecture 5 Part 2: Forward Automatic Differentiation via Dual Numbers

36:02

Description: One simple way to automatically differentiate (AD) computer programs (in “forward mode”) is to define a new kind of number that carries both value and derivative information: dual numbers. A few lines of Julia let us build an AD system!

Instructors: Alan Edelman, Steven G. Johnson