18.S096 | January IAP 2023 | Undergraduate

Matrix Calculus for Machine Learning and Beyond

Lecture 5 Part 2: Forward Automatic Differentiation via Dual Numbers

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

Course Info

Departments
As Taught In
January IAP 2023
Learning Resource Types
Lecture Videos
Lecture Notes
Readings
Instructor Insights
Editable Files
Problem Sets
Problem Set Solutions