Lecture 8 Part 2: Automatic Differentiation on Computational Graphs
Description: Complicated computational processes can be expressed as “graphs” of computational steps that flow from inputs to outputs. Forward- and reverse-mode automatic differentiation (AD) traverse in opposite directions, giving very different algorithms.
Instructors: Alan Edelman, Steven G. Johnson
Viewing videos requires an internet connection
Course Info
Instructors
Departments
As Taught In
January IAP
2023
Level
Learning Resource Types
theaters
Lecture Videos
notes
Lecture Notes
assignment_turned_in
Problem Sets with Solutions
Readings
Instructor Insights