Video details loaded
HomeMIT 18.S096 Matrix Calculus For Machine Learning And Beyond, IAP 2023Lecture 8 Part 2: Automatic Differentiation on Computational Graphs

Lecture 8 Part 2: Automatic Differentiation on Computational Graphs

1:05:29

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