Lecture 8 Part 2: Automatic Differentiation on Computational Graphs

From the creator

MIT 18.S096 Matrix Calculus For Machine Learning And Beyond, IAP 2023 Instructors: Alan Edelman, Steven G. Johnson View the complete course: https://ocw.mit.edu/courses/18-s096-matrix-calculus-for-machine-learning-and-beyond-january-iap-2023/ YouTube Playlist: https://www.youtube.com/playlist?list=PLUl4u3cNGP62EaLLH92E_VCN4izBKK6OE Description: Complicated computational processes can be expressed as “graphs” of computational steps that flow from inputs to outputs. Forward/reverse-mode automatic differentiation (AD) traverse in opposite directions, giving very different algorithms. License: Creative Commons BY-NC-SA More information at https://ocw.mit.edu/terms More courses at https://ocw.mit.edu Support OCW at http://ow.ly/a1If50zVRlQ We encourage constructive comments and discussion on OCW’s YouTube and other social media channels. Personal attacks, hate speech, trolling, and inappropriate comments are not allowed and may be removed. More details at https://ocw.mit.edu/comments.

Published 2023-10-23 · Watch on YouTube ↗
Availability and playback restrictions are controlled by the original channel.