An Introduction to Algorithmic Differentiation
Add to your list(s)
Download to your calendar using vCal
If you have a question about this talk, please contact .
Zoom link available upon request (it is sent out on our mailing list, eng-mlg-rcc [at] lists.cam.ac.uk). Sign up to our mailing list for easier reminders via lists.cam.ac.uk.
Reverse-mode Algorithmic Differentiation (AD) is a foundational tool in modern Machine Learning. In this session we will review what AD does, how it does it, and the implications of this in both principle and practice.
I will only assume familiarity with calculus (the chain rule, gradients, Jacobians, directional derivatives, etc), and that you have at some point used a framework like PyTorch or JAX , and are therefore familiar with what these frameworks tend to offer.
This talk is part of the Machine Learning Reading Group @ CUED series.
This talk is included in these lists:
Note that ex-directory lists are not shown.
|