Autodiff and Adjoints for Differentiable Physics

This is a recording of a lecture for our TUM Master Course "Advanced Deep Learning for Physics". You can find the lecture slides here: fkoehler.site/files/autodiff_...
Lecture script: physicsbaseddeeplearning.org/...
Course website: www.cs.cit.tum.de/cg/teaching...
This module is hosted by the Thuerey group at TUM (which I am PhD student in): ge.in.tum.de/
-------
📝 : Check out the GitHub Repository of the channel, where I upload all the handwritten notes and source-code files (contributions are very welcome): github.com/Ceyron/machine-lea...
📢 : Follow me on LinkedIn or Twitter for updates on the channel and other cool Machine Learning & Simulation stuff: / felix-koehler and / felix_m_koehler
💸 : If you want to support my work on the channel, you can become a Patreon here: / mlsim
🪙: Or you can make a one-time donation via PayPal: www.paypal.com/paypalme/Felix...

[@MachineLearningSimulation]

Errata:
33:30: The pullback/vJp rule for the matrix-vector product should use A (not W, which was never introduced), hence \bar{x} = A^T \bar{y}

[@howwway4999]

huge fan, thanks for sharing the great lecture

[@MachineLearningSimulation]

Thanks :) You're very welcome!

[@DrSimulate]

Nice lecture! Thanks for sharing this!

[@JousefMuradAPEX]

Good one, Felix!!

[@MachineLearningSimulation]

Thanks jousef 😊