The recording from the Getting Started with Slang - Automatic Differentiation meetup is now available: https://youtu.be/gUE-RIOwQKI?si=wQY4vTNVmNKAX8kD

#Slang #autodiff #shader #graphics #neural #rendering #gpu

Join us next week for Getting Started with Slang - Automatic Differentiation! This meetup will be led by Slang Working Group Chair, Shannon Woods. She will distill the core concepts of autodiff, emphasizing how forward and reverse modes work, how gradients propagate, and how to reason about correctness and efficiency with clear, minimal examples.

Learn more and register: https://shader-slang.org/event/2025/10/06/getting-started-with-slang-automatic-differentiation/
#slang #autodiff #graphics #neural #rendering #GPU

Join us in two weeks on October 21st for the next Getting Started with Slang meetup! This time we will tackle Automatic Differentiation. Led by Slang Working Group Chair, Shannon Woods, this session will distill the core concepts of autodiff, emphasizing how forward and reverse modes work, how gradients propagate, and how to reason about correctness and efficiency with clear, minimal examples.

Learn more and register: https://shader-slang.org/event/2025/10/06/getting-started-with-slang-automatic-differentiation/
#slang #autodiff #graphics #neural #rendering #GPU

I tried using analytical normal vector calculation on a fractal. It turns out that even without any antialiasing, the image becomes much less noisy.

#sdf #indiedev #compiler #autodiff

Using the gradient length of the signed distance field, we can see where the function is non-euclidean.

#sdf #autodiff #render

Beyond Backpropagation - Higher Order, Forward and Reverse-mode Automatic Differentiation for Tensorken
https://open.substack.com/pub/getcode/p/beyond-backpropagation-higher-order

#Rust #rustlang #autodiff