All lessons
automatic-differentiation
2 free lessons tagged automatic-differentiation across Computer Science. Each one is a short sequence of focused steps with narration and a five-question quiz at the end — take them in any order, no signup required.
Computer Science
advancedMaking Differentiable Rendering Affordable
Correct gradients are useless if computing them exhausts memory. Radiative backpropagation, path replay backpropagation's constant-memory trick, and why differentiable renderers needed their own compiler.
7 steps·~11 min
Computer Science
advancedThe Discontinuity Problem
Differentiating a renderer is easy until geometry moves. Why silhouettes break naive automatic differentiation, and the three families of solutions: edge sampling, reparameterization, and warped-area methods.
8 steps·~12 min