pytorch

1 free lesson tagged pytorch across Math. 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.

Math

intermediate

Automatic Differentiation: How Gradients Are Actually Computed

Frameworks do not differentiate formulas symbolically or estimate derivatives numerically. They differentiate the program. This lesson builds forward mode from dual numbers and reverse mode from the backward sweep, shows why a full gradient costs about four function evaluations at any size, and where the answer is not what you meant.

10 steps·~15 min

Automatic Differentiation: How Gradients Are Actually Computed

Related topics