Phase 2 · Math, when you need it · Calculus
Derivative rules
Power, sum and product rules, so you rarely compute from scratch.
Open this lesson Create a free account
Why it matters
You'll rarely differentiate by hand: PyTorch and JAX do it automatically. But a handful of rules explain what those libraries compute, why some activation functions train better than others (sigmoid's slope nearly vanishes for big inputs; ReLU's doesn't), and how to sanity-check a gradient. Ten minutes with these rules pays off every time you read a training formula.
What you'll be able to do
- Apply the power, constant, sum and product rules
- Know the derivatives of eˣ, ln x, sigmoid and ReLU
- Differentiate a polynomial from its list of coefficients
- Check derivatives symbolically with SymPy and numerically with a small step
Before this lesson
Next in this phase: The chain rule