← All Courses
CA

Calculus for Deep Learning

Derivatives, gradients, and the chain rule — the math that makes neural networks learn.

6 lessons ~3 hours 390 XP

Chapter 1: Foundations: Functions and Derivatives

What derivatives are and why they matter for optimization.

1.1

Functions and Their Graphs

The building blocks of calculus.

Soon+50 XP
1.2

Derivatives and What They Mean

The rate of change — the core idea behind gradient descent.

Soon+60 XP
1.3

The Chain Rule

The math behind backpropagation.

Soon+70 XP

Chapter 2: Multivariable Calculus for Neural Networks

Partial derivatives, gradients, and the Jacobian.

2.1

Partial Derivatives

Derivatives in multiple dimensions.

Soon+60 XP
2.2

Gradients and Gradient Vectors

The direction of steepest ascent.

Soon+70 XP
2.3

Jacobian and Hessian Matrices

Derivatives of vector functions.

Soon+80 XP