Calculus is the maths of change, and it is how AI models learn. A model makes a prediction, measures how wrong it was, and then uses calculus to work out which way to adjust its settings to be less wrong. The key tool is the derivative, which tells you how fast one quantity changes when another one does.
The lessons start with an overview of why calculus matters for machine learning, then build up the core ideas: rates of change, limits, and derivatives, followed by integrals and how they relate to derivatives. They finish with a first look at how derivatives power gradient descent.
Watch the lessons in order, then continue on to Gradients & the Chain Rule.
Introduces the derivative as a rate of change, the idea behind how models measure which way to improve.
Video 13minA lesson from a Machine Learning Foundations series covering limits and derivatives.
Video 3minBuilds intuition for common derivative formulas by looking at them geometrically.
Video 17minIntroduces integration and how it connects back to derivatives through the fundamental theorem of calculus.
Video 20minShows how derivatives are used in gradient descent, the method AI models use to learn.
Video 3h 55min