Module 00

Mathematics for AI

Intermediate10 lessons

Build AI-ready number sense with integers, floats, fractions, percentages, ratios, scientific notation, and logarithms.

Learn linear algebra for AI: vectors, matrices, tensors, vector operations, dot products, and eigenvalues used in machine learning models.

Learn calculus for machine learning: limits, derivatives, partial derivatives, and the chain rule with AI and real-estate pricing examples.

Master probability formulas, conditional probability, and Bayes theorem used throughout machine learning and AI systems.

Use mean, median, mode, standard deviation, and the normal distribution to describe and evaluate machine learning data.

Connect loss functions, MSE, cross-entropy, and gradient descent — the optimization loop behind modern model training.

Measure uncertainty with entropy and information gain — core ideas behind decision trees and large language models.

Handle floating-point precision, overflow, underflow, numerical stability, and softmax stabilization in real AI code.

Extend calculus to vectors and matrices with Jacobians and Hessians — the mathematical language of backpropagation.

Apply math topics in practice: vector calculator, gradient descent visualizer, PCA from scratch, and Bayes spam detection.