Math Overview

Build the math intuition that powers machine learning. Short, focused lessons with clear examples and practice you can use right away.

The language of data and models

Understand vectors, matrices, and transformations—the backbone of features, embeddings, and neural networks. Learn the operations that show up everywhere: dot products, norms, matrix multiplication, and projections.

You’ll learn: How data is represented, how models combine inputs, and how to work with matrices confidently.

NumPy

Fast and easy math with arrays

Learn to use NumPy, Python’s main library for number crunching. See how to make and change arrays, do math on whole groups of numbers at once, and handle data the way ML tools expect.

You’ll learn: How to create arrays, use built-in functions, reshape data, pick out values, and do fast math without loops.

Calculus

Change, slopes, and optimization

Grasp derivatives, gradients, and chain rule to see how models learn. Connect loss functions to gradient descent and learn why step size and curvature matter.

You’ll learn: How to compute and interpret gradients, tune learning, and reason about optimization.

Probability & Statistics

Uncertainty, inference, and decisions

Work with distributions, sampling, estimation, and confidence. Learn how to evaluate models with sound metrics and understand variance, bias, and overfitting.

You’ll learn: How to quantify uncertainty, choose the right metrics, and make data‑driven decisions.

---

Start here: Pick one topic, do a quick review, then try a small exercise in code. Repeat often as clarity compounds.