The Math Behind the Machine
The mathematics of machine learning & AI

Learn the math under the machine — by touching it.

All the math you need to truly understand modern machine learning and AI — told simply, built to be touched. Every idea opens as a story, every concept is something you can drag, spin, and break, and every unit ends with its full problem set solved step by step. Curiosity is the only prerequisite.

📐 16 units · 8 live so far 🎛 74 hands-on widgets ✅ 115 pause-and-predict checks ✍ 86 problems solved step by step 🧾 77 rules derived step by step, nothing on faith
Start with Unit 1 →Each unit is a story you can play with — about an hour, no prerequisites.
drag the space to orbit

IPart I · Linear Algebra

01

Systems of Linear Equations

A matrix is a machine that moves space. Three windows on Ax = b, the three fates, and elimination — the algorithm that never lies.

✓ Ready13 widgets · 11 checks · 10 problems
02

Vector Spaces

The universe where vectors live: groups, subspaces, span, independence, basis, dimension — the architecture of ML math.

✓ Ready6 widgets · 11 checks · 18 problems
03

Analytic Geometry

The board gets its ruler: norms, inner products, angles, orthogonality — and Gram–Schmidt, the cleanest grid a geometry can have.

✓ Ready8 widgets · 13 checks · 8 problems
04

Determinants, Eigenvalues & the Spectral Theorem

A matrix's fingerprints: the volume dial, the directions it cannot turn, A = QΛQᵀ — and Cholesky, the covariance square root.

✓ Ready8 widgets · 13 checks · 5 problems
05

Matrix Decompositions & SVD

Prime factorization for transformations: the ladder from spectral to eigen to SVD — ending with a real photograph compressed live.

✓ Ready10 widgets · 17 checks · 12 problems

IIPart II · Calculus & Differentiation

06

Differentiation

Which way is down? From a shrinking secant to the Jacobian matrices behind backpropagation — the language every learning machine speaks.

✓ Ready13 widgets · 17 checks · 10 problems
07

Backprop & Automatic Differentiation

The chain rule, industrialized: watch blame flow backwards through a graph, train a neuron with your own hands, and see why a million derivatives cost one sweep.

✓ Ready7 widgets · 16 checks · 11 problems
08

Taylor & MacLaurin Series

Polynomial impostors: where Taylor's formula comes from, exactly how big the lie (the remainder) is — and the Hessian, the judge that tells a bowl from a dome from a saddle.

✓ Ready9 widgets · 17 checks · 12 problems

IIIPart III · Optimization

09

Gradient Descent

Walk downhill in thick fog: steps, step sizes, and why a little noise helps you scale.

Coming soon
10

Optimization I — Gradients that Work

Nonlinear optimization and the minutiae that make or break gradient methods.

Coming soon
11

Optimization II — Five Ways Down One Valley

Momentum, AdaGrad, RMSProp, Adam — and the cliffs and valleys that defeat naive descent.

Coming soon

IVPart IV · Applications

12

PCA I — Foundations

Compress a thousand dimensions without losing the story: variance, projections, eigenvectors.

Coming soon
13

PCA II — In Action

Principal components at work — linear algebra earning its keep on real data.

Coming soon
14

SVM I — Constrained Optimization & Kernels

Lagrange multipliers, KKT conditions, duality, and the kernel trick — the math that draws the widest possible line.

Coming soon
15

SVM II — Solving the SVM

From primal to dual to solution — and soft margins for a messy world.

Coming soon
16

The Finale

Where every thread ties together — the last stop on the route from lines to learning machines.

Coming soon