Learn the Maths Behind Machine Learning from the Ground Up
Every algorithm explained in plain English, with the linear algebra, calculus and statistics it actually rests on. Written for people who never did a maths degree.
Email sign-up opens shortly. The learning path is free and needs no account.

Gradient Boosting Explained: 5 Ideas Behind XGBoost
Gradient boosting adds shallow trees in sequence, each fixing the last one’s errors. Learning rate, early stopping, and how it differs from a random forest.
Read the GuideNew guides every week
One email when a new explainer is published. No courses, no affiliate links.
Sign-ups open shortly.
Not sure where to begin?
The learning path orders every guide on the site, from vectors and derivatives through to transformers.
Open the PathFind a topic by its first letter
Every guide on the site, alphabetically — 183 topics across linear algebra, calculus, statistics and machine learning.
How alike two vectors are — the distance metric behind search and recommendations.
Builds the covariance matrix step by step, the object at the heart of PCA.
Eigenvalues and eigenvectors, with the characteristic polynomial in full.
Inverts a matrix and shows every row operation on the way.
Population and sample standard deviation with each term laid out.
Fits a line to your data and shows the slope, intercept and R² working.
Every formula is derived, not asserted. If a result is stated, the working that produces it is on the page.
Every diagram is generated from the real numbers it describes, so the picture and the maths always agree.
Guides are corrected and updated when an error is found — including ones already published.
Written for people who never did a maths degree. School algebra is the only assumed prerequisite.
Track 01
Linear Algebra
- Vectors and vector operations
- Matrix multiplication
- The determinant and the inverse
- Eigenvalues and eigenvectors
Track 02
Calculus
- Derivatives from first principles
- The chain rule
- Partial derivatives and gradients
- Gradient descent
Track 03
Machine Learning
- Linear and logistic regression
- Decision trees and k-NN
- Clustering and dimensionality reduction
- Attention and transformers
Get New Guides as They Land
One email when a new explainer is published. No courses to sell, no affiliate links — just the maths, written out properly.
Sign-ups open shortly — the form is not connected yet.