Learn
Read it end to end, or land on the one section you need.
Chapters stay on the left. Maths is typeset, not screenshotted. Your position is remembered in this browser.
Prefer to watch? 1 video guide below ↓
Studio Tour
Step by step through the Lab: the canvas, every block, and the script that comes out.
A guided tour of the Lab, from your first notebook to a PyTorch script you can run. Each row below is one page. Read them in order, or…
Physics-Informed Neural Networks, from scratch
From the first derivative to a solver you can defend.
An open textbook. It starts from machine learning and neural networks with nothing assumed, then builds the physics-informed method piece by piece: differential equations, automatic differentiation, residual and…
Operator Learning
Learn the solution operator, not one solution.
Methods such as DeepONet and the Fourier Neural Operator learn a map from whole input functions to solutions, so one trained model can answer many problems. This book…
Video guides