C0Free
The Math Behind Neural Networks: A Guided Tour
A fast, visual tour of the math inside a neural network: vectors, matrices, derivatives and gradient descent, ending with a tiny network you train in the browser.
5 lessons · about 3 hours
What you'll be able to do
- See what vectors, matrices and gradients do inside a neural network
- Run every idea as NumPy code in the browser
- Know which course to take next to go deeper
Before you start
Class 12 mathematics and basic Python.
Syllabus
- 115 min
Turn things into lists of numbers, measure how far two of them point the same way, and build a tiny search engine with cosine similarity.
- 215 min
See a matrix as a machine that moves every point of the plane, learn why its columns say where the axes land, and build one layer of a neural network.
- 415 min
Find the bottom of a loss by walking downhill. The gradient says which way, the learning rate says how far, and a model learns a line.
2 more lessons coming soon