Course

Neural Networks from Scratch

Take the tiny autograd engine from Zero to GPT and build a real, trainable multi-layer perceptron with it — one neuron, one layer, one training loop at a time, ending with a 2D classifier you watch learn its decision boundary live.

Lesson 1

A Single Neuron

The atomic unit of every neural network: a weighted sum and a squashing function.

Start

Lesson 2

A Layer of Neurons

Several neurons, same inputs, different weights — a vector out instead of a number.

Start

Lesson 3

Stacking into an MLP

Chain layers together and depth starts doing real work.

Start

Lesson 4

A Loss Function for Classification

Turning 'right or wrong' into a number the network can take a derivative of.

Start

Lesson 5

Training on a 2D Toy Dataset

Forward pass, loss, backward pass, update — watch a real decision boundary form.

Start

Lesson 6

Overfitting and Regularization

More capacity can fit noise as easily as signal — unless you tax complexity.

Start