Machine Learning Studio
Neural Networks

A stack of matrix multiplies, a non-linearity, and the chain rule run backwards.

There is no magic in a neural network — only three ideas composed together. Work through them in order: what a non-linearity buys you, how gradient descent uses a slope, and how backpropagation gets every gradient in one backward sweep. Every page computes its numbers from inputs you control.

Edit inputs, weights and targets Every number computed live Step forward and backward