Neural network
Definition
A model made of layers of simple connected units that pass numbers forward, loosely inspired by neurons in the brain.
In plain English
Each unit takes some numbers in, multiplies them by its weights, adds them up, and passes the result on. Training adjusts those weights millions of times until the network’s outputs match the examples.
Networks with many layers are called “deep,” which is where the term deep learning comes from.
Example
A network that reads handwritten digits takes the pixel values of an image, passes them through a few layers, and outputs which digit from 0 to 9 it most likely is.
Draft, not yet reviewed by a person · Updated Nov 2026