Layers
One neuron can only do so much. The power comes from connecting many of them into layers, where the output of every neuron in one layer feeds every neuron in the next.
Flip the inputs on and off. Watch the signal ripple left to right — each neuron's brightness is its activation, and every layer's output becomes the next layer's input.
Flip the inputs on or off and watch the signal ripple forward. Each neuron's brightness is its activation. The output of one layer becomes the input to the next — that is what makes it a network.
How it works
A network is organised into layers. The input layer holds the raw numbers. Each hidden layer takes the previous layer's outputs, and every neuron computes its own weighted sum and activation — so one layer's outputs become the next layer's inputs. The output layer produces the final answer. This depth is what lets networks learn complex patterns: early layers pick up simple features, and later layers combine them into higher-level ones. A single neuron can only draw a straight dividing line; stacking layers lets the network bend that line into any shape. Networks like this, where every neuron connects to every neuron in the next layer, are called fully connected or dense networks.
Check yourself
Why can a network of layers learn patterns that a single neuron cannot?