Layers Explained — Input, Hidden, Output
Neurons, organized into layers
A neural network arranges neurons into layers. Data enters one side, flows through, and a prediction comes out the other. Three kinds of layer do the work.
One neuron per input feature — pixels, words, measurements. No computation, just the data.
Where the magic happens. Each layer transforms the previous one, learning ever more abstract features.
See the data flow
Watch values enter the input layer, fan through fully-connected hidden layers, and arrive at the output — and see how each connection is a weight.
Why depth helps
Early layers learn simple patterns (an edge, a key word); later layers combine them into complex ones (a face, a sentiment). Depth lets a network build understanding in stages — the "deep" in deep learning.
More neurons = more capacity to represent patterns in a layer.
More layers = more abstraction, but harder to train (see vanishing gradients).
Every neuron connects to every neuron in the next layer — the basic layer type.
Counting parameters
A dense layer from m to n neurons has m × n weights plus n biases — all the numbers training will tune. A modern network has millions to billions of them.
Next: trace how a single input becomes a prediction in Forward Propagation.