How a Neural Network Is Structured

The structural anatomy of a neural network — layers, weights, biases, activation functions, and how one prediction flows through it — without touching how training works.

1. Neurons, Layers, and What "Network" Means The layered picture of a neural network — input, hidden, and output layers — and what a single neuron structurally is.
2. Weights, Biases, and Activation Functions What a neuron actually computes — a weighted sum plus a bias, then squashed through a non-linear activation function — and why skipping that non-linearity collapses the whole network into one big linear function.
3. The Forward Pass How one prediction flows through the entire network structure end to end, from the input layer to the output layer — and where to go next to learn how the weights get set.