12.2 Artificial Neurons

An artificial neuron is the basic building block of a neural network. It takes several inputs, multiplies each by a weight, adds them together with a bias term, and then passes the result through an activation function to produce an output.

Imagine deciding whether to carry an umbrella in Addis Ababa. Cloud cover, season, and morning humidity are inputs; you weight each by how much it matters, add them up, and if the total crosses a threshold you take the umbrella. A neuron works the same way.