A single neuron

An artificial neuron multiplies each input by a weight, adds them up and adds a bias (a dot product plus a number), then passes the total through an activation function. A common one, ReLU, keeps positive totals and turns negatives into 0. Learning means adjusting the weights and bias. One neuron can only draw a simple dividing line; the power comes from many of them together.

Why it matters: Networks, and so every modern AI model, are built from this one small unit.

Builds on: The dot product and similarity, Functions and graphs, Learning from examples

Learn it, then prove it

Sign in (free) to take this step's mastery check and save your journey.