Glossary · Phase 4 · Deep learning
Neuron
One unit in a neural network: a weighted sum of its inputs, then a simple function.
Try it now
Multiply each input by its weight, add the bias, then pass the sum through an activation. Move anything and follow the numbers.
Learn it properly
The artificial neuron · Weighted sum plus a nonlinearity. About 25 minutes.
Other terms from the same lesson
- hyperplane: A flat dividing surface in any number of dimensions: a line in 2D, a flat sheet in 3D, and so on.
- linearly separable: When one straight line (or flat surface) can split the yes examples from the no examples. A single neuron can only learn these.
- XOR: "Exclusive or": yes when exactly one of two things is true, but not both. One neuron can't learn it; two layers can.
Never trained an AI?
Teach a small one to write, right in your browser. It takes about 20 seconds and needs no account.