Layers

Solving XOR with a hidden layer

An interactive lesson with 6 steps, about 5 minutes: you predict, drag and solve, with instant feedback on every answer. It runs in your browser and needs JavaScript.

What you’ll learn

• Hidden layers let networks combine simple boundaries into complex ones.
• Two hidden neurons (OR and NAND) plus an AND output compute XOR.
• With enough neurons, networks can approximate any continuous function.

Steps

1. A hidden layer
2. Trace the network
3. Counting parameters
4. Exactly one
5. Two bends make a V
6. How powerful?