How a neural network moves information
If you missed Meeting 1 or want additional review, use this lesson to understand what a neuron receives, what a connection changes, and how values move forward through layers.
Watch the visual introduction
Use 3Blue1Brown's handwritten-digit example through 13:32. Stop before the compact vector and matrix notation begins.
Open “But what is a neural network?” ↗Walk through five networks
Open the playground and change presets in this order:
- 1 → 1Follow one input across one weighted connection.
- 2 → 1See how a neuron combines more than one input.
- 1 → 2 → 1Introduce a hidden layer and two intermediate values.
- 2 → 2 → 1Compare several weighted paths through the same layer.
- 3 → 3 → 2Finish with multiple inputs, hidden neurons, and outputs.
Try changing one thing
Choose one input, connection, or node. Predict which later values will change, make one edit, and compare your prediction with the result. Then repeat with a different part when you are ready.