# Backpropagation

Concept · [Building with AI](https://ecosystem.samcarlton.com/ai)

Also called: backprop, back propagation, backward pass

The calculation that works out how much each weight in a [neural network](https://ecosystem.samcarlton.com/neural-network) contributed to an error, layer by layer from the output back, so [gradient descent](https://ecosystem.samcarlton.com/gradient-descent) knows how to adjust it.

**For example:** After the model guesses wrong, backpropagation assigns a share of the blame to each of its millions of [weights](https://ecosystem.samcarlton.com/weights).

## Connects to (4)

- [Gradient descent](https://ecosystem.samcarlton.com/gradient-descent): The method used to train neural networks: measure how wrong the model is, work out which direction to nudge each weight to be less wrong…
- [Neural network](https://ecosystem.samcarlton.com/neural-network): A kind of software model made of many layers of simple math units connected by weights, loosely inspired by the brain.
- [Weights](https://ecosystem.samcarlton.com/weights): The numbers inside a model that it learned during training.
- [Loss function](https://ecosystem.samcarlton.com/loss-function): A formula that scores how wrong a model's output is compared with the right answer.

Map view: https://ecosystem.samcarlton.com/backpropagation