# Backpropagation

> It traces the error back through the layers to see which weights to fix.

**Field:** Artificial Intelligence  
**Category:** Machine Learning  
**Also known as:** Backprop, Backward Pass

## Think of it like

Think of it like a coach after a lost game. The coach goes back through the game to see who caused each miss.

## Definition

Backpropagation finds how much each weight in a network added to its error. After the network makes a guess, the loss is measured at the output. Then the error is passed backwards, layer by layer, toward the input. At each layer, it works out how much each weight should change. Gradient descent then uses those numbers to update the weights.

## Example

Lucy's network says dog for a cat photo. Backpropagation traces the miss back through all 12 layers. It finds the weights that pushed hardest toward dog.

## Why it matters

It makes training deep networks possible. Without a fast way to share out the blame, big networks could not learn.

## Common mistake

Thinking it is the same thing as gradient descent. This step works out the changes. Gradient descent then makes them.

## Three principles

- **Start at the error.** Measured at the output.
- **Go backwards.** Layer by layer to the input.
- **Share the blame.** How much each weight should change.

## Related terms

- [Gradient Descent](https://learn.benibix.com/term/ai/gradient-descent)
- [Loss Function](https://learn.benibix.com/term/ai/loss-function)
- [Weight (Neural Network)](https://learn.benibix.com/term/ai/weight)
- [Neural Network](https://learn.benibix.com/term/ai/neural-network)

## Told apart from

- [Backpropagation vs Gradient Descent](https://learn.benibix.com/compare/backpropagation-vs-gradient-descent): People often use the two names for the same thing. They are two steps that work as a pair. Backpropagation works out how much each weight added to the error. Gradient descent then uses those numbers to move every weight a small step. One finds the changes, and the other makes them.

## Taught in

- [Gradient Descent and Backprop](https://learn.benibix.com/learn/ai-machine-learning/gradient-descent-and-backprop): Machine Learning, 14/18

![A loop of four boxes. Forward pass gives a guess. The loss compares it with the answer. Backpropagation sends the error back. Gradient descent updates the weights, and the loop starts again.](https://learn.benibix.com/diagrams/nn-training-loop.svg)

---

Source: https://learn.benibix.com/term/ai/backpropagation
Author: Behnia Zarei (a developer in Vienna, Austria, who builds and teaches data, AI and business intelligence at BENIBIX)
Publisher: BENIBIX Learn (https://learn.benibix.com/)
Last updated: 2026-11-17
Licence: CC BY 4.0 (https://creativecommons.org/licenses/by/4.0/). Quote freely with attribution.
