Skip to main content
Home/Glossary/Backpropagation

Backpropagation

The algorithm that calculates how much each weight in a neural network contributed to a prediction error, so every weight can be corrected.

Machine LearningAlso called: "backprop", "backward propagation"

Backpropagation (short for "backward propagation of errors") is the algorithm that makes training neural networks possible. After the network makes a prediction and the error is measured, backpropagation works backwards through the layers, using calculus (the chain rule) to compute each weight's exact share of the blame.

Why it matters

  • A neural network can have millions or billions of weights.
  • Backpropagation computes the gradient — the direction and amount each weight should change — for all of them efficiently in one backward pass.
  • Without it, training deep networks would be computationally impossible.

The training loop

  1. Forward pass — run an example through the network to get a prediction.
  2. Loss — measure how wrong the prediction is.
  3. Backpropagation — compute each weight's contribution to the error.
  4. Gradient descent — nudge every weight to reduce the error.

This loop repeats for every batch of training data, every epoch, until the network converges.