AI Glossary Term
What does “Backpropagation” mean?
The core training algorithm that updates model weights by propagating prediction errors backward through the network.
How Backpropagation works
Example
A digit-recognition network guesses '3' for an image of an '8'. Backpropagation traces the error back through the layers and calculates how each weight contributed to the mistake. Small adjustments are applied, and repeated over many examples, the guesses improve.
Why it matters
Backpropagation is what makes training deep networks practical. Almost every modern neural network is trained with it.
Common questions
Is backpropagation the same as gradient descent?
No. Backpropagation computes the gradients efficiently; gradient descent (or a variant) then uses them to update the weights.
Does the brain use backpropagation?
Not in any way that is established. It is a mathematical training method, not a model of how biological neurons learn.
Why is it called backward?
Because error information flows from the output layer back toward the input layer, reversing the direction of the forward prediction.