Backpropagation
The process that tells a neural network which internal settings caused an error and how to adjust them, working backwards through layers.
Plain English Explanation
Backpropagation is the process that tells a neural network which internal settings caused an error and how to adjust them. After making a prediction, the system works backwards through its layers to assign blame and fix mistakes.
Combined with gradient descent, it makes training deep networks practical.
Analogy
Backpropagation is like tracing a wrong answer on a maths test back through each step to find exactly where the mistake started, then correcting that step before trying again.
How is it used?
Backpropagation is built into virtually every deep learning framework and runs silently whenever a neural network is trained — including the models behind modern chatbots and image generators.
Real-world Example
Training an image classifier to distinguish cats from dogs depends on backpropagation to update millions of weights after each batch of photos.
Common Misconceptions
Backpropagation is a training technique, not something that happens when you chat with a finished model at inference time.
See Also
Also known as: backprop