Backpropagation is a method of training neural networks to perform tasks more accurately. The algorithm was first used for this purpose in 1974 in papers published by Werbos, Rumelhart, Hinton, and Williams. The term backpropagation is short for "backward propagation of errors".
It works especially well for feed forward neural networks (networks without any loops) and problems that require supervised learning.
How it works[change | change source]
The idea is to test, how wrong the neural network is and then correct it. This is repeated many times.
With a little more detail:
- You create a loss function, which shows how far the answers from the neural net are from the real answers. (This is often done many times. After that you take the average)
- You calculate how to adjust the parameters (weights and biases) inside the neural net through the derivative of the loss function.
- You adjust the parameters.
This is repeated until the neural network is good enough at its job.