Backpropagation (Learning representations by back-propagating errors)

Editorial record

Plain-language summary

The paper applies the chain rule to compute, for every weight in a layered network, how much it contributed to the output error, then adjusts weights in the direction that reduces that error. This gave hidden units a way to learn useful internal representations instead of being hand-designed. It made training networks with one or more hidden layers a routine gradient-descent procedure and became the standard method for supervised neural network learning.