Learn in the textbookNeural Networks and Deep Learning
DefinitionBackpropagation (バックプロパゲーション, error backpropagation) is a learning method that traces the error between the output and the correct answer backward, from the output-layer side toward the input-layer side, correcting the weight of each connection along the way.
ExplanationThe calculation itself runs forward from the input layer to the output layer, but the information used for correction travels from back to front. Layer by layer, the method works out how much each connection contributed to the gap, and weights with more influence get larger corrections. Repeating this over a large amount of data brings the output steadily closer to the correct answer.
AnalogyLike tasting a dish, finding it too salty, and working back from the last seasoning you added to decide which ones to cut and by how much.
Memory hookSplit the name into "back" and "propagation" (spreading along) and you get "the gap spreads backward," so you won't mix up the direction.