Who Invented Backpropagation?

Backpropagation, the backbone of modern deep learning, has a 50+ year history often misattributed. Finnish student Seppo Linnainmaa first published its modern version in 1970, with precursors dating to 1960. This efficient method for calculating derivatives in neural networks wasn't widely accepted for training deep networks until 2010, when researchers demonstrated deep neural networks could be trained with plain backpropagation without requiring unsupervised pre-training.