backprop-historical-priority

IN premiseentries/2026/06/21/wiki-Backpropagation-chunk-7.md

Created 2026-06-21T09:55:49+00:00

Kelley (1960) and Bryson (1961) first described gradient computation for optimal control; Linnainmaa (1970) formalized reverse mode AD; Werbos (1974) first applied it to neural networks; Rumelhart, Hinton & Williams (1986) popularized it.