Get the latest tech news
Who Invented Backpropagation?
Its modern version (the reverse mode of automatic differentiation) was first published in 1970 by Seppo Linnainmaa
Steepest descent in the weight space of such systems can be performed (Kelley, 1960[BPA]; Bryson, 1961[BPB]) by iterating the chain rule ( Leibniz, 1676[LEI07-10][DLH]; L'Hopital, 1696) in Dynamic Programming style (DP, e.g., Bellman, 1957[BEL53]). Explicit, efficient error backpropagation (BP) in arbitrary, discrete, possibly sparsely connected, NN-like networks was first described in a 1970 master's thesis (Linnainmaa, 1970, 1976)[BP1][R7], albeit without reference to NNs. However, already in 1967, Amari suggested to train deep multilayer perceptrons (MLPs) with many layers in non-incremental end-to-end fashion from scratch by stochastic gradient descent (SGD)[GD1], a method proposed in 1951[STO51-52].
Or read this on Hacker News