The earliest neural network work on perceptrons was done in an applied contract lab for the US Navy, it was not done in an academic setting.
Backpropagation has been reinvented multiple times, because it is a basic application of the chain rule. The earliest recognizable usage of it is in control theory at NASA during the Apollo program.
It's a mistake to be dismissive of academic work which has been very important, but it's equally a mistake to think that academia is the sole source of foundational work.
Backpropagation has been reinvented multiple times, because it is a basic application of the chain rule. The earliest recognizable usage of it is in control theory at NASA during the Apollo program.
It's a mistake to be dismissive of academic work which has been very important, but it's equally a mistake to think that academia is the sole source of foundational work.