[varjag]

I wouldn't call the early McCulloch & Pitts work quite "full-fledged". Also backpropagation, essential for multi level perceptrons was not a thing until 1980s.

[samus]

Backprop is just applied calculus. People simply didn't think about using it for neuronal networks yet.

[varjag]

It was thought of as early as in 1960s by Rosenblatt but he did not come up with a practical implementation at the time. Lotsa things look obvious in hindsight.