The Perceptron: A Perceiving and Recognizing Automaton
Frank Rosenblatt · 1957 · Report 85-460-1, Project PARA, Cornell Aeronautical Laboratory
Summary
Introduces the perceptron, a trainable unit that computes a weighted sum of its inputs and fires if the sum exceeds a threshold, with a rule for adjusting weights from labelled examples.
Why it matters
It is the direct ancestor of the artificial neuron. The perceptron established that a classifier could be learned from examples rather than designed by hand, and its single-layer limitations were exactly what motivated the multilayer networks and the training algorithm that followed decades later.