Minsky, Marvin; Papert, Seymour (1969). Perceptrons: an introduction to computational geometry. «The perceptron has shown itself worthy of study despite (and even because of!) its severe
limitations. It has many features to attract attention: its linearity; its intriguing learning
theorem; its clear paradigmatic simplicity as a kind of parallel computation. There is no
reason to suppose that any of these virtues carry over to the many-layered version. Never-
theless, we consider it to be an important research problem to elucidate (or reject) our in-
tuitive judgement that the extension to multilayer systems is sterile.»
