Wikinventia — Atlas of discoveries and inventions · Global Age

Machine learning in neural networks — Frank Rosenblatt

1958 AD · Transmission: Global
AIMethodNorth American

In 1958 Frank Rosenblatt, at Cornell Aeronautical Laboratory, publishes "The Perceptron" and implements the Mark I Perceptron: the first neural network able to learn from examples via a supervised learning rule adjusting weights proportionally to error — the birth of machine learning as practice. It can learn linearly separable patterns without explicit programming of rules. Optimism is checked in 1969 when Minsky and Papert mathematically prove single-layer perceptron limitations, triggering the first AI winter.

InstitutionCornell Aeronautical Laboratory, Buffalo, New York
Historical regionUSA
Primary sourceRosenblatt, F. — "The Perceptron" (Psychological Review, 65:6, 386-408, 1958). DOI: 10.1037/h0042519
Secondary sourceRosenblatt, F. — Principles of Neurodynamics (1962)
Original languageEnglish
View this entry in the interactive atlas → View in graph →