Frank Rosenblatt

American psychologist and neural-network pioneer at the Cornell Aeronautical Laboratory and Cornell University. In 1957–58 he introduced the perceptronperceptron, n.: One of the first learning machines: a single artificial neuron that sorts inputs into two groups by drawing a straight dividing line, nudging its weights whenever it guesses wrong., a network of threshold units whose connection weights are adjusted by an error-correction rule; he and others proved that the rule converges whenever the classes are linearly separablelinear separability, n.: When two groups of points can be perfectly divided by a single straight line or, in more dimensions, a flat surface. Many simple learning methods only fully succeed in this case.. A US Navy demonstration in July 1958, simulated on an IBM 704, drew extravagant press claims about thinking machines; the custom-built Mark I PerceptronMark I Perceptron, prop. n.: A room-sized machine built around 1960 that learned to recognize simple shapes and letters through a camera made of 400 light sensors. It was one of the first machines built to learn from examples., which learned to classify images from a camera-like array of photocells, followed around 1960. His book 'Principles of Neurodynamics' (1962) analyzed many network designs, including multilayer ones and a scheme he called back-propagating error correction. The 1969 critique 'PerceptronsPerceptrons (book), prop. n.: A 1969 book by Marvin Minsky and Seymour Papert proving that simple one-layer neural networks cannot learn certain patterns. It is widely blamed for a decade-long slump in neural-network research.' by Marvin MinskyMarvin Minsky, prop. n.: An American AI pioneer who helped launch the field and MIT's AI laboratory, co-wrote a famous critique of early neural networks, and pictured the mind as a society of many simple parts. and Seymour Papert contributed to a decline in such research, which connectionismconnectionism, n.: The view that minds and intelligent machines are best built from huge networks of simple, neuron-like units whose connection strengths are learned, rather than from explicit rules and symbols. revived in the 1980s. He died in a boating accident in 1971.