Oliver Selfridge
In plain wordsA British-born American computer scientist who pioneered teaching machines to recognize patterns; his 1959 'Pandemonium' model did it through layers of simple, competing detectors.
British-born American computer scientist and a founder of machine perception, the study of how computers can recognize patterns in sensory input. A student of Norbert WienerNorbert Wiener, prop. n.: An American mathematician who founded cybernetics, the study of feedback and control in animals and machines, and warned early that machines might pursue goals we did not truly intend. at MIT and later a researcher at MIT's Lincoln Laboratory, Bolt Beranek and Newman, and GTE Laboratories, he took part in the 1956 Dartmouth workshopDartmouth workshop, prop. n.: A summer meeting of scientists at Dartmouth College in 1956, planned in a 1955 funding proposal that first used the phrase 'artificial intelligence'. Most histories treat it as the moment AI became a research field of its own.. His paper 'Pandemonium: A Paradigm for Learning' (1959) described recognition by layers of 'demons': feature demons respond to parts of the input, cognitive demons call out in proportion to the evidence for the pattern each represents, and a decision demon picks the loudest, with the weightings adjusted by experience. The architecture anticipated hierarchical feature extractionfeature extraction, n.: Turning raw data such as pixels or sound into a short list of telling numbers — computed by hand-designed rules or by an AI system trained earlier — that a new model can learn from or compare. and parallel models of perception, and his work with Ulric Neisser on letter recognition (1960) influenced cognitive psychology. His demons also prefigured the software agentagent, n.: Something that acts. In AI, a program that observes its situation and takes actions toward a goal: a game-playing learner, a software helper, or a chatbot that uses tools to complete tasks., a theme of his later writing on adaptive, learning software.
Related
- pattern recognitionpattern recognition, n.: The ability of a computer, or a brain, to spot regularities in data and sort things into categories, such as recognizing handwritten letters, faces or spoken words.
- feature extractionfeature extraction, n.: Turning raw data such as pixels or sound into a short list of telling numbers — computed by hand-designed rules or by an AI system trained earlier — that a new model can learn from or compare.
- Dartmouth workshopDartmouth workshop, prop. n.: A summer meeting of scientists at Dartmouth College in 1956, planned in a 1955 funding proposal that first used the phrase 'artificial intelligence'. Most histories treat it as the moment AI became a research field of its own.
- agentagent, n.: Something that acts. In AI, a program that observes its situation and takes actions toward a goal: a game-playing learner, a software helper, or a chatbot that uses tools to complete tasks.
- 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.
Sources
- Selfridge, O. G. (1959). Pandemonium: A Paradigm for Learning. In Mechanisation of Thought Processes: Proceedings of a Symposium Held at the National Physical Laboratory, November 1958. HMSO.