Ray Solomonoff
In plain wordsAn American mathematician who worked out an ideal mathematical recipe for predicting what comes next from past data, and who attended the 1956 meeting that launched AI.
American mathematician whose formal theory of induction helped found algorithmic information theory. One of the few participants to stay for the whole of 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., he wrote an early paper on machine learning, 'An Inductive Inference Machine' (1957). In a 1960 report and the two-part 'A Formal Theory of Inductive Inference' (1964) he defined algorithmic probability, which weights every program that could have produced the observed data according to its length, favoring shorter ones, and used it for universal prediction, now called Solomonoff inductionSolomonoff induction, n.: A mathematical recipe for ideal prediction: consider every computer program that could have produced the data so far, trust shorter programs more, and predict what they would output next.. The work anticipated the complexity measure introduced independently by Andrey Kolmogorov and Gregory Chaitin (Kolmogorov complexityKolmogorov complexity, n.: How briefly something can be described by a computer program that recreates it exactly: a million zeros needs only a tiny program, while a truly random string needs one about as long as itself.) and gave Occam's razorOccam's razor, n.: A rule of thumb for choosing between explanations: if two fit the evidence equally well, bet on the one that assumes less. In AI it motivates preferring simpler models, which are less likely to fit noise. a formal basis. Incomputable but optimal in a precise sense, it underlies minimum description lengthminimum description length, n.: The principle that the best explanation of some data is the one that lets you write the data down most briefly, counting both the rule and its exceptions. Good theories compress. ideas and Marcus Hutter's AIXIAIXI, prop. n.: A mathematical description of a perfect learning agent that weighs every possible explanation of its experience and acts to get the most future reward. It cannot actually be built, but it defines an ideal.. He worked largely independently through his own firm, Oxbridge Research, and received the first Kolmogorov Medal (2003).
Related
- Solomonoff inductionSolomonoff induction, n.: A mathematical recipe for ideal prediction: consider every computer program that could have produced the data so far, trust shorter programs more, and predict what they would output next.
- Kolmogorov complexityKolmogorov complexity, n.: How briefly something can be described by a computer program that recreates it exactly: a million zeros needs only a tiny program, while a truly random string needs one about as long as itself.
- minimum description lengthminimum description length, n.: The principle that the best explanation of some data is the one that lets you write the data down most briefly, counting both the rule and its exceptions. Good theories compress.
- AIXIAIXI, prop. n.: A mathematical description of a perfect learning agent that weighs every possible explanation of its experience and acts to get the most future reward. It cannot actually be built, but it defines an ideal.
- Occam's razorOccam's razor, n.: A rule of thumb for choosing between explanations: if two fit the evidence equally well, bet on the one that assumes less. In AI it motivates preferring simpler models, which are less likely to fit noise.
- 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.
Sources
- Solomonoff, R. J. (1964). A Formal Theory of Inductive Inference, Parts I and II. Information and Control 7(1): 1–22; 7(2): 224–254.
Mentioned in
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.