Ray Solomonoff

From GM-RKB
Jump to navigation Jump to search

Ray Solomonoff was a person.



References

2010


  • New York Times. (2010-01-10). “http://www.nytimes.com/2010/01/10/science/10solomonoff.html Ray Solomonoff, Pioneer in Artificial Intelligence, Dies at 83]."
    • … In 1952 he met Marvin Minsky, a cognitive scientist who was also exploring the idea of machine learning, and John McCarthy, a young mathematician. In 1956 he became one of the 10 scientists who took part in the original Dartmouth Summer Research Project, whose organizers included Mr. Minsky and Mr. McCarthy, and which coined the term “artificial intelligence” and was instrumental in creating the field.

      In 1960 Mr. Solomonoff developed the idea of algorithmic probability, which emerged from his effort to grapple with a problem of induction: Given a long sequence of symbols describing real-world events, how can you extrapolate the sequence? The idea gave rise to a new approach to probability theory.

      Mr. Solomonoff went on to pioneer the application of probability theory to solving artificial intelligence problems. But in the 1960s and 1970s he was ahead of his time, and the approach initially had little impact on the field. More recently, probability theory has caught on among artificial intelligence researchers; it is now the dominant approach. …

      Fiercely independent, he would remain self-employed for much of his life, taking a variety of visiting scholar positions. In 2001 he was a visiting professor at the Dalle Molle Institute for Artificial Intelligence in Lugano, Switzerland, and more recently he was a visiting professor at the Computer Learning Research Center at Royal Holloway, University of London.

      He is survived by his wife.

1999

  • (Solomonoff, 1999) ⇒ Ray Solomonoff. (1999). “Two Kinds of Probabilistic Induction.” In: The Computer Journal 1999 42(4). doi:10.1093/comjnl/42.4.256
    • ABSTRACT: Problems in probabilistic induction are of two general kinds. In the first, we have a linearly ordered sequence of symbols that must be extrapolated. In the second we want to extrapolate an unordered set of finite strings. A very general formal solution to the first kind of problem is well known and much work has been done in obtaining good approximations to it [1, 3, 4, 5, 6, 9, 10]. Though the second kind of problem is of much practical importance, no general solution has been published. We present two general solutions for unordered data. We also show how machines can be constructed to summarize sequential and unordered data in optimum ways.

1964