What is algorithmic probability?

Algorithmic Probability

In algorithmic information theory, algorithmic (Solomonoff) probability is a method of assigning a probability to each hypothesis (algorithm/program) that explains a given observation, with the simplest hypothesis (the shortest program) having the highest probability and the increasingly complex hypotheses (longer programs) receiving increasingly small probabilities. These probabilities form a priori a probability distribution for the observation, which Ray Solomonoff proved to be machine-invariant (called the invariance theorem) and can be used with Bayes' theorem to predict the most likely continuation of that observation. A theoretic computer, the universal Turing machine, is used for the computer operations.

Read more about Algorithmic Probability.

Some articles on algorithmic probability:

Algorithmic Probability
... In algorithmic information theory, algorithmic (Solomonoff) probability is a method of assigning a probability to each hypothesis (algorithm/program) that ... These probabilities form a priori a probability distribution for the observation, which Ray Solomonoff proved to be machine-invariant (called the invariance theorem ... Solomonoff invented the concept of algorithmic probability with its associated invariance theorem around 1960 ...
Ray Solomonoff - Work History — The Later Years
... Originally algorithmic induction methods extrapolated ordered sequences of strings ... and began research on new applications of Algorithmic Probability ... Algorithmic Probability and Solomonoff Induction have many advantages for Artificial Intelligence ...

Famous quotes containing the word probability:

    Liberty is a blessing so inestimable, that, wherever there appears any probability of recovering it, a nation may willingly run many hazards, and ought not even to repine at the greatest effusion of blood or dissipation of treasure.
    David Hume (1711–1776)