Ray Solomonoff (born 1926) invented the concept of algorithmic probability around 1960. Take a universal computer and randomly generate an input program. The program will generate some possibly infinite output.
The algorithmic probability of any given finite output prefix q is the sum of the probabilities of the programs that compute something starting with q.
Algorithmic probability is the main ingredient of Solomonoff's theory of inductive inference, the theory of prediction based on observations. Given a sequence of symbols -- which will come next? Solomonoff's theory provides an answer that is optimal in a certain sense.
Unlike Karl Popper's informal theory, Solomonoff's is mathematically sound.
Algorithmic probability is closely related to the concept of Kolmogorov complexity. In fact, Solomonoff was the first to prove the invariance theorem, which shows that it is not really important which computer we use.
Ray Solomonoff's Homepage (http://world.std.com/~rjs/ray.html)
Our apologies, but you must have JavaScript enabled to view author contact information.
Kolmogorov, Chaitin, and Solomonoff independently came up with the idea of representing the complexity of a string based on its compressibility by representing it as a program.
Given a Universal Turing Machine U, the algorithmic information content, also called algorithmic complexity or Kolmogorov Complexity (KC) H(X) of string X is defined as the length of the shortest program p on U producing string X.
Feeds |
Contact