Ray Solomonoff
(1926-2009)
Ray Solomonoff invented algorithmic probability, which he called a General (or Universal) Theory of Inductive Inference. Anticipating the more recent work of
Gregory Chaitin, Solomonoff is known as the "father of algorithmic information theory."
His work led to the idea of
Kolmogorov Complexity - the length of the shortest computer program (in a defined programming language) that produces the object as output. It is a measure of the computational resources needed to specify the object. It is also the Shannon information contained in the text. All redundancy has been removed.
Solomonoff studied under
Rudolf Carnap and Enrico Fermi at the University of Chicago and graduated with an M.S. in Physics in 1951.
But the fundamental notion of
ontological possibilities and their probabilities (i.e., the idea that chance is real and the universe
indeterministic) was disliked by many mathematically and logically inclined scientists of the times. As a result, Solomonff's work was often ignored by his colleagues.
Solomonoff was a member of the elite group of computer scientists that in 1956 attended
John McCarthy's Dartmouth Summer Research Project on artificial intelligence.
Trenchard More, John McCarthy, Marvin Minsky, Oliver Selfridge, and Ray Solomonoff at the 50th anniversary.
Not Shown: Allen Newell, Claude Shannon, Nathaniel Rochester, Herbert Simon,
References
Wikipedia page
Solomonoff Publications
Normal |
Teacher |
Scholar
|
