# A formal theory of inductive inference. Part I (II). In Brillouin et al., eds., Information and Control

**Publisher Information: **New York: Academic Press, 1964.

Solomonoff, Ray R. (1926-2009). A formal theory of inductive inference. Part I [II]. In Information and Control 7 (1964): 1-22; 224-254. Whole volume. 221 x 141 mm. Library buckram. Very good.

First Edition, journal issue. Solomonoff was a founder of the branch of AI based on machine learning, prediction and probability. He invented algorithmic probability, a mathematical method of assigning a prior probability to a given observation. He introduced this concept in a preliminary report published in 1960 and gave it a much fuller treatment in the present two-part paper, which is considered the beginning of algorithmic information theory. Prior to the 1960s, the usual method of calculating probability was based on frequency: taking the ratio of favorable results to the total number of trials. In his 1960 publication, and, more completely, in his 1964 publications, Solomonoff seriously revised this definition of probability. He called this new form of probability “Algorithmic Probability” and showed how to use it for prediction in his theory of inductive inference. As part of this work, he produced the philosophical foundation for the use of Bayes rule of causation for prediction [a method now known as Solomonoff’s induction] . . . In the years following his discovery of Algorithmic Probability he focused on how to use this probability and Solomonoff Induction in actual prediction and problem solving for A.I. (Wikipedia article on Solomonoff).

Solomonoff was one of the original 11 attendees at the 1956 Dartmouth Summer Research Conference on Artificial Intelligence, which introduced AI as a science.

**Book Id:**51683

**
Price:
$850.00
**