Foundations of Probability Theory for AI - The Application of Algorithmic Probability to Problems in Artificial Intelligence

2013/03/27 by Ray Solomonoff, Solomonoff, Ray
Computer Science · #Artificial Intelligence (cs.AI) #FOS: Computer and information sciences #cs.AI

paper · pdf · doi:10.48550/arxiv.1304.3424

Appears in Proceedings of the First Conference on Uncertainty in Artificial Intelligence (UAI1985)

arxiv created 2013/03/27 · arxiv updated 2013/04/15

Abstract

This paper covers two topics: first an introduction to Algorithmic Complexity Theory: how it defines probability, some of its characteristic properties and past successful applications. Second, we apply it to problems in A.I. - where it promises to give near optimum search procedures for two very broad classes of problems.

Related

• Diverse Consequences of Algorithmic Probability
• The Mathematics of Artificial Intelligence
• Algorithmic statistics: forty years later
• Exceeding Computational Complexity Trial-and-Error Dynamic Action and Intelligence
• Complexity and intelligence