AIMar 27, 2013
Foundations of Probability Theory for AI - The Application of Algorithmic Probability to Problems in Artificial Intelligence
arXiv:1304.3424v19.497 citations
Originality Synthesis-oriented
AI Analysis
It addresses foundational probability theory for AI, offering potential improvements in search algorithms, but appears incremental as it builds on existing algorithmic probability concepts.
The paper introduces algorithmic complexity theory and applies it to AI, promising near-optimum search procedures for two broad problem classes.
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.