A Formal Theory of Inductive Inference, Part II

Solomonoff, R. J. (1964). A Formal Theory of Inductive Inference, Part II. Information and Control, 7(2), 224-254.

Type

Journal article

Intellectual base

Primary research

Year

1964

DOI

10.1016/s0019-9958(64)90131-7

Link

https://doi.org/10.1016/S0019-9958(64)90223-2

Cited from

information_theory, mathematics, philosophy, systems_cybernetics

Cited by

6 citations across 5 artifacts.

Each citation links to the sentence it supports in the citing article.

Primes

• Complexity
  • Kolmogorov complexity (independently defined by Solomonoff, Kolmogorov, Chaitin in the 1960s) measures the length of the shortest program generating a string, providing an information-theoretic foundation independent of any specific machine

    This sourceThree independent foundations of Kolmogorov complexity (shortest program generating a string; machine-independent).

• Compression
  • The construct manages the complexity of representing large information streams by providing algorithms parameterized by source model and distortion constraint, by tying representation size to the underlying entropy (a deep connection to probability theory)

    This sourceFounds algorithmic probability and universal inductive inference, tying predictive probability to shortest description. SUPPORTS marker 177 only loosely — the marker sits on 'tying representation size to the underlying entropy (a deep connection to probability theory)'; Solomonoff supplies the algorithmic-probability link, defensible but indirect for the entropy-size claim. DOI verified. See flag.

• Parsimony (Occam's Razor)
  • and Solomonoff universal induction

    This source(Originating treatment of algorithmic probability and universal inductive inference; establishes theoretical foundations for learning from data; parallel independent work to Kolmogorov and Chaitin.)

• Randomness
  • and Solomonoff (1964)

    This source(Originating treatment of algorithmic probability and universal inductive inference; establishes theoretical foundations for learning from data; parallel independent work to Kolmogorov and Chaitin.)

Domain-specific

• Solomonoff Induction
  • It combines Bayesian prediction with algorithmic probability: retain all programmatic explanations compatible with the observations, weight shorter programs more heavily, and average their implied continuations rather than selecting only one model.

Verification

This reference passed the adversarial substantiation pipeline: it was checked to exist and to support the claim it is attached to. See how references were verified.

Links previously used in the corpus

Before the registry existed this work was also linked 2 other ways.

• https://doi.org/10.1016/S0019-9958(64)90131-7 ×1
• https://doi.org/10.1145/321356.321363 ×1

Registry ID ref:a13e898e5a41 · see in the full table