# Solomonoff Induction

@inproceedings{Legg1997SolomonoffI, title={Solomonoff Induction}, author={Shane Legg}, year={1997} }

Solomonoff's induction method is an interesting theoretical model of what could be considered a perfect inductive inference system. Furthermore, it can be proven that a whole range of commonly used induction principles are computable approximations or special cases of Solomonoff's method. As such, Solomonoff induction provides us with a powerful and unifying perspective on the many diverse principles and methods that exist to deal with induction problems. The foundations of Solomonoff induction…

## 4 Citations

Universal Semimeasures: An Introduction

- Computer Science, Mathematics
- 2007

This work demonstrates the existence of universal semimeasure using a novel proof of the equivalence between enumerable semimeasures and processes, and defines a novel complexity measure, simulation complexity, which generalises monotone complexity.

The Relativity of Induction

- Computer ScienceArXiv
- 2020

The core problem of generalization is explored and it is shown that long-accepted Occam's razor and parsimony principles are insufficient to ground learning, and a set of relativistic principles are derived that yield clearer insight into the nature and dynamics of learning.

Formalizing preference utilitarianism in physical world models

- Computer ScienceSynthese
- 2015

This paper uses Bayesian inference to introduce a formalization of preference utilitarianism in physical world models, specifically cellular automata.

Investigations of galaxy clusters using gravitational lensing

- Physics
- 2014

In this dissertation, we discuss the properties of galaxy clusters that have been determined using strong and weak gravitational lensing. A galaxy cluster is a collection of galaxies that are bound…

## References

SHOWING 1-10 OF 10 REFERENCES

Inductive Reasoning and Kolmogorov Complexity

- Computer ScienceJ. Comput. Syst. Sci.
- 1992

The thesis is developed that Solomonoff's method is fundamental in the sense that many other induction principles can be viewed as particular ways to obtain computable approximations to it.

An Introduction to Kolmogorov Complexity and Its Applications

- Computer ScienceTexts and Monographs in Computer Science
- 1993

The book presents a thorough treatment of the central ideas and their applications of Kolmogorov complexity with a wide range of illustrative applications, and will be ideal for advanced undergraduate students, graduate students, and researchers in computer science, mathematics, cognitive sciences, philosophy, artificial intelligence, statistics, and physics.

Complexity-based induction systems: Comparisons and convergence theorems

- Computer ScienceIEEE Trans. Inf. Theory
- 1978

Levin has shown that if tilde{P}'_{M}(x) is an unnormalized form of this measure, and P( x) is any computable probability measure on strings, x, then \tilde{M}'_M}\geqCP (x) where C is a constant independent of x .

THE COMPLEXITY OF FINITE OBJECTS AND THE DEVELOPMENT OF THE CONCEPTS OF INFORMATION AND RANDOMNESS BY MEANS OF THE THEORY OF ALGORITHMS

- Computer Science
- 1970

The present article is a survey of the fundamental results connected with the concept of complexity as the minimum number of binary signs containing all the information about a given object that are sufficient for its recovery (decoding).

Solomonoff . Complexitybased induction systems : comparisons and convergence theorems

- IEEE Trans . IT -
- 1978

Solomonoff . A formal theory of inductive inference , Part 1 and Part 2

- Inform . and Control
- 1964

A formal theory of inductive inference, Part 1 and Part 2

- Inform. and Control
- 1964

A formal theory of inductive inference, Part 1 and Part 2, Inform. and Control

- 1964

A formal theory of inductive inference, Part 1 and Part 2

- Inform. and Control
- 1964