A Philosophical Treatise of Universal Induction

Abstract

Understanding inductive reasoning is a problem that has engaged mankind for thousands of years. This problem is relevant to a wide range of fields and is integral to the philosophy of science. It has been tackled by many great minds ranging from philosophers to scientists to mathematicians, and more recently computer scientists. In this article we argue the case for Solomonoff Induction, a formal inductive framework which combines algorithmic information theory with the Bayesian framework. Although it achieves excellent theoretical results and is based on solid philosophical foundations, the requisite technical knowledge necessary for understanding this framework has caused it to remain largely unknown and unappreciated in the wider scientific community. The main contribution of this article is to convey Solomonoff induction and its related concepts in a generally accessible form with the aim of bridging this current technical gap. In the process we examine the major historical contributions that have led to the formulation of Solomonoff Induction as well as criticisms of Solomonoff and induction in general. In particular we examine how Solomonoff induction addresses many issues that have plagued other inductive systems, such as the black ravens paradox and the confirmation problem, and compare this approach with other recent approaches.

72 pages, 2 figures, 1 table, LaTeX

References in corpus (4)

• Adaptive Online Prediction by Following the Perturbed Leader
• Similarity of Objects and the Meaning of Words
• Algorithmic Complexity Bounds on Future Prediction Errors
• Algorithmic Information Theory: a brief non-technical guide to the field

Cited by in corpus (26)

• Entropy-based Logic Explanations of Neural Networks
• Thermodynamic costs of Turing Machines
• The Minimum Description Length Principle for Pattern Mining: A Survey
• On the Origin of Samples: Attribution of Output to a Particular Algorithm
• Can Intelligence Explode?
• Deep neural networks have an inbuilt Occam's razor
• Towards common-sense reasoning via conditional simulation: legacies of Turing in Artificial Intelligence
• Efficiency at optimal work from finite reservoirs: a probabilistic perspective
• A Dilemma for Solomonoff Prediction
• Is SGD a Bayesian sampler? Well, almost
• Causal Analysis of Agent Behavior for AI Safety
• A Minimal Active Inference Agent
• Free Lunch for Optimisation under the Universal Distribution
• Resolving Spurious Correlations in Causal Models of Environments via Interventions
• Bayesian Causal Induction
• On the Computability of Solomonoff Induction and Knowledge-Seeking
• Multiclass classification utilising an estimated algorithmic probability prior
• Don't choose theories: Normative inductive reasoning and the status of physical theories
• Applying Deutsch's concept of good explanations to artificial intelligence and neuroscience -- an initial exploration
• On the Computability of AIXI
• On the inherent competition between valid and spurious inductive inferences in Boolean data
• Applications of Algorithmic Probability to the Philosophy of Mind
• Principles of Solomonoff Induction and AIXI
• The Relativity of Induction
• On Nicod's Condition, Rules of Induction and the Raven Paradox
• Probabilities on Sentences in an Expressive Logic