There is a reason for everything (probably): on the application of maxent to induction

Authors:
Jeff B. Paris;Alena Vencovská
Affiliations:
Department of Mathematics, University of Manchester, Manchester, UK;Department of Mathematics, University of Manchester, Manchester, UK
Venue:
WCII'02 Proceedings of the 2002 international conference on Conditionals, Information, and Inference
Year:
2002

Citing 6
Cited 1

A note on the inevitability of maximum entropy

International Journal of Approximate Reasoning
Reasoning about knowledge and probability

Journal of the ACM (JACM)
Reasoning about knowledge

Reasoning about knowledge
Asymptotic Conditional Probabilities: The Unary Case

SIAM Journal on Computing
The uncertain reasoner's companion: a mathematical perspective

The uncertain reasoner's companion: a mathematical perspective
From statistical knowledge bases to degrees of belief

Artificial Intelligence

The emergence of reasons conjecture

Journal of Applied Logic - Special issue on combining probability and logic

Quantified Score

Hi-index	0.00

Visualization

Abstract

In this paper we show how the maxent paradigm may be used to produce an inductive method (in the sense of Carnap) applicable to a wide class of problems in inductive logic. A surprising consequence of this method is that the answers it gives are consistent with, or explicable by, the existence of underlying reasons for the given knowledge base, even when no such reasons are explicitly present. We would conjecture that the same result holds for the full class of problems of this type.