scispace - formally typeset
Open AccessJournal ArticleDOI

Characterizing the principle of minimum cross-entropy within a conditional-logical framework

Gabriele Kern-Isberner
- 01 Jan 1998 - 
- Vol. 98, Iss: 1, pp 169-208
TLDR
In this paper, it is shown how probabilistic conditionals allow a new and constructive approach to the principle of minimum cross-entropy, and four principles that describe their handling in a reasonable and consistent way are developed.
About
This article is published in Artificial Intelligence.The article was published on 1998-01-01 and is currently open access. It has received 107 citations till now. The article focuses on the topics: Principle of maximum entropy & Prior probability.

read more

Citations
More filters
Journal ArticleDOI

Common sense and maximum entropy

TL;DR: It is argued that within the rather narrow context in which this complete and consistent mode of uncertain reasoning is actually characterised by the observance of just a single common sense principle (or slogan).
Journal ArticleDOI

Combining probabilistic logic programming with the power of maximum entropy

TL;DR: It turns out that both approaches to probabilistic logic programming under maximum entropy have very nice nonmonotonic features and satisfy the property of rational monotonicity and several irrelevance properties.
Journal ArticleDOI

A Thorough Axiomatization of a Principle of Conditional Preservation in Belief Revision

TL;DR: A thorough axiomatization of a principle of conditional preservation in a very general framework, considering the revision of epistemic states by sets of conditionals, based on a nonstandard approach to conditionals which focuses on their dynamic aspects, and uses the newly introduced notion of conditional valuation functions as representations of Epistemic states.
Posted Content

Unifying Computing and Cognition: The SP Theory and its Applications

TL;DR: This book develops the conjecture that all kinds of information processing in computers and in brains may usefully be understood as "information compression by multiple alignment, unification and search".
Journal ArticleDOI

Conditional logic and the principle of entropy

TL;DR: The conditional three-valued logic of Calabrese is applied to the language L ∗ of conditionals on propositional variables with finite domain, which enables large-scale applications in the expert system-shell SPIRIT.
References
More filters
Book

Theory of probability

TL;DR: In this paper, the authors introduce the concept of direct probabilities, approximate methods and simplifications, and significant importance tests for various complications, including one new parameter, and various complications for frequency definitions and direct methods.
Book

Combinatorial Group Theory

TL;DR: In this article, the authors introduce the concept of Free Products with Amalgamation (FPAM) and Small Cancellation Theory over free products with amalgamation and HNN extensions.
Journal ArticleDOI

Axiomatic derivation of the principle of maximum entropy and the principle of minimum cross-entropy

TL;DR: Jaynes's principle of maximum entropy and Kullbacks principle of minimum cross-entropy (minimum directed divergence) are shown to be uniquely correct methods for inductive inference when new information is given in the form of expected values.
Related Papers (5)