Surprise-Based Qualitative Probabilistic Networks

Authors:
Zina M. Ibrahim;Ahmed Y. Tawfik;Alioune Ngom
Affiliations:
School of Computer Science, University of Windsor, Windsor, Canada N9B 3P4;School of Computer Science, University of Windsor, Windsor, Canada N9B 3P4;School of Computer Science, University of Windsor, Windsor, Canada N9B 3P4
Venue:
ECSQARU '09 Proceedings of the 10th European Conference on Symbolic and Quantitative Approaches to Reasoning with Uncertainty
Year:
2009

Citing 8
Cited 0

Fundamental concepts of qualitative probabilistic networks

Artificial Intelligence
Defaults and probabilities: extensions and coherence

Proceedings of the first international conference on Principles of knowledge representation and reasoning
Qualitative probabilities for default reasoning, belief revision, and causal modeling

Artificial Intelligence
A general non-probabilistic theory of inductive reasoning

UAI '88 Proceedings of the Fourth Annual Conference on Uncertainty in Artificial Intelligence
Pivotal Pruning of Trade-offs in QPNs

UAI '00 Proceedings of the 16th Conference on Uncertainty in Artificial Intelligence
Ranking functions and rankings on languages

Artificial Intelligence
Introducing situational signs in qualitative probabilistic networks

International Journal of Approximate Reasoning
Incremental tradeoff resolution in qualitative probabilistic networks

UAI'98 Proceedings of the Fourteenth conference on Uncertainty in artificial intelligence

Quantified Score

Hi-index	0.00

Visualization

Abstract

This paper discusses a modification of the kappa measure of surprise and uses it to build semi-qualitative probabilistic networks. The new measure is designed to enable the definition of partial-order relations on its conditional values and is hence used to define qualitative influences over the edges of the network, similarly to Qualitative Probabilistic Networks. The resulting networks combine the advantages of kappa calculus of robustness and ease of assessment and the efficiency of Qualitative Probabilistic Networks. The measure also enables a built-in tradeoff resolution mechanism for the proposed network.