Uncertainty in Artificial Intelligence
First Name   Last Name   Password   Forgot Password   Log in!
    Proceedings         Authors   Author's Info   Article details         Search    
General Belief Measures
Emil Weydert
Abstract:
Probability measures by themselves ,are known to be inappropriate for modeling the dynamics of plain belief and their excessively strong measurability constraints make them unsuitable for some representational tasks, e.g. in the context of firstorder knowledge. In this paper, we are therefore going to look for possible alternatives and extensions. We begin by delimiting the general area of interest, proposing a minimal list of assumptions to be satisfied by any reasonable quasi-probabilistic valuation concept. Within this framework, we investigate two particularly interesting kinds of quasi-measures which are not or much less affected by the traditional problems. * Ranking measures, which generalize Spohn-type and possibility measures. * Cumulative measures, which combine the probabilistic and the ranking philosophy, allowing thereby a fine-grained account of static and dynamic belief.
Keywords: Qualitative probability, possibility functions, rankings, generalized belief measures
Pages: 575-582
PS Link: ftp://ftp.mpi-sb.mpg.de/pub/guide/staff/weydert/publications/General-Belief-Measures-
PDF Link: /papers/94/p575-weydert.pdf
BibTex:
@INPROCEEDINGS{Weydert94,
AUTHOR = "Emil Weydert ",
TITLE = "General Belief Measures",
BOOKTITLE = "Proceedings of the Tenth Conference Annual Conference on Uncertainty in Artificial Intelligence (UAI-94)",
PUBLISHER = "Morgan Kaufmann",
ADDRESS = "San Francisco, CA",
YEAR = "1994",
PAGES = "575--582"
}


hosted by DSL   •   site info   •   help