Uncertainty Theories: a Unified View

Didier Dubois (1)

1 IRIT-ADRIA - Argumentation, Décision, Raisonnement, Incertitude et Apprentissage

The variability of physical phenomena and partial ignorance about them motivated the development of probability theory in the two last centuries. However, the mathematical framework of probability theory, together with Bayesian credo claiming the inevitability of unique probability measures for representing agents beliefs, have blurred the distinction between variability and ignorance. Modern theories of uncertainty, by putting together probabilistic and set-valued representations of information, provide a better account of various facets of uncertainty.

Domaines: Intelligence artificielle [cs.AI]

Didier Dubois. Uncertainty Theories: a Unified View. Cybernetic Systems conference (2007), Sep 2007, Dublin, Ireland. pp.4-94. ⟨hal-03445671⟩