Sciweavers

4007 search results - page 36 / 802
» Computation with imprecise probabilities
Sort
View
ICML
2006
IEEE
14 years 9 months ago
Qualitative reinforcement learning
When the transition probabilities and rewards of a Markov Decision Process are specified exactly, the problem can be solved without any interaction with the environment. When no s...
Arkady Epshteyn, Gerald DeJong
IJAR
2008
161views more  IJAR 2008»
13 years 8 months ago
Bayesian learning for a class of priors with prescribed marginals
We present Bayesian updating of an imprecise probability measure, represented by a class of precise multidimensional probability measures. Choice and analysis of our class are mot...
Hermann Held, Thomas Augustin, Elmar Kriegler
SIGMOD
2008
ACM
162views Database» more  SIGMOD 2008»
14 years 9 months ago
Event queries on correlated probabilistic streams
A major problem in detecting events in streams of data is that the data can be imprecise (e.g. RFID data). However, current state-ofthe-art event detection systems such as Cayuga ...
Christopher Ré, Dan Suciu, Julie Letchner, ...
ISIPTA
2003
IEEE
106views Mathematics» more  ISIPTA 2003»
14 years 2 months ago
Continuous Linear Representation of Coherent Lower Previsions
This paper studies the possibility of representing lower previsions by continuous linear functionals. We prove the existence of a linear isomorphism between the linear space spann...
Sebastian Maaß
EUSFLAT
2009
173views Fuzzy Logic» more  EUSFLAT 2009»
13 years 6 months ago
Application of Zadeh's Impossibility Principle to Approximate Explanation
Abstract: We consider application of Zadeh's impossibility principle and extended logic FLe to approximate scientific explanation from the standpoint of the philosophy of scie...
Vesa A. Niskanen