652,934 Hits in 5.8 sec

Value of Evidence on Influence Diagrams [article]

Kazuo J. Ezawa
2013 arXiv   pre-print
In this paper, we introduce evidence propagation operations on influence diagrams and a concept of value of evidence, which measures the value of experimentation.  ...  Evidence propagation operations are critical for the computation of the value of evidence, general update and inference operations in normative expert systems which are based on the influence diagram (  ...  We can compute the value of perfect information and value of control from the values of evidence. We also discussed that the efficient methods for the computation of value of evidence.  ... 
arXiv:1302.6805v1 fatcat:cfgnpfymmrbj5llv4srqdtx7ti

Evaluating influence diagrams with decision circuits [article]

Debarun Bhattacharjya, Ross D. Shachter
2012 arXiv   pre-print
Although a number of related algorithms have been developed to evaluate influence diagrams, exploiting the conditional independence in the diagram, the exact solution has remained intractable for many  ...  In this paper we introduce decision circuits as a means to exploit the local structure usually found in decision problems and to improve the performance of influence diagram analysis.  ...  We thank John Weyant for his support, the UCLA Automated Reasoning Group for the use of their software, and the anonymous reviewers for their feedback.  ... 
arXiv:1206.5257v1 fatcat:uttievh3nfehlafuf23feennni

Using Potential Influence Diagrams for Probabilistic Inference and Decision Making [article]

Ross D. Shachter, Pierre Ndilikilikesha
2013 arXiv   pre-print
In particular, we show how to convert a potential influence diagram into a conditional influence diagram, and how to view the potential influence diagram operations in terms of the conditional influence  ...  In this paper, we explore the relationship between potential and conditional influence diagrams and provide insight into the properties of the potential influence diagram.  ...  Acknowledgments We appreciate the helpful comments of Bill Poland and the anonymous referees.  ... 
arXiv:1303.1500v1 fatcat:fubbmcq32ffp7gqgf7oz3u74b4

Sensitivity analysis in decision circuits [article]

Debarun Bhattacharjya, Ross D. Shachter
2012 arXiv   pre-print
Decision circuits have been developed to perform efficient evaluation of influence diagrams [Bhattacharjya and Shachter, 2007], building on the advances in arithmetic circuits for belief network inference  ...  available to compute the value of information for the uncertainties in the problem and the effects of changes to model parameters on the value and the optimal strategy.  ...  ANALYZING NORMAL FORM INFLUENCE DIAGRAMS When there is only one decision node in an influence diagram and it has no parents, the diagram is said to be in normal form.  ... 
arXiv:1206.3551v1 fatcat:qddxvm5d5nemjinpop7i4eljlu

A Method for Using Belief Networks as Influence Diagrams [article]

Gregory F. Cooper
2013 arXiv   pre-print
More generally, knowing the relationship between belief-network and influence-diagram problems may be useful in the design and development of more efficient influence diagram algorithms.  ...  This paper demonstrates a method for using belief-network algorithms to solve influence diagram problems.  ...  ACKNOWLEDGEMENTS I wish to thank Jaap Suermondt, Lyn Dupre, and the Workshop reviewers for valuable comments on this paper.  ... 
arXiv:1304.2346v1 fatcat:rrgufdldqzgmro5haku5tqvcju

Dynamic programming in in uence diagrams with decision circuits [article]

Ross D. Shachter, Debarun Bhattacharjya
2012 arXiv   pre-print
Decision circuits perform efficient evaluation of influence diagrams, building on the ad- vances in arithmetic circuits for belief net- work inference [Darwiche, 2003; Bhattachar- jya and Shachter, 2007  ...  We show how even more compact decision circuits can be con- structed for dynamic programming in influ- ence diagrams with separable value functions and conditionally independent subproblems.  ...  the probability of the evidence about any of the variables, including the value variables.  ... 
arXiv:1203.3513v1 fatcat:ffz5uvd5zzhqvmtghxu2emhrpi

Model-based Influence Diagrams for Machine Vision [article]

Tod S. Levitt, John Mark Agosta, Thomas O. Binford
2013 arXiv   pre-print
We show an approach to automated control of machine vision systems based on incremental creation and evaluation of a particular family of influence diagrams that represent hypotheses of imagery interpretation  ...  evaluating the final influence diagram that contains all random variables created during the run of the vision system.  ...  Model Guided Influence Diagram Construction The influence diagram formalism with which we build the model-base allows three kinds of nodes; probability nodes, value nodes and decision nodes.  ... 
arXiv:1304.1517v1 fatcat:qhf5i3c5dbcrjafftpbwmogc4u

Decision Making Using Probabilistic Inference Methods [article]

Ross D. Shachter, Mark Alan Peot
2013 arXiv   pre-print
The analysis of decision making under uncertainty is closely related to the analysis of probabilistic inference.  ...  Indeed, much of the research into efficient methods for probabilistic inference in expert systems has been motivated by the fundamental normative arguments of decision theory.  ...  ACKNOWLEDGEMENTS We benefitted greatly from the comments and suggestions of Stig Andersen, David Heckerman, Prakash Shenoy, the two anonymous referees, and a number of students in the EES department This  ... 
arXiv:1303.5428v1 fatcat:u2ptmnnm4jf3tmpcmbuyfsy2aa

The Myth of Modularity in Rule-Based Systems [article]

David Heckerman, Eric J. Horvitz
2013 arXiv   pre-print
We show that the assumption of semantic modularity imposes strong restrictions on rules in a knowledge base. We argue that such restrictions are rarely valid in practical applications.  ...  In this paper, we examine the concept of modularity, an often cited advantage of the ruled-based representation methodology.  ...  Another difference is that propositions in an influence diagram can take on any number (possibly infinite) of mutually exclusive and exhaustive values.  ... 
arXiv:1304.3090v1 fatcat:sn37ctq54jfrdj7s5uoci3a22e

Evidence Absorption and Propagation through Evidence Reversals [article]

Ross D. Shachter
2013 arXiv   pre-print
The arc reversal/node reduction approach to probabilistic inference is extended to include the case of instantiated evidence by an operation called "evidence reversal."  ...  This not only provides a technique for computing posterior joint distributions on general belief networks, but also provides insight into the methods of Pearl [1986b] and Lauritzen and Spiegelhalter [1988  ...  This probabilistic influence diagram with evidence nodes corresponds exactly to belief networks, and from here on, they will be referred to as belief diagrams.  ... 
arXiv:1304.1525v1 fatcat:h25w25ssoza5fdawtvkrgfkt7u

Decision analysis with influence diagrams using Elvira's explanation facilities

Manuel Luque, Francisco Javier Díez
2006 European Workshop on Probabilistic Graphical Models  
Influence diagrams have proved to be effective tools for building decision-support systems, but explanation of their reasoning is difficult, because inference in probabilistic graphical models seems to  ...  The current paper describes some explanation capabilities for influence diagrams and how they have been implemented in Elvira, a public software tool.  ...  Manuel Luque has also been partially supported by Department of Education of the Comunidad de Madrid and the European Social Fund (ESF).  ... 
dblp:conf/pgm/LuqueD06 fatcat:oexscsmao5eehlcrqxycl7wnxu

Combining Defense Graphs and Enterprise Architecture Models for Security Analysis

Teodor Sommestad, Mathias Ekstedt, Pontus Johnson
2008 2008 12th International IEEE Enterprise Distributed Object Computing Conference  
The framework also takes uncertainties of the security assessment into consideration. Moreover, using the extended influence diagram formalism the expected loss from each attack can be calculated.  ...  Security is dependent on a mixture of interrelated concepts such as technical countermeasures, organizational policies, security procedures, and more.  ...  Extended Influence Diagrams support probabilistic inference in the same manner as Bayesian networks do; given the value of one node, the values of related nodes can be inferred.  ... 
doi:10.1109/edoc.2008.37 dblp:conf/edoc/SommestadEJ08 fatcat:2byyxlhuwbaptl2o7s4qndcpkq

Influence Diagrams for Contextual Information Retrieval [chapter]

Lynda Tamine-Lechani, Mohand Boughanem
2006 Lecture Notes in Computer Science  
The purpose of contextual information retrieval is to make some exploration towards designing user specific search engines that are able to adapt the retrieval model to the variety of differences on user's  ...  In this paper we propose an influence diagram based retrieval model which is able to incorporate contexts, viewed as user's long-term interests into the retrieval process.  ...  Ackowledgments This research was partially supported by the French Ministry of Research and New Technolologies under the ACI program devoted to Data Masses (ACI-MD), project MD-33.  ... 
doi:10.1007/11735106_42 fatcat:em7k3u2nofcpjlid3kl2dnc2ku

Directed Reduction Algorithms and Decomposable Graphs [article]

Ross D. Shachter, Stig K. Andersen, Kim-Leng Poh
2013 arXiv   pre-print
diagram.  ...  Many people have concluded that the best methods are those based on undirected graph structures, and that those methods are inherently superior to those based on node reduction operations on the influence  ...  Acknowledgements We are grateful for the comments and suggestions of Richard Barlow, Stephen Chyu, and Robert Fung. References  ... 
arXiv:1304.1110v1 fatcat:si3puxhz6vfdhpoucaagriwzdq

Three new sensitivity analysis methods for influence diagrams [article]

Debarun Bhattacharjya, Ross D. Shachter
2012 arXiv   pre-print
Specifically, we show how to efficiently compare strategies in decision situations, perform sensitivity to risk aversion and compute the value of perfect hedging [Seyller, 2008].  ...  Performing sensitivity analysis for influence diagrams using the decision circuit framework is particularly convenient, since the partial derivatives with respect to every parameter are readily available  ...  An influence diagram represents a total ordering of the decisions, which enforces a partial order on the uncertainties.  ... 
arXiv:1203.3467v1 fatcat:6pjubmna45bvdhg2bdlfwye23e
« Previous Showing results 1 — 15 out of 652,934 results