Filters








229 Hits in 2.6 sec

Ergo: A Graphical Environment for Constructing Bayesian [article]

Ingo Beinlich, Edward H. Herskovits
2013 arXiv   pre-print
We present an introduction to Bayesian belief networks, discuss algorithms for inference with these networks, and delineate the classes of problems that can be solved with this paradigm.  ...  Algorithms for belief-network inference, such as those developed by Pearl [Pearl 1986; Suermondt 1988 ] and Lauritzen and Spiegelhalter [Lauritzen 1988 ], allow the user to instantiate values for some  ...  The Lauritzen-Spiegelhalter algorithm rearranges the network into a tree by form ing clusters of nodes (cliques).  ... 
arXiv:1304.1095v1 fatcat:756nqytpc5hbrattioqqeg2htu

Iterative Multiagent Probabilistic Inference

Xiangdong An, Nick Cercone
2006 2006 IEEE/WIC/ACM International Conference on Intelligent Agent Technology  
Multiply sectioned Bayesian networks (MSBNs) support multiagent probabilistic inference in distributed large problem domains, where agents are organized in a tree structure (called hypertree).  ...  In this paper, we present an iterative method where multiple agents asynchronously perform belief updating in a complete parallel.  ...  Extension of Shenoy-Shafer architecture to MSBNs for LJF based inference has also been discussed [23] . Hugin architecture is a modification of Lauritzen-Spiegelhalter architecture.  ... 
doi:10.1109/iat.2006.83 dblp:conf/iat/AnC06a fatcat:vue6k4kuifai7paiiue6jvdlpm

A combination of exact algorithms for inference on Bayesian belief networks

H.Jacques Suermondt, Gregory F. Cooper
1991 International Journal of Approximate Reasoning  
Cutset conditioning and clique-tree propagation are two popular methods for exact probabilistic inference in Bayesian belief networks.  ...  We describe a means to combine cutset conditioning and clique-tree propagation in an approach called aggregation after decomposition (AD), which can perform inference relatively efficiently for certain  ...  Andersen for stimulating discussions about this work. Lyn Dupr6 gave insightful comments on earlier versions of this document.  ... 
doi:10.1016/0888-613x(91)90028-k fatcat:dwev4vpxcng2li3kvezikj6hse

Belief networks revisited

Judea Pearl
1993 Artificial Intelligence  
versatility and power and are now considered the most common representation scheme for probabilistic knowledge.  ...  pictures, to perform filtering, smoothing and prediction, to facilitate planning in uncertain environments, and to study causation, nonmonotonicity, action, change, and attention, l The following is a  ...  Lauritzen and Spiegelhalter [ 14 ] , and later Jensen et al.  ... 
doi:10.1016/0004-3702(93)90169-c fatcat:wbbmxq64rzf5hkorhzjdhn7rgy

Logarithmic Time Parallel Bayesian Inference [article]

David M. Pennock
2013 arXiv   pre-print
I present a parallel algorithm for exact probabilistic inference in Bayesian networks.  ...  For polytree networks with n variables, the worst-case time complexity is O(log n) on a CREW PRAM (concurrent-read, exclusive-write parallel random-access machine) with n processors, for any constant number  ...  The popular junction tree algorithm for multiply connected networks (Jensen, Lauritzen, and Olesen 1990; Lauritzen and Spiegelhalter 1988; Neapolitan 1990; Spiegelhalter, Dawid, Lauritzen, and Cowell  ... 
arXiv:1301.7406v1 fatcat:ch7ehex4ajcohf4qyzvniaekgi

Probabilistic Inferences in Bayesian Networks [article]

Jianguo Ding
2010 arXiv   pre-print
This paper sums up various inference techniques in Bayesian networks and provide guidance for the algorithm calculation in probabilistic inference in Bayesian networks.  ...  Bayesian network is a complete model for the variables and their relationships, it can be used to answer probabilistic queries about them.  ...  Another popular exact Bayesian network inference algorithm is Lauritzen and Spiegelhalter's clique-tree propagation algorithm [Lauritzen & Spiegelhalter, 1988] .  ... 
arXiv:1011.0935v2 fatcat:xhsl5wkbpvfkberywap5zxeysm

Probabilistic Inferences in Bayesian Networks [chapter]

Jianguo Ding
2010 Bayesian Network  
Acknowledgment This work is supported by ERCIM (the European Research Consortium for Informatics and Mathematics). References  ...  Another popular exact Bayesian network inference algorithm is Lauritzen and Spiegelhalter's clique-tree propagation algorithm (Lauritzen & Spiegelhalter, 1988) .  ...  algorithms exist for Bayesian networks (Lauritzen & Spiegelhalter, 1988 ) (Pearl, 1988) (Pearl, 2000) (Neal, 1993) .  ... 
doi:10.5772/46968 fatcat:v6stpe6dtfarles636fpga7mca

Local Learning in Probabilistic Networks with Hidden Variables

Stuart J. Russell, John Binder, Daphne Koller, Keiji Kanazawa
1995 International Joint Conference on Artificial Intelligence  
Probabilistic networks which provide compact descriptions of complex stochastic relationships among several random variables are rapidly becoming the tool of choice for uncertain reasoning in artificial  ...  intelligence We show that networks with fixed structure containing hidden variables can be learned automatically from data using a gradient-descent mechanism similar to that used in neural networks We  ...  simple local algorithm for training the network allows one to use the same network and algorithms for both training and inference Furthermore the similarity to real biological processes lends a certain  ... 
dblp:conf/ijcai/RussellBKK95 fatcat:qtwcj5tvyrdc7cuonhpdpdq5da

Dynamic Data Feed to Bayesian Network Model and SMILE Web Application

Nipat Jongsawat, Pittaya Poompuang, Wichian Premchaiswadi
2008 2008 Ninth ACIS International Conference on Software Engineering, Artificial Intelligence, Networking, and Parallel/Distributed Computing  
Lauritzen and Spiegelhalter, Jensen et al, and Dawid proposed an efficient algorithm that first transforms a Bayesian network into a tree where each node in the tree corresponds to a subset of variables  ...  in the original graph (Lauritzen & Spiegelhalter, 1988; Jensen et al., 1990; Dawid, 1992) .  ...  They provide a language that supports efficient algorithms for the automatic construction of expert systems in several different contexts.  ... 
doi:10.1109/snpd.2008.67 dblp:conf/snpd/JongsawatPP08 fatcat:p3ei2ffpxrcrxjhrbwn2ovxtau

Error-Correcting and Verifiable Parallel Inference in Graphical Models

Negin Karimi, Petteri Kaski, Mikko Koivisto
2020 PROCEEDINGS OF THE THIRTIETH AAAI CONFERENCE ON ARTIFICIAL INTELLIGENCE AND THE TWENTY-EIGHTH INNOVATIVE APPLICATIONS OF ARTIFICIAL INTELLIGENCE CONFERENCE  
We present a novel framework for parallel exact inference in graphical models.  ...  The computational complexity of inference essentially matches the cost of w-cutset conditioning, a known generalization of Pearl's classical loop-cutset conditioning for inference.  ...  While polynomial-time algorithms are known for special cases, most notably for models where the underlying graph has bounded treewidth (Lauritzen and Spiegelhalter 1988; Zhang and Poole 1994; Dechter  ... 
doi:10.1609/aaai.v34i06.6580 fatcat:avzrzy2ctbavvdz2rj2bjvohpi

Designing a Bayesian network for preventive maintenance from expert opinions in a rapid and reliable way

G. Celeux, F. Corset, A. Lannoy, B. Ricard
2006 Reliability Engineering & System Safety  
It describes a causal representation of the phenomena involved in the degradation process. Inference from such a BN needs to specify a great number of marginal and conditional probabilities.  ...  In this study, a Bayesian Network (BN) is considered to represent a nuclear plant mechanical system degradation.  ...  We can cite the well-known 'junction tree' algorithm (see Lauritzen and Spiegelhalter[10] , Cowell [6] for instance).  ... 
doi:10.1016/j.ress.2005.08.007 fatcat:4szd2jotfvcv3diugdnog4uvse

Global Conditioning for Probabilistic Inference in Belief Networks [chapter]

Ross D. Shachter, Stig.K. Andersen, Peter Szolovits
1994 Uncertainty Proceedings 1994  
Nonetheless, this approach provides new opportunities for parallel processing and, in the case of sequential processing, a tradeoff of time for memory.  ...  In this paper we propose a new approach to probabilistic inference on belief networks, global conditioning, which is a simple generalization of Pearl's (1986b) method of loopcutset conditioning.  ...  We have a finite set of elements N = {1, . . . , n}, corresponding to the nodes in a directed acyclic graph.  ... 
doi:10.1016/b978-1-55860-332-5.50070-5 fatcat:ad64awnw25dophb5n4yg6vosgq

Global Conditioning for Probabilistic Inference in Belief Networks [article]

Ross D. Shachter, Stig K. Andersen, Peter Szolovits
2013 arXiv   pre-print
Nonetheless, this approach provides new opportunities for parallel processing and, in the case of sequential processing, a tradeoff of time for memory.  ...  In this paper we propose a new approach to probabilistic inference on belief networks, global conditioning, which is a simple generalization of Pearl's (1986b) method of loopcutset conditioning.  ...  INTRODUCTION In recent years, there have been intense research efforts to develop efficient methods for probabilistic inference on belief networks.  ... 
arXiv:1302.6843v1 fatcat:tbemsn2agve3xkrlktlpiz6xbi

A Review of Inference Algorithms for Hybrid Bayesian Networks

Antonio Salmerón, Rafael Rumí, Helge Langseth, Thomas D. Nielsen, Anders L. Madsen
2018 The Journal of Artificial Intelligence Research  
In this paper we provide an overview of the main trends and principled approaches for performing inference in hybrid Bayesian networks.  ...  However, this extra feature also comes at a cost: inference in these types of models is computationally more challenging and the underlying models and updating procedures may not even support closed-form  ...  AMIDST has received funding from the European Union's Seventh Framework Programme for research, technological development and demonstration under grant agreement no 619209.  ... 
doi:10.1613/jair.1.11228 fatcat:vhmuf44ftbg73mjygiyrwrdw44

Strategy Generation Under Uncertainty Using Bayesian Networks and Black Box Optimization

Eli Faulkner
2007 2007 IEEE Symposium on Computational Intelligence in Multi-Criteria Decision-Making  
We describe a mechanism for optimal strategy generation from a Bayesian Belief Network (BBN). This system takes a BBN model either created by the user or derived from data.  ...  The user then specifies a set of goals (consisting of both objectives and constraints) and the observed and actionable variables in the model.  ...  Throughout this paper, our Bayesian inference approach follows the algorithm proposed by Lauritzen and Spiegelhalter [5] .  ... 
doi:10.1109/mcdm.2007.369418 dblp:conf/cimcdm/Faulkner07 fatcat:3orlf6ktxbecjiu665lttb7bnu
« Previous Showing results 1 — 15 out of 229 results