Filters








145,144 Hits in 5.6 sec

A Markov random field model for term dependencies

Donald Metzler, W. Bruce Croft
2005 Proceedings of the 28th annual international ACM SIGIR conference on Research and development in information retrieval - SIGIR '05  
This paper develops a general, formal framework for modeling term dependencies via Markov random fields. The model allows for arbitrary text features to be incorporated as evidence.  ...  The results show significant improvements are possible by modeling dependencies, especially on the larger web collections. Information retrieval, term dependence, phrases, Markov random fields tions.  ...  Acknowledgments This work was supported in part by the Center for Intelligent Information Retrieval and in part by Advanced Research and Development Activity and NSF grant #CCF-0205575.  ... 
doi:10.1145/1076034.1076115 dblp:conf/sigir/MetzlerC05 fatcat:o3gdmhwp7jdz5hc5mjbkfd2bm4

Randomized and Distributed Self-Configuration of Wireless Networks: Two-Layer Markov Random Fields and Near-Optimality

S Jeon, C Ji
2010 IEEE Transactions on Signal Processing  
A local model is a two-layer Markov Random Field (i.e., a random bond model) that approximates the global model with the local spatial dependence of neighbors.  ...  Index Terms-Near-optimality, randomized and distributed management, self-configuration, two-layer Markov Random Field.  ...  ACKNOWLEDGMENT The authors would like to thank anonymous reviewers for helpful comments. C. Ji would like to thank C. S. Ji and J. Modestino for helpful discussions on Markov Random Fields.  ... 
doi:10.1109/tsp.2010.2051806 fatcat:3ylb2npzhzdofjyuqehrjijyfy

Probabilistic graphs using coupled random variables [article]

Kenric P. Nelson, Madalina Barbu, Brian J. Scannell
2014 arXiv   pre-print
A coupled Markov random field is designed for the inferencing and classification of UCI's MLR 'Multiple Features Data Set' such that thousands of linear correlation parameters can be replaced with a single  ...  A generalization of Bayes rule using the coupled product enables a single node to model correlation between hundreds of random variables.  ...  ACKNOWLEDGEMENTS The authors benefited from discussion with Sabir Umarov and Fred Daum regarding modeling long range dependence with nonextensive statistical mechanics.  ... 
arXiv:1404.6955v1 fatcat:ufyf5grrbzamjcfl5mxcpdkdiy

Random Fields in Physics, Biology and Data Science

Enrique Hernández-Lemus
2021 Frontiers in Physics  
For strictly positive probability densities, a Markov random field is also a Gibbs field, i.e., a random field supplemented with a measure that implies the existence of a regular conditional distribution  ...  A random field is the representation of the joint probability distribution for a set of random variables.  ...  (Markov Random Fields: A Theoretical Framework).  ... 
doi:10.3389/fphy.2021.641859 fatcat:2bi74vqkureefmtzwinma2yiwq

A recursive algorithm for Markov random fields

F. Bartolucci
2002 Biometrika  
full conditional distributions, as occurs for Markov random fields.  ...  ; Full conditional; Graphical model; Hidden Markov chain; Markov chain Monte Carlo; Markov random field; Monotone coupling from the past. 2  ...  Acknowledgements We are grateful to the editor and a referee for their helpful suggestions.  ... 
doi:10.1093/biomet/89.3.724 fatcat:sbmy7s5lh5aojja5rm5efiyvfm

Page 1566 of Mathematical Reviews Vol. , Issue 94c [page]

1994 Mathematical Reviews  
In this paper the Stein-Chen method for Poisson approximation is extended to give estimates for the accuracy of approximation of functionals of random fields of indicator random variables with weak dependence  ...  The Slepian models have, for stationary ergodic processes, simple interpretations in terms of empirical distributions.  ... 

Using Bayesian response surface updating for estimating the covariance function of random fields based on limited measurements [chapter]

P Criel, R Caspeele, L Taerwe
2014 Safety, Reliability, Risk and Life-Cycle Performance of Structures and Infrastructures  
A Markov chain is defined as a sequence of random variables ! for which the distribution of ! depends only on the previous sample !!! , i.e. not on !!! , !!! , etc. (Gelman et al., 2003) .  ...  RANDOM FIELDS Basic concepts A random field , ∈ is a function whose values are random variables for any position in the domain Ω ∈ ℝ ! .  ... 
doi:10.1201/b16387-780 fatcat:6ift24ofnvfh7jk7s7j7hey4i4

Page 4499 of Mathematical Reviews Vol. , Issue 93h [page]

1993 Mathematical Reviews  
The equivalence of a minimal sufficient statistic and a canonical nearest-neighbor Gibbs potential is obtained for arbitrary Markov chains and for Markov fields which are exponential families.”  ...  The technique is applied to estimate the variance of the sample intensity of a binary Markov random field, and the variance of an index of clumping for spatial point processes studied by quadrat methods  ... 

Markov Processes and Slope Series: The Scale Problem, A Comment

R. P. Haining
2010 Geographical Analysis  
This may be due to the fact that there are a number of alternative models for generating two-dimensional random fields. Matern [3], for example, noted that a process of the form - - + — a?  ...  This model is similar to (3.a) for p small.  ... 
doi:10.1111/j.1538-4632.1977.tb00564.x fatcat:gyg6mrqne5bsnmvdmmg3eebwga

Sequence Labeling using Conditional Random Fields

Romansha Chopra, Nivedita Singh, Yang Zhenning, N.Ch.S.N. Iyengar
2017 International Journal of u- and e- Service, Science and Technology  
Conditional random fields (CRFs), is a scheme for building probabilistic models to divide and tag sequence data.  ...  A machine learning technique termed as Conditional Random Fields, which is designed for sequence labeling will be used in order to take advantage of the surrounding context.  ...  This methodology will be a combination of both Conditional Random Fields and Hidden Markov Model.  ... 
doi:10.14257/ijunesst.2017.10.9.10 fatcat:pofo2sdqazgfjgt3bvnsn5ibmi

Spatial Markov processes for modeling Lagrangian particle dynamics in heterogeneous porous media

Tanguy Le Borgne, Marco Dentz, Jesus Carrera
2008 Physical Review E  
It expresses particle movements as a random walk in space time characterized by a correlated random temporal increment and thus generalizes the continuous time random walk model to transport in correlated  ...  characterize these complex velocity field organizations, ͑ii͒ classical effective transport descriptions that rely on Markov processes in time for the particle velocities are not suited for describing  ...  The Markov model is defined for a spatial increment x = / 2.  ... 
doi:10.1103/physreve.78.026308 pmid:18850937 fatcat:lcz2kn6x3fgo3k2uyu46qnekyu

Efficient recursions for general factorisable models

R. Reeves, A. N. Pettitt
2004 Biometrika  
We show how a lag-r model represents a Markov random field and allows a neighbourhood structure to be related to the unnormalised joint likelihood.  ...  If each subset contains at most r + 1 of the n components in the joint distribution, we term this a lag-r model, whose normalising constant can be computed using a forward recursion in O(S r+1 ) computations  ...  A general factorisable model as a Markov random field A Markov random field on a set of nodes {1, . . . , n} is defined by conditional probabilities for each node that depend only on a subset of the remaining  ... 
doi:10.1093/biomet/91.3.751 fatcat:3njdv7j36ney5d24zwkb35z2j4

JPR volume 34 issue 3 Cover and Back matter

1997 Journal of Applied Probability  
AALTO, SAMULI Characterization of the output rate' process for a Markovian storage model ANDERSSON, HAKAN and BRITTON, TOM Heterogeneity in epidemic models and its effect on the spread of infection ANDERSSON  ...  A series expansion approach to the inverse problem BAUERLE, NICOLE and ROLSKI, TOMASZ A monotonicity result for the workload in Markov-modulated queues BAXTER, LAURENCE A.  ...  , FRANCIS and JANZURA, MARTIN A central limit theorem for conditionally centered random fields with an application to Markov fields COMTET, ALAIN, MONTHUS, CECILE and YOR, MARC Exponential functionals  ... 
doi:10.1017/s0021900200101524 fatcat:bxy3crxjyfdm7opqpbsxqvz4fm

Efficient mapping through exploitation of spatial dependencies

Y. Rachlin, J.M. Dolan, P. Khosla
2005 2005 IEEE/RSJ International Conference on Intelligent Robots and Systems  
To account for such dependencies, we model the environment as a pairwise Markov random field.  ...  Index Terms-occupancy grids, belief propagation, markov random fields, demining  ...  Spatial dependencies can be modeled, and in this paper we seek to do this through a Markov random field [2] .  ... 
doi:10.1109/iros.2005.1545118 dblp:conf/iros/RachlinDK05 fatcat:iyo6ykeisvbcth7nns56gq2jgq

Inference and parameter estimation on hierarchical belief networks for image segmentation

Christian Wolf, Gérald Gavin
2010 Neurocomputing  
A parametric distribution depending on a single parameter allows the design of a fast inference algorithm on graph cuts, whereas for arbitrary distributions, we propose inference with loopy belief propagation  ...  We introduce a new causal hierarchical belief network for image segmentation. Contrary to classical tree structured (or pyramidal) models, the factor graph of the network contains cycles.  ...  We propose therefore a new model, which combines the advantages of causal hierarchical models with the shift invariance of stationary Markov random fields.  ... 
doi:10.1016/j.neucom.2009.07.017 fatcat:wg6ouvai4faujcclucfsakqqyi
« Previous Showing results 1 — 15 out of 145,144 results