贝叶斯网络应用中的结构学习方法研究

摘要/Abstract

摘要：

贝叶斯网络是用于表示不确定变量之间潜在依赖关系的图形模型。结构学习是贝叶斯网络学习的核心,有效的结构学习方法和算法是构建最优网络结构的基础。文中对迄今为止贝叶斯网络应用中的结构学习方法进行探讨,从复杂度、适用性等方面对其进行分析比较,并指出每种方法的关键环节和主要思想,对实际应用中的方法选择和研究提供了参考。

关键词: 贝叶斯网络;结构学习;完备数据;不完备数据

Abstract:

Bayesian network is the graphical model used to describe potential dependencies between uncertain variables.Structure learning is the core of Bayesian network learning.The effective learning methods and algorithms of structure learning are the foundation of constructing Bayesian network.In this paper,we summarize the present achievement on Bayesian network structure learning,with a thorough analysis of their complexity and application presented and some key aspects and main idea of the methods pointed out.The summary is helpful in selecting proper methods in practical applications.

Key words: bayesian network;structure learning;compete data;incomplete data

中图分类号:

张秀方,唐兴佳. 贝叶斯网络应用中的结构学习方法研究[J]. , 2014, 27(4): 179-.

ZHANG Xiufang,TANG Xingjia. Structure Learning Methods in Bayesian Network Application[J]. , 2014, 27(4): 179-.

参考文献

［1］PEARL J F.Propagation and structuring in belief networks［J］.Artificial Intelligence,1986,29(3):241-288.

［2］PAN H,LIU L.Fuzzy bayesian networks—a general formalism for representation,inference and learning with hybrid bayesian networks［J］.International Journal of Pattern Recognition and Artificial Intelligence,2000,14(07):941-962.

［3］COWELL R G,DAVID A P,LAURITZEN S L,et al,Probabilistic networks and expert systems［M］.Newyork:Springer Publications,1999.

［4］COX D R,WERMUTH N.Multivariate dependencies:models,analysis,and interpretation［M］.London:Chapman and Hall,1993.

［5］EDWARDS D.Introduction to graphical modelling［M］.Newyork:Springer-Verlag,1995.

［6］邢文训,谢金星.现代优化计算方法［M］.北京:清华大学出版社,1999.

［7］PEARL J.Probabilistic reasoning in intelligent systems［M］.San Mateo:Morgan Kaufmann,1988.

［8］LAURITZEN S L.Graphical models［M］.Oxford:Clarendon Press,1996.

［9］PEARL J.Probabilistic reasoning in intelligent systems［M］.San Mateo:Morgan Kaufmann,1988.

［10］BOUCHAERT R R.Belief networks construction using the minimum description length principle［J］.Lecture Note in Computer Science,1993,747:41-48.

［11］LAM W,BACCHUS F.Learning bayesian belief networks:an approach based on the MDL principle［J］.Computational Intelligence,1994(10):269-293.

［12］COOPER G,HERSKOVITS E.A bayesian method for the induction of bayesian networks from data［J］.Machine Learning,1992(9):309-347.

［13］SINGH M,VALTORTA M.Construction of bayesian network structures from data:a brief survey and an efficient algorithm［J］.International Journal of Approximate Reasoning,1995(12):111-131.

［14］CHICKERING D M.Learning equivalence classes of bayesian network structures［J］.Journal of Machine Learning Research,2002(2):445-498.

［15］Cowell R G,David A P,Lauritzen S L,et al.Probabilistic networks and expert systems［M］.Newyork:Springer Publications,1999.

［16］PEARL J.Causality［M］.Cambridge:Cambridge University Press,2000.

［17］SPIRTES P,GLYMOUR C,SCHEINES R.Causation,Prediction and Search［M］.Cambridge:MIT Press,2000.

［18］HECKERMAN D.A tutorial on learning with Bayesian networks［M］.Newyork:Springer Berlin Heidelberg,2008.

［19］VERMA T,PEARL J.Equivalence and synthesis of causal models［C］.Amsterdam,Proceedings of the 6th Conference on Uncertainty in Artificial Intelligence,1990.

［20］YU Jing,SMITH V A,WANG P P,Advances to bayesian network inference for generating causal network form observational biological data［J］.Bioinformatics,2004,20(18):3594-3603.

［21］GUROVSKII M Z,BIDYUK P I,TERENTS V A N.Methods ofconstructing bayesian network based on scoring functions［J］.Cybernetics and System Analysis,2008,44(2):219-224.

［22］YANG Shulin,CHENG Kuochu.Comparison of score metrics for bayesian network learning［J］.IEEE Trans.Man and Cybernetics-Part A:Systems and Humans,2002,32(3):419-428.

［23］SCHWARZ G.Estimating the dimension of a model［J］.Annals of Statistic,1978,7(2):461-464.

［24］COOPER G F,HERSKOVITS E A.Bayesian method for the induction of probabilistic network form data［J］.Machine Learning,1992,9(4):309-347.

［25］CHEN P C.A non-line-sight mitigation algorithm in location esfima［C］.New Orleans:IEEE Wireless Communifications and Networking Conference,1999.

［26］DUHAMEL C,POTVIN J Y,ROUSSEAU J M.A tabu search heuristic for the vehicle routing problem with backhauls and time windows［J］.Transportation Science,1997,31(1):49-59.

［27］CORDEAU J F,LAPORTE G,MERCIER A.A unified tabu search heuristic for vehicle routing problems with time windows［J］.Journal of the Operational Research Society,2001(6):928-936.

［28］BOHACHEVSKY I O,JOHNSON M E,STEIN M L.Generalized simulated annealing for function optimization［J］.Technometrics,1986,28(3):209-217.

［29］郭嗣宗,陈刚.信息科学中的软计算方法［M］.沈阳:东北大学出版社,2001.

［30］陈国良,王煦法,庄镇泉.遗传算法及其应用［M］.北京:人民邮电出版社,2001.

［31］MYERS J W,LASKEY K B,LEVITT T S.Learning bayesian networks from incomplete data with stochastic search algorithms［C］.Morgankaufmann,Stockholm,Sweden:Proeeedings of the 15th Conference on Uncertainty in Artifical Intelligence,1999.

［32］BOUCHAALA L,MASMOUDI A,GARGOURI F,et al.Improving algorithms for structure learning in BayesianNetworks using a new implicit score［J］.Expert Systems with Applications,2010,37(7):5470-5475.

［33］PERRIER E,IMOTO S,MIYANO S.Finding optimal bayesian network given a super-structure［J］.Journal of Machine Learning Research,2008,9(2):2251-2286.

［34］BORGELT C.A conditional independence algorithm for learning undirected graphical models［J］.Journal of Computer and System Sciences,2010,76(1):21-33.

［35］JI J Z,ZHANG H X,HU R B,et al.A bayesian network learning algorithm based on independence test and ant colony optimization［J］.Acta Automatica Sinica,2009,35(3):281-288.

[1]	唐兴佳, 张秀方. 基于ICA的多维贝叶斯分类器[J]. , 2014, 27(2): 25-.
[2]	孙良帅, 李秀峰. 求解非负矩阵分解的子空间共轭梯度算法[J]. , 2014, 27(1): 9-.
[3]	张秀方,唐兴佳. [J]. , 0, (): 179-.