DocumentCode :
3576387
Title :
Efficient learning of general Bayesian network Classifier by Local and Adaptive Search
Author :
Sein Minn ; Shunkai Fu ; Desmarais, Michel C.
Author_Institution :
Coll. of Comput. Sci. & Technol., Huaqiao Univ., Xiamen, China
fYear :
2014
Firstpage :
385
Lastpage :
391
Abstract :
General Bayesian network classifier (GBNC) contains only features necessary for classification, so an ideal structure learning solution is to learn GBNC without having to learn the whole Bayesian network (BN). A local search based algorithm called LAS-GBNC is proposed. Given faithfulness assumption, LAS-GBNC relies on the information about each variable´s appearance in the so-called d-separator(cut set) to sort candidate CI tests dynamically, performing `effective´ ones with priority. Experimental studies indicate that (1) LAS-GBNC achieves the same quality of networks as PC and IPC-BNC, (2)It is much more efficient than PC due to its local search design, and (3) It is obviously faster than IPC-BNC because of its adaptive search strategy.
Keywords :
belief networks; learning (artificial intelligence); pattern classification; LAS-GBNC; adaptive search based algorithm; candidate CI tests; d-separator; general Bayesian network classifier; local search based algorithm; structure learning solution; Adaptive systems; Bayes methods; Cascading style sheets; Educational institutions; Knowledge discovery; Markov processes; Prediction algorithms; Bayes classifier; Bayesian Network classifier; Bayesian network; Markov blanket; constraint learning;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Data Science and Advanced Analytics (DSAA), 2014 International Conference on
Type :
conf
DOI :
10.1109/DSAA.2014.7058101
Filename :
7058101
Link To Document :
بازگشت