DocumentCode :
991042
Title :
Multiple model regression estimation
Author :
Cherkassky, Vladimir ; Ma, Yunqian
Author_Institution :
Dept. of Electr. & Comput. Eng., Univ. of Minnesota, Minneapolis, MN, USA
Volume :
16
Issue :
4
fYear :
2005
fDate :
7/1/2005 12:00:00 AM
Firstpage :
785
Lastpage :
798
Abstract :
This paper presents a new learning formulation for multiple model estimation (MME). Under this formulation, training data samples are generated by several (unknown) statistical models. Hence, most existing learning methods (for classification or regression) based on a single model formulation are no longer applicable. We describe a general framework for MME. Then we introduce a constructive support vector machine (SVM)-based methodology for multiple regression estimation. Several empirical comparisons using synthetic and real-life data sets are presented to illustrate the proposed approach for multiple model regression formulation.
Keywords :
learning (artificial intelligence); regression analysis; support vector machines; learning formulation; multiple model regression estimation; statistical model; support vector machine; Classification tree analysis; Learning systems; Mars; Predictive models; Regression tree analysis; Robustness; Supervised learning; Support vector machine classification; Support vector machines; Training data; Learning formulation; multiple model estimation (MME); regression; robust estimation; support vector machines (SVMs); Algorithms; Artificial Intelligence; Cluster Analysis; Computer Simulation; Computing Methodologies; Models, Biological; Models, Statistical; Numerical Analysis, Computer-Assisted; Pattern Recognition, Automated; Stochastic Processes;
fLanguage :
English
Journal_Title :
Neural Networks, IEEE Transactions on
Publisher :
ieee
ISSN :
1045-9227
Type :
jour
DOI :
10.1109/TNN.2005.849836
Filename :
1461422
Link To Document :
بازگشت