New Incremental Learning Algorithm With Support Vector Machines
- 31 January 2018
- journal article
- research article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Systems, Man, and Cybernetics: Systems
- Vol. 49 (11) , 2230-2241
Abstract
Incremental learning is one of the most effective methods of learning accumulated data and large-scale data. The newly increased samples of the previously known works on incremental learning are usually independent and identically distributed. To study how dependent sampling methods influence the learning ability of incremental support vector machines (ISVM) algorithm, in this paper we introduce an ISVM based on Markov resampling (MR-ISVM), and give the experimental research on the learning ability of the MR-ISVM algorithm. The experimental results indicate that the MR-ISVM algorithm has not only smaller misclassification rates and sparser of the obtained classifiers, but also less total time of sampling and training compared to ISVM based on randomly independent sampling. We also compare it with other ISVM algorithms.Keywords
Funding Information
- Natural Science Foundation of China Project (61403132, 61370002, 61772011)
- Natural Science Foundation of Hubei Province (2015CFB404)
- Natural Sciences and Engineering Research Council of Canada (GPIN-2016-05024)
- National Natural Science Foundation of China (11690014)
This publication has 26 references indexed in Scilit:
- An online incremental learning support vector machine for large-scale dataNeural Computing and Applications, 2012
- The incremental learning algorithm with support vector machine based on hyperplane-distanceApplied Intelligence, 2009
- ONLINE LEARNING WITH MARKOV SAMPLINGAnalysis and Applications, 2009
- Learning from dependent observationsJournal of Multivariate Analysis, 2009
- Consistency of Support Vector Machines and Other Regularized Kernel ClassifiersIEEE Transactions on Information Theory, 2005
- Statistical behavior and consistency of classification methods based on convex risk minimizationThe Annals of Statistics, 2004
- Capacity of reproducing kernel spaces in learning theoryIEEE Transactions on Information Theory, 2003
- On the mathematical foundations of learningBulletin of the American Mathematical Society, 2001
- Concentration of measure inequalities for Markov chains and $\Phi$-mixing processesThe Annals of Probability, 2000
- Theory of reproducing kernelsTransactions of the American Mathematical Society, 1950