Kernel Extreme Learning Machine Based Domain Adaptation
- 1 November 2018
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 593-597
Abstract
In this paper, a new domain adaptation learning method is proposed by jointing weighted balanced feature matching and instance reweighting based on kernel extreme learning machine (KELM). Specifically, for the weighted balance feature matching, it can not only adapt the importance of the difference between the marginal and the condition, but also deal with the class imbalances adaptively for the domain adaptation learning. In addition, the instance reweighting is combined to reduce the effect of unrelated instances on inter domain differences in source domain instances. The experimental results show the performance of the proposed approach is better than the state-of-the-art approaches in terms of the classification accuracy and operation speed, especially in the speed of operation is particularly prominent.Keywords
This publication has 9 references indexed in Scilit:
- Extreme learning machine based transfer learning for data classificationNeurocomputing, 2016
- An Insight into Extreme Learning Machines: Random Neurons, Random Features and KernelsCognitive Computation, 2014
- Extreme Learning Machine for Regression and Multiclass ClassificationIEEE Transactions on Systems, Man, and Cybernetics, Part B (Cybernetics), 2011
- Domain Adaptation via Transfer Component AnalysisIEEE Transactions on Neural Networks, 2010
- Domain Adaptation Problems: A DASVM Classification Technique and a Circular Validation StrategyIEEE Transactions on Pattern Analysis and Machine Intelligence, 2009
- Extreme learning machine: Theory and applicationsNeurocomputing, 2006
- Improved extreme learning machine for function approximation by encoding a priori informationNeurocomputing, 2006
- Artificial neural networks: a tutorialComputer, 1996
- Support-vector networksMachine Learning, 1995