An adaptive kernel width update for correntropy
Authors:
- 1 June 2012
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- No. 21614393,p. 1-5
Abstract
Correntropy, as an adaptive criterion of Information Theoretic Learning (ITL), has been successfully used in signal processing and machine learning. How to appropriately select the kernel width of correntropy is a crucial problem in correntropy applications. Existing kernel width selection methods are not suitable enough for this problem. In this paper, we develop an adaptive method for kernel width selection in correntropy. Based on the Middleton's non-Gaussian models, this method utilizes the kurtosis as a ratio to adjust the standard deviation of the prediction error to obtain the kernel width online. The superior performance of the new method has been demonstrated by simulation examples in the noisy frequency doubling and echo cancelation problems.Keywords
This publication has 14 references indexed in Scilit:
- Kernel adaptive filtering with maximum correntropy criterion2011
- Information theoretic learning with adaptive kernelsSignal Processing, 2011
- A fixed point update for kernel width adaptation in information theoretic criteria2010
- Using Correntropy as a cost function in linear adaptive filters2009
- Correntropy: Properties and Applications in Non-Gaussian Signal ProcessingIEEE Transactions on Signal Processing, 2007
- The Plenacoustic Function and Its SamplingIEEE Transactions on Signal Processing, 2006
- Generalized correlation function: definition, properties, and application to blind equalizationIEEE Transactions on Signal Processing, 2006
- A Brief Survey of Bandwidth Selection for Density EstimationJournal of the American Statistical Association, 1996
- Biased and Unbiased Cross-Validation in Density EstimationJournal of the American Statistical Association, 1987
- Statistical-Physical Models of Electromagnetic InterferenceIEEE Transactions on Electromagnetic Compatibility, 1977