What question did this study set out to answer?

To explore the properties of the correntropy function and its applications in non-Gaussian signal processing.

Correntropy: Properties and Applications in Non-Gaussian Signal Processing

View Full Paper

Ask AI

Bookmark

Authors

Demonstrates the effectiveness of correntropy in non-Gaussian signal processing, indicating its advantages over traditional methods.

To explore the properties of the correntropy function and its applications in non-Gaussian signal processing.
Defined the correntropy function as a localized similarity measure.
Established a relationship between correntropy and M-estimation.
Presented examples to illustrate the effectiveness of correntropy in impulsive noise environments.
Correntropy shows vastly different properties compared to second-order statistics in non-Gaussian settings.
It is particularly effective in processing signals affected by impulsive noise.
Connections with kernel methods highlight unique advantages of correntropy.

Liu et al. (2007) studied this question.

View Full Paper

Ask AI

Bookmark