5/26/2020 Correntropy: Properties and Applications in Non-Gaussian Signal Processing - IEEE Journals & Magazine

IEEE.org IEEE Xplore IEEE-SA IEEE Spectrum More Sites SUBSCRIBE SUBSCRIBE Cart Create Account
Personal Sign In 

 Browse  My Settings  Help  Institutional Sign In

Institutional Sign In

All  

ADVANCED SEARCH

Journals & Magazines > IEEE Transactions on Signal P... > Volume: 55 Issue: 11

Correntropy: Properties and Applications in Non-Gaussian

Signal Processing
Publisher: IEEE Cite This Cite This  PDF

3 Author(s) Weifeng Liu ; Puskal P. Pokharel ; Jose C. Principe All Authors

More Like This

Export to

Collabratec A statistical analysis of the affine projection

662
Paper
6407
Full
View References Alerts algorithm for unity step size and
autoregressive inputs
Citations Text Views IEEE Transactions on Circuits and Systems
Manage I: Regular Papers
Published: 2005
Content Alerts

Detection of non-Gaussian signals: a

Add to paradigm for modern statistical signal
processing
Citation Alerts
Proceedings of the IEEE
Published: 1994

Show More

Abstract
Top Organizations with Patents
Downl
Document Sections on Technologies Mentioned in
PDF
This Article
I. Introduction
Abstract: The optimality of second-order statistics depends heavily on the assumption
II. Brief Background
of Gaussianity. In this paper, we elucidate further the probabilistic and geometric
on ITL and Kernel
meaning of... View more
Methods

III. Definition and Metadata

Properties of Abstract:
Cross The optimality of second-order statistics depends heavily on the assumption of 
Correntropy Gaussianity. In this paper, we elucidate further the probabilistic and geometric meaning
of the recently defined correntropy function as a localized similarity measure. A close
IV. Comparison
relationship between correntropy and M-estimation is established. Connections and
between MSE
differences between correntropy and kernel methods are presented. As such
and Correntropy
correntropy has vastly different properties compared with second-order statistics that
V. Applications can be very useful in non-Gaussian signal processing, especially in the impulsive noise
environment. Examples are presented to illustrate the technique.

Authors
Published in: IEEE Transactions on Signal Processing ( Volume: 55 , Issue: 11 , Nov.
Figures 2007 )

https://ieeexplore.ieee.org/document/4355325 1/3
5/26/2020 Correntropy: Properties and Applications in Non-Gaussian Signal Processing - IEEE Journals & Magazine
References Page(s): 5286 - 5298 INSPEC Accession Number: 9671130

Citations Date of Publication: 22 October 2007 DOI: 10.1109/TSP.2007.896065

Keywords ISSN Information: Publisher: IEEE

Metrics

More Like This

Contents

I. Introduction
Second-Order statistics in the form of correlation and in particular the
mean square error (MSE) are probably the most widely utilized
methodologies for quantifying how similar two random variables are.
Successful engineering solutions from these methodologies rely heavily
on the Gaussianity and linearity assumptions. Recently, our group has
extended the concept of mean square error adaptation to include
information theoretic criteria
Sign[1],
in to
which
Continue
has been
Reading
named information
theoretic learning (ITL). ITL preserves the nonparametric nature of
correlation learning and MSE adaptation, i.e., the cost function is still
directly estimated from data via a Parzen kernel estimator [2], but it
extracts more information from the data for adaptation, and yields,
therefore, solutions that are more accurate than MSE in non-Gaussian
and nonlinear signal processing [3]–[8].

Authors 
Figures 
References 
Citations 
Keywords 
Metrics 

IEEE Personal Account Purchase Details Profile Information Need Help? Follow

CHANGE USERNAME/PASSWORD PAYMENT OPTIONS COMMUNICATIONS PREFERENCES US & CANADA: +1 800 678 4333   
VIEW PURCHASED DOCUMENTS PROFESSION AND EDUCATION WORLDWIDE: +1 732 981 0060

TECHNICAL INTERESTS CONTACT & SUPPORT

About IEEE Xplore | Contact Us | Help | Accessibility | Terms of Use | Nondiscrimination Policy | Sitemap | Privacy & Opting Out of Cookies
A not-for-profit organization, IEEE is the world's largest technical professional organization dedicated to advancing technology for the benefit of humanity.

© Copyright 2020 IEEE - All rights reserved. Use of this web site signifies your agreement to the terms and conditions.

IEEE Account Purchase Details Profile Information Need Help?

» Change Username/Password » Payment Options » Communications Preferences » US & Canada: +1 800 678 4333
» Update Address » Order History » Profession and Education » Worldwide: +1 732 981 0060
» View Purchased Documents » Technical Interests » Contact & Support

https://ieeexplore.ieee.org/document/4355325 2/3
5/26/2020 Correntropy: Properties and Applications in Non-Gaussian Signal Processing - IEEE Journals & Magazine
About IEEE Xplore | Contact Us | Help | Accessibility | Terms of Use | Nondiscrimination Policy | Sitemap | Privacy & Opting Out of Cookies

A not-for-profit organization, IEEE is the world's largest technical professional organization dedicated to advancing technology for the benefit of humanity.
© Copyright 2020 IEEE - All rights reserved. Use of this web site signifies your agreement to the terms and conditions.

https://ieeexplore.ieee.org/document/4355325 3/3