DocumentCode
1825142
Title
Learning from examples with Renyi´s information criterion
Author
Principe, Jose C. ; Xu, Dongxin
Author_Institution
Comput. NeuroEng. Lab., Florida Univ., Gainesville, FL, USA
Volume
2
fYear
1999
fDate
24-27 Oct. 1999
Firstpage
966
Abstract
This paper discusses a novel algorithm to train linear or nonlinear systems with information theoretic criteria (entropy or mutual information) directly from a training set. The method is based on Renyi´s quadratic definition of entropy and a distance measure based on the Cauchy-Schwartz inequality.
Keywords
entropy; estimation theory; linear systems; nonlinear systems; Cauchy-Schwartz inequality; Renyi´s information criterion; distance measure; entropy; information theoretic criteria; linear systems; mutual information; nonlinear systems; quadratic definition; training set; Entropy; Information analysis; Information processing; Information theory; Laboratories; Mutual information; Neural engineering; Nonlinear systems; Pattern recognition; Probability distribution;
fLanguage
English
Publisher
ieee
Conference_Titel
Signals, Systems, and Computers, 1999. Conference Record of the Thirty-Third Asilomar Conference on
Conference_Location
Pacific Grove, CA, USA
ISSN
1058-6393
Print_ISBN
0-7803-5700-0
Type
conf
DOI
10.1109/ACSSC.1999.831853
Filename
831853
Link To Document