Renyi entropy with respect to Choquet capacities

Author

Gader, Paul D. ; Lee, Wen-Hsiung ; Zha, Xuping

Author_Institution

Dept. of Comput. & Inf. Sci. & Eng., Florida Univ., Gainesville, FL, USA

Volume

1

fYear

2004

fDate

25-29 July 2004

Firstpage

529

Abstract

Entropy terms are analyzed for use in a heterogeneous network involving ordered weighted averaging (OWA) operators and feed-forward neural networks, referred to as FOWA networks. The OWA operators are used to aggregate feature information and were previously used successfully in a landmine application. Weight vectors of OWA operators are special cases of Choquet capacities for which the Shannon entropy has been defined. One can also consider the quadratic Renyi entropy for OWA weight vectors. A term is added to the objective function of the FOWA network involving these entropy terms. An analysis of the derivatives used in gradient descent is conducted.

Keywords

entropy; feature extraction; feedforward neural nets; mathematical operators; Choquet capacities; Shannon entropy; feature information; feed-forward neural networks; ordered weighted averaging operators; quadratic Renyi entropy; Computer networks; Entropy; Feedforward neural networks; Feedforward systems; Information analysis; Information science; Landmine detection; Neural networks; Open wireless architecture; Statistics;

fLanguage

English

Publisher

ieee

Conference_Titel

Fuzzy Systems, 2004. Proceedings. 2004 IEEE International Conference on

ISSN

1098-7584

Print_ISBN

0-7803-8353-2

Type

conf

DOI

10.1109/FUZZY.2004.1375789

Filename

1375789