Analysis of Feature Extraction Criterion Function Maximum in Nonlinear Multi-layer Feedforward Neural Networks for Pattern Recognition

Author

Junhong, Cao ; Zhuobin, Wei ; Tao, Huang ; Xianwei, Xiong

Author_Institution

Dept. of Logistics Command & Eng., Naval Univ. of Eng., Tianjin, China

Volume

1

fYear

2010

fDate

11-12 May 2010

Firstpage

655

Lastpage

658

Abstract

This paper addresses feature extraction criterion function of multi-layer feed forward neural networks with linear output units and nonlinear hidden units. From the minimum mean square error function of the network output, the paper uses the nature of matrix trace and singular value decomposition, deduces the formula for calculating the nonlinear criterion function maximum, then explains the significance of this formula. Finally, simulation examples prove the correctness of the analytic style.

Keywords

feature extraction; feedforward neural nets; least mean squares methods; matrix algebra; multilayer perceptrons; pattern recognition; singular value decomposition; feature extraction criterion function maximum analysis; matrix trace; minimum mean square error function; multilayer perceptrons; nonlinear criterion function maximum; nonlinear multilayer feedforward neural networks; pattern recognition; singular value decomposition; Feature extraction; Feedforward neural networks; Feeds; Matrix decomposition; Mean square error methods; Multi-layer neural network; Neural networks; Pattern analysis; Pattern recognition; Singular value decomposition; criterion function maximum; feature extraction; multi-layer feedforward neural network; pattern recognition;

fLanguage

English

Publisher

ieee

Conference_Titel

Intelligent Computation Technology and Automation (ICICTA), 2010 International Conference on

Conference_Location

Changsha

Print_ISBN

978-1-4244-7279-6

Electronic_ISBN

978-1-4244-7280-2

Type

conf

DOI

10.1109/ICICTA.2010.193

Filename

5522992