DocumentCode
1586243
Title
Compact polynomial modeling of the multi-layer perceptron
Author
Jiang, Xianping ; Chen, Mu-Song ; Manry, Michael T.
Author_Institution
Dept. of Electr. Eng., Texas Univ., Arlington, TX, USA
fYear
1992
Firstpage
791
Abstract
A technique for analyzing multilayer perceptron (MLP) neural networks is presented in which each hidden unit is modeled as a power series of the net function. This allows (1) pruning useless hidden units, (2) measuring the effect of removing a hidden layer, and (3) determining the degree of the overall polynomial discriminant (PD) which approximates the network. Classification and mapping networks are analyzed to illustrate the technique
Keywords
neural nets; polynomials; classification networks; hidden unit; mapping networks; multi-layer perceptron; neural networks; polynomial discriminant; polynomial modeling; power series; Electric variables measurement; Equations; Measurement units; Multi-layer neural network; Multilayer perceptrons; Network topology; Neural networks; Polynomials; Power measurement; Senior members;
fLanguage
English
Publisher
ieee
Conference_Titel
Signals, Systems and Computers, 1992. 1992 Conference Record of The Twenty-Sixth Asilomar Conference on
Conference_Location
Pacific Grove, CA
ISSN
1058-6393
Print_ISBN
0-8186-3160-0
Type
conf
DOI
10.1109/ACSSC.1992.269164
Filename
269164
Link To Document