Canonical PWL network and multilayer perceptron-like networks: A unified view

Author

Lin, Ji-Nan ; Unbehauen, Rolf

Author_Institution

Lehrstuhl fuer Allgemeine & Theoretische Elektrotech., Erlangen-Nurnberg Univ., Erlangen, Germany

fYear

1993

fDate

3-6 May 1993

Firstpage

2588

Abstract

The authors consider the behavior of the most popular type of mapping networks, the multilayer perceptron-like (MLPL) networks in implementing or approximating functions, in terms of the canonical piecewise-linear (PWL) functions. They show that a MLPL network may be understood as performing a canonical PWL function or a PWL function which is a composition of the canonical PWL functions. The discussion further suggests a generalized class of the canonical-PWL (CPWL) networks, i.e., networks which perform a canonical PWL function or a composition of the canonical PWL functions, which includes all layered feedforward networks where the nonlinearity of the units is represented or approximately represented by a PWL function

Keywords

feedforward neural nets; function approximation; multilayer perceptrons; piecewise-linear techniques; canonical piecewise-linear functions; function approximation; layered feedforward networks; mapping networks; multilayer perceptron-like networks; nonlinearity; Adaptive signal processing; Approximation methods; Biological system modeling; Biomedical signal processing; Multidimensional signal processing; Nonhomogeneous media; Pattern recognition; Piecewise linear techniques; Signal mapping; Signal processing algorithms;

fLanguage

English

Publisher

ieee

Conference_Titel

Circuits and Systems, 1993., ISCAS '93, 1993 IEEE International Symposium on

Conference_Location

Chicago, IL

Print_ISBN

0-7803-1281-3

Type

conf

DOI

10.1109/ISCAS.1993.394295

Filename

394295