DocumentCode
288544
Title
Genetic synthesis of piecewise-linear neural networks
Author
Estévez, Pablo A. ; Okabe, Yoichi
Author_Institution
Res. Center for Adv. Sci. & Technol., Tokyo Univ., Japan
Volume
3
fYear
1994
fDate
27 Jun-2 Jul 1994
Firstpage
1783
Abstract
A genetic algorithm is used to partially synthesize the structure of a piecewise-linear neural network appropriate for a given set of input-output examples. The networks studied are composed of linear weighted sum units and weightless switching operators, such as maximum and minimum. The procedure allows one to find the weight, type and location of every linear weighted sum unit but left unsolved the weightless switch nodes. The module can be useful as preprocessor. An application example to the modeling of the normality of electrocardiograms is provided
Keywords
electrocardiography; genetic algorithms; medical computing; neural nets; electrocardiograms; genetic algorithm; linear weighted sum units; piecewise-linear neural networks; weightless switching operators; Boolean functions; Electronic mail; Equations; Explosions; Feedforward neural networks; Genetic algorithms; Network synthesis; Neural networks; Piecewise linear techniques; Switches;
fLanguage
English
Publisher
ieee
Conference_Titel
Neural Networks, 1994. IEEE World Congress on Computational Intelligence., 1994 IEEE International Conference on
Conference_Location
Orlando, FL
Print_ISBN
0-7803-1901-X
Type
conf
DOI
10.1109/ICNN.1994.374426
Filename
374426
Link To Document