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
fDate :
27 Jun-2 Jul 1994
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;
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
DOI :
10.1109/ICNN.1994.374426
