PASS: a program for automatic structure search

Author

Chen, Zhanbo ; Xiao, Jing ; Cheng, Jie

Author_Institution

Dept. of Comput. Sci., North Carolina Univ., Charlotte, NC, USA

Volume

1

fYear

1997

Firstpage

308

Abstract

We utilized the heuristic knowledge gained from a vast number of experiments on using feedforward neural networks (FNNs) to approximate highly nonlinear real-valued functions and developed a program for automatic search of FNNs based on evolutionary computation techniques, called PASS (program for automatic structure search). PASS has been successfully tested in an industrial application-finding FNNs to approximate the mappings between automobile engine control variables and performance parameters. It has shown the promise to be a general and efficient tool for automatic determination of FNNs for real-valued function approximation

Keywords

Newton method; backpropagation; feedforward neural nets; function approximation; genetic algorithms; internal combustion engines; multilayer perceptrons; neural net architecture; search problems; automatic structure search; automobile engine control; evolutionary computation techniques; feedforward neural networks; heuristic knowledge; highly nonlinear real-valued functions; Automatic control; Automobiles; Engines; Evolutionary computation; Feedforward neural networks; Function approximation; Fuzzy control; Industrial control; Neural networks; Testing;

fLanguage

English

Publisher

ieee

Conference_Titel

Neural Networks,1997., International Conference on

Print_ISBN

0-7803-4122-8

Type

conf

DOI

10.1109/ICNN.1997.611684

Filename

611684