Title :
A constructive neural network algorithm for function approximation
Author :
Draelos, Tim ; Hush, Don
Author_Institution :
Sandia Nat. Labs., Albuquerque, NM, USA
Abstract :
A study of the approximation capabilities of single hidden layer neural networks leads to a strong motivation for investigating constructive learning techniques as a means of realizing established error bounds. Learning characteristics employed by constructive algorithms provide ideas for development of new algorithms applicable to the function approximation problem. A novel constructive algorithm, the iterative incremental function approximation (IIFA) algorithm is presented in detail. The algorithm operates in polynomial time and is demonstrated on one and two dimensional function approximation problems
Keywords :
computational complexity; function approximation; iterative methods; neural nets; constructive neural network algorithm; established error bounds; iterative incremental function approximation; polynomial time algorithm; single hidden layer neural networks; Approximation algorithms; Approximation error; Computer errors; Costs; Function approximation; Iterative algorithms; Laboratories; Neural networks; Polynomials; Weather forecasting;
Conference_Titel :
Neural Networks, 1996., IEEE International Conference on
Conference_Location :
Washington, DC
Print_ISBN :
0-7803-3210-5
DOI :
10.1109/ICNN.1996.548865
