DocumentCode :
3252020
Title :
Extrapolation limitations of multilayer feedforward neural networks
Author :
Haley, Pamela J. ; Soloway, Donald
Author_Institution :
NASA Langley Res. Center, Hampton, VA, USA
Volume :
4
fYear :
1992
fDate :
7-11 Jun 1992
Firstpage :
25
Abstract :
The limitations of backpropagation used as a function extrapolator were investigated. Four common functions were used to investigate the network´s extrapolation capability. The purpose of the experiment was to determine whether neural networks are capable of extrapolation and, if so, to determine the range for which networks can extrapolate. The authors show that neural networks cannot extrapolate and offer an explanation to support this result
Keywords :
backpropagation; extrapolation; feedforward neural nets; backpropagation; extrapolation; function extrapolator; multilayer feedforward neural networks; neural networks; Backpropagation; Extrapolation; Feedforward neural networks; Joining processes; Multi-layer neural network; NASA; Neural networks; Protection; Stock markets; Testing;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Neural Networks, 1992. IJCNN., International Joint Conference on
Conference_Location :
Baltimore, MD
Print_ISBN :
0-7803-0559-0
Type :
conf
DOI :
10.1109/IJCNN.1992.227294
Filename :
227294
Link To Document :
بازگشت