DocumentCode
2266266
Title
Training of feedforward artificial neural networks using selective updating
Author
Hunt, S.D. ; Deller, J.R., Jr.
Author_Institution
Dept. of Electr. Eng. & Comput. Sci., Puerto Rico Univ., Mayaguez, Puerto Rico
fYear
1993
fDate
16-18 Aug 1993
Firstpage
1189
Abstract
A new training method for feedforward neural networks is presented which exploits results from matrix perturbation theory for significant training time improvement. This theory is used to assess the effect of a particular training pattern on the weight estimates prior to its inclusion in any iteration. Data which do not significantly change the weights are not used in that iteration obviating the computation expense of updating
Keywords
data reduction; feedforward neural nets; learning (artificial intelligence); matrix algebra; artificial neural networks; feedforward ANN; iteration; matrix perturbation theory; selective updating; training method; training time improvement; weight estimates; Artificial neural networks; Associative memory; Computer networks; Equations; Feedforward neural networks; Joining processes; Least squares approximation; Least squares methods; Neural networks; Pattern classification;
fLanguage
English
Publisher
ieee
Conference_Titel
Circuits and Systems, 1993., Proceedings of the 36th Midwest Symposium on
Conference_Location
Detroit, MI
Print_ISBN
0-7803-1760-2
Type
conf
DOI
10.1109/MWSCAS.1993.343306
Filename
343306
Link To Document