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
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;
Conference_Titel :
Circuits and Systems, 1993., Proceedings of the 36th Midwest Symposium on
Conference_Location :
Detroit, MI
Print_ISBN :
0-7803-1760-2
DOI :
10.1109/MWSCAS.1993.343306
