DocumentCode
3442296
Title
Faster, higher-quality training of feedforward neural networks by select updating
Author
Deller, J.R., Jr. ; Hunt, S.D.
Author_Institution
Dept. of Electr. Eng., Michigan State Univ., East Lansing, MI, USA
Volume
6
fYear
1994
fDate
30 May-2 Jun 1994
Firstpage
435
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
feedforward neural nets; iterative methods; learning (artificial intelligence); matrix algebra; perturbation techniques; computation; feedforward neural networks; iteration; matrix perturbation theory; select updating; training; weight estimates; Feedforward neural networks; Joining processes; Laboratories; Least squares approximation; Least squares methods; Linear systems; Neural networks; Nonlinear equations; Speech processing; Vectors;
fLanguage
English
Publisher
ieee
Conference_Titel
Circuits and Systems, 1994. ISCAS '94., 1994 IEEE International Symposium on
Conference_Location
London
Print_ISBN
0-7803-1915-X
Type
conf
DOI
10.1109/ISCAS.1994.409619
Filename
409619
Link To Document