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
fDate :
30 May-2 Jun 1994
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;
Conference_Titel :
Circuits and Systems, 1994. ISCAS '94., 1994 IEEE International Symposium on
Conference_Location :
London
Print_ISBN :
0-7803-1915-X
DOI :
10.1109/ISCAS.1994.409619
