DocumentCode :
3442218
Title :
Computationally-improved optimal filtering for supervised learning [feedforward neural nets]
Author :
Benromdhane, Saida ; Salam, Fathi M A
Author_Institution :
Dept. of Electr. Eng., Michigan State Univ., East Lansing, MI, USA
Volume :
6
fYear :
1994
fDate :
30 May-2 Jun 1994
Firstpage :
419
Abstract :
We propose a modification of the Kalman filtering approach to supervised learning that avoids existing approximations while improving its overall computational efficiency. The modification eliminates the necessity of computing an inverse. The same global network structure is retained while the computational effort is extensively reduced. The performance of the approach with the modification, assessed from several test cases, is found to be more refined than the existing approaches
Keywords :
Kalman filters; feedforward neural nets; filtering theory; learning (artificial intelligence); parameter estimation; Kalman filtering approach; computational efficiency; computational effort; computationally-improved optimal filtering; feedforward neural networks; global network structure; parameter estimation; supervised learning; Artificial neural networks; Backpropagation algorithms; Computational efficiency; Equations; Feedforward neural networks; Filtering; Kalman filters; Laboratories; Neural networks; Supervised learning;
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.1994.409615
Filename :
409615
Link To Document :
بازگشت