DocumentCode
393802
Title
A study of self-organization method of neural networks
Author
Yamawaki, Shigenobu
Author_Institution
Dept. of Electr. Eng., Kinki Univ., Osaka, Japan
Volume
3
fYear
2002
fDate
5-7 Aug. 2002
Firstpage
1596
Abstract
The ability to describe a neural network depends greatly on the number of neurons. in this paper, we consider a method of obtaining an optimal neural network through a forgetting operation. It is shown that by using the proposed method, an optimum neural network can be constructed not only from neurons having large singular values of the coefficient matrix, but also from neurons having small singular values of the coefficient matrix.
Keywords
backpropagation; identification; neural nets; self-adjusting systems; back propagation; identification; least squares method; neural network; regression neural network; self-organization; Convergence; Equations; Error correction; Finite difference methods; Least squares methods; Neural networks; Neurons; Nonlinear systems; Recurrent neural networks; System identification;
fLanguage
English
Publisher
ieee
Conference_Titel
SICE 2002. Proceedings of the 41st SICE Annual Conference
Print_ISBN
0-7803-7631-5
Type
conf
DOI
10.1109/SICE.2002.1196549
Filename
1196549
Link To Document