FNN (Feedforward Neural Network) Training Method Based on Robust Recursive Least Square Method

Authors:
Junseok Lim;Koengmo Sung
Affiliations:
Department of Electronics Engineering, Sejong University, 98 Kwangjin Kunja, Seoul Korea, 143-747,;School of Electrical Engineering and Computer Science, Seoul National University,
Venue:
ISNN '07 Proceedings of the 4th international symposium on Neural Networks: Part II--Advances in Neural Networks
Year:
2007

Citing 5
Cited 0

Adaptive filter theory (3rd ed.)

Adaptive filter theory (3rd ed.)
On-line Successive Synthesis of Wavelet Networks

Neural Processing Letters
Numerically-robust O(N/sup 2/) RLS algorithms using least-squares prewhitening

ICASSP '00 Proceedings of the Acoustics, Speech, and Signal Processing, 2000. on IEEE International Conference - Volume 01
Neural networks for blind decorrelation of signals

IEEE Transactions on Signal Processing
Two regularizers for recursive least squared algorithms in feedforward multilayered neural networks

IEEE Transactions on Neural Networks

Quantified Score

Hi-index	0.00

Visualization

Abstract

We present a robust recursive least squares algorithm for multilayer feed-forward neural network training. So far, recursive least squares (RLS) has been successfully applied to training multilayer feed-forward neural networks. However, RLS method has a tendency to become diverse due to the instability in the recursive inversion procedure. In this paper, we propose a numerically robust recursive least square type algorithm using prewhitening. The proposed algorithm improves the performance of RLS in infinite numerical precision as well as in finite numerical precision. The computer simulation results in the various precision cases show that the proposed algorithm improves the numerical robustness of RLS training.