Boundedness of estimator with an improved back propagation algorithm

This paper proposes a novel learning algorithm with a variable learning gain and a /spl sigma/-modification term for a multilayered neural network. The learning gain is decided by the 'Levenberg-Marquardt' algorithm, which is a nonlinear least squares method. The boundedness of the weighti...

Full description

Saved in:
Bibliographic Details
Published in:Proceedings of the 1996 IEEE IECON : 22nd International Conference on Industrial Electronics, Control, and Instrumentation Vol. 1; pp. 309 - 314 vol.1
Main Authors: Ikeda, K., Shin, S.
Format: Conference Proceeding
Language:English
Published: IEEE 1996
Subjects:
Adaptive control
Education
Filters
Gain
Multi-layer neural network
Neural networks
Neurons
Physics
Robust control
Upper bound
ISBN:0780327756, 9780780327757
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:This paper proposes a novel learning algorithm with a variable learning gain and a /spl sigma/-modification term for a multilayered neural network. The learning gain is decided by the 'Levenberg-Marquardt' algorithm, which is a nonlinear least squares method. The boundedness of the weightings is shown from a viewpoint of the robust adaptive control theory and a relationship between data sizes and learning rates is considered. Furthermore, simple numerical simulations are presented to show the efficiency of the proposed learning algorithm.
ISBN:0780327756
9780780327757
DOI:10.1109/IECON.1996.570970