• Computer Science
  • Published 1999

On-line adaptive learning rate BP algorithm for MLP and application to an identification problem

@inproceedings{Sha1999OnlineAL,
  title={On-line adaptive learning rate BP algorithm for MLP and application to an identification problem},
  author={D. H. Sha and Vladimir B. Bajic},
  year={1999}
}
Abstract An on-line algorithm that uses an adaptive learning rate is proposed. Its development isbased on the analysis of the convergence of the conventional gradient descent method for three-layer BP neural networks. The effectiveness of the proposed algorithm applied to theidentification and prediction of behavior of non-linear dynamic systems is demonstrated bysimulation experiments. Keywords: Neural networks, learning algorithms, adaptive behavior, Gradient descent method,Input/output… CONTINUE READING

Topics from this paper.

Citations

Publications citing this paper.
SHOWING 1-8 OF 8 CITATIONS

On-line identification of multivariable nonlinear system using neural networks

Design and analysis of an active predictive algorithm in wireless multicast networks

VIEW 1 EXCERPT
CITES METHODS

Implementation of Rate Control in Distributed Wireless Multicast by Neural Network Prediction

VIEW 3 EXCERPTS
CITES METHODS & BACKGROUND

A Distributed Neural Network Control Approach for Multicast Services

VIEW 1 EXCERPT
CITES METHODS