Separable Recursive Training Algorithms with Switching Module
A novel hybrid or separable recursive training strategies are de rived for the training of feedforward neural networks which incoporates a switching module. This new technique for updating weights combines non linear recursive training algorithms for the optimization of nonlinear weights with recurs...
Saved in:
Main Author: | |
---|---|
Other Authors: | |
Format: | Book Section |
Published: |
Springer
2009
|
Subjects: | |
Online Access: | http://www.springerlink.com/content/41g22372271138w5/ http://eprints.utp.edu.my/3814/ |
Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
Summary: | A novel hybrid or separable recursive training strategies are de rived for the training of feedforward neural networks which incoporates a switching module. This new technique for updating weights combines non linear recursive training algorithms for the optimization of nonlinear weights with recursive least square type algorithms for the training of linear weights in one integrated routine. The proposed new variant of hybrid weight update includes switching mechanism based on the condition of input data to the system (correlated or noncorrelated). Simulation results demonstrate the im provement of the new proposed switching mode training scheme. |
---|