Robust Design of Artificial Neural Networks Applying the Taguchi methodology and DoE

The integration of artificial neural networks and optimization provides a tool for designing robust network parameters and improving their performance. The Taguchi method offers considerable benefits in time and accuracy when is compared with the conventional trial and error neural network design ap...

Full description

Saved in:
Bibliographic Details
Main Authors: Ortiz-Rodriguez, J.M., Martinez-Blanco, M.R., Vega-Carrillo, H.R.
Format: Conference Proceeding
Language:English
Subjects:
Algorithm design and analysis
Artificial neural networks
Design methodology
Design optimization
Feedforward neural networks
Multi-layer neural network
Neural networks
Robustness
Signal analysis
Testing
Citations: Items that cite this one
Online Access:Request full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:The integration of artificial neural networks and optimization provides a tool for designing robust network parameters and improving their performance. The Taguchi method offers considerable benefits in time and accuracy when is compared with the conventional trial and error neural network design approach. This work is concerned with the robust design of multilayer feedforward neural networks trained by backpropagation algorithm and develops a systematic and experimental strategy which emphasizes simultaneous optimization artificial neural network's parameters optimization under various noise conditions. We make a comparison among this method and conventional training methods. The attention is drawing on the advantages on Taguchi methods which offer potential benefits in evaluating the network behavior
DOI:10.1109/CERMA.2006.83