Cascade-Correlation Neural Networks: A Survey
This paper is an overview of cascade-correlation neural networks which form a specific class inside neural network function approximators. They are based on a special architecture which autonomously adapts to the application and makes the training much more efficient than the widely used backpropagation algorithm. This survey describes the cascade-correlation architecture variants, shows important applications and points to many future research directions.
Citation
G. Balazs.
"Cascade-Correlation Neural Networks: A Survey". Technical Report,
Comput603 Survey Paper (2009), University of Alberta, December 2009.
Keywords: |
cascade-correlation, neural networks |
Category: |
Technical Report |
BibTeX
@manual{Balazs:Cmput60309,
author = {Gabor Balazs},
title = {Cascade-Correlation Neural Networks: A Survey},
Institution = {University of Alberta},
year = 2009,
}
Last Updated: January 05, 2010
Submitted by Gabor Balazs