Download: PDF.
“Genetically Evolving Optimal Neural Networks” by Chad Williams. In Neural Networks and Expert Systems, Jan. 2007.
One of the greatest challenges of neural networks is determining an efficient network configuration that also is highly accurate. Due to the number of possible configurations and the significant difference in similar networks, the search for an optimal configuration is not well suited to traditional search techniques. Genetic algorithms seem a natural fit for this type of complex search. This paper examines genetic algorithms research that has focused on addressing these challenges. Specific focus is paid to techniques that have been used to encode the problem space in order to optimize neural network configurations. A summary of the results as well as areas for future research in this field are also discussed.
Keywords: neural networks, automatic network configuration
Download: PDF.
BibTeX entry:
@incollection{W07,
author = {Chad Williams},
title = {Genetically Evolving Optimal Neural Networks},
booktitle = {Neural Networks and Expert Systems},
publisher = {The Institute of Chartered Financial Analysts of India
(ICFAI)},
month = jan,
year = {2007},
url =
{http://sites.google.com/site/chadwilliamshome/publications/publication-files/CWilliams-NNES07.pdf}
}