Comparative performance of backpropagation networks designed by genetic algorithms and heuristics

James V. Hansen

Intelligent Systems in Accounting, Finance and Management, 1998, vol. 7, issue 2, 69-79

Abstract: The design of neural network models involves numerous complexities, including the determination of input vectors, choosing the number of hidden layers and their computational units, and specifying activation functions for the latter. The combinatoric possibilities are daunting, yet experience has yielded informal guidelines that can be useful. Alternatively, current research on genetic algorithms (GA) suggests that they might be of practical use as a formal method of determining ‘good’ architectures for neural networks. In this paper, we use a genetic algorithm to find effective architectures for backpropagation neural networks (BP). We compare the performance of heuristically designed BP networks with that of GA‐designed BP networks. Our test domains are sets of problems having compensatory, conjunctive, and mixed‐decision structures. The results of our experiment suggest that heuristic methods produce architectures that are simpler and yet perform comparatively well. © 1998 John Wiley & Sons, Ltd.

Date: 1998
References: Add references at CitEc
Citations:

Downloads: (external link)
https://doi.org/10.1002/(SICI)1099-1174(199806)7:23.0.CO;2-2

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:wly:isacfm:v:7:y:1998:i:2:p:69-79

Ordering information: This journal article can be ordered from
http://www.blackwell ... bs.asp?ref=1099-1174

Access Statistics for this article

More articles in Intelligent Systems in Accounting, Finance and Management from John Wiley & Sons, Ltd.
Bibliographic data for series maintained by Wiley Content Delivery ().