Back to Search
Start Over
Implementation and performance evaluation of the agent-based algorithm for ANN training.
- Source :
-
International Journal of Knowledge Based Intelligent Engineering Systems . Mar2010, Vol. 14 Issue 1, p1-10. 10p. - Publication Year :
- 2010
-
Abstract
- The paper contains a description of the implementation and performance evaluation of the agent-based population learning algorithm used to train the feed-forward artificial neural networks. The goal of the research was to evaluate efficiency of the agent-based approach and to establish experimentally which different factors representing the A-Team structure and topology affect the performance of the analyzed agent-based algorithm. The paper includes a general overview of the JABAT environment used to deploy the ANN training algorithm, a description of different agents employed and their roles, as well as the computational experiment plan and the discussion of the performance evaluation results. [ABSTRACT FROM AUTHOR]
Details
- Language :
- English
- ISSN :
- 13272314
- Volume :
- 14
- Issue :
- 1
- Database :
- Academic Search Index
- Journal :
- International Journal of Knowledge Based Intelligent Engineering Systems
- Publication Type :
- Academic Journal
- Accession number :
- 48120094
- Full Text :
- https://doi.org/10.3233/KES-2010-0185