Implementation and performance evaluation of the agent-based algorithm for ANN training

Article type: Research Article

Authors: Czarnowski, Ireneusz^{; *} | Jędrzejowicz, Piotr

Affiliations: Department of Information Systems, Gdynia Maritime University, Morska 83, 81-225 Gdynia, Poland

Correspondence: [*] Corresponding author. Tel.: +48 58 6901554; E-mail: irek@am.gdynia.pl

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.

Keywords: JABAT, A-Team, optimization, multi-agents systems, artificial neural network

DOI: 10.3233/KES-2010-0185

Journal: International Journal of Knowledge-based and Intelligent Engineering Systems, vol. 14, no. 1, pp. 1-10, 2010