Dynamic self organizing maps for discovery and sharing of knowledge in multi agent systems

Article type: Research Article

Authors: Wickramasinghe, L.K. | Alahakoon, L.D.

Affiliations: School of Business Systems, Monash University, Australia. E-mail: {kumari.wickramasinghe, damminda.alahakoon}@infotech.monash.edu.au

Abstract: This paper presents a multi agent system which provides a method for cooperation and coordination among agents using collective reasoning. There are two types of agents in the system: distributed agents and a central administrator agent. The distributed agents provide local knowledge extraction tasks and communicate it to the central administrator agent. The central administrator agent builds a global picture about the problem domain using the local knowledge of each agent. It uses the Growing Self Organizing Map (GSOM), which is a dynamic version of the Self Organizing Map (SOM) for analyzing the global knowledge. The system differs from similar systems which employ central administrator functionality as the central administrator agent in the proposed system is capable of autonomously refining the task model of the distributed agents and dynamically determining the efficient number of agents required in the system.

Keywords: knowledge discovery, knowledge sharing, self-organization, unsupervised learning, hierarchical clustering, data mining, distributed agents

Journal: Web Intelligence and Agent Systems: An international journal, vol. 3, no. 1, pp. 31-47, 2005