SELF-LEARNING FOR AUTONOMOUS SYSTEMS

Learning is a key element in the strive for machine intelligence. Unsu pervised learning is even more important for robots or autonomous syst ems that operate in remote environment away from human interactions, s uch as the case in the fully automated factory floor. To achieve unsup ervised learning, a variety of models and techniques have been employe d by investigators. In this paper some of the models, especially in th e area of Neural Networks are compared and contrasted. Special conside ration will be given self organizing maps (Kohonen Networks) [1,6]. A comparison of the Kohonen Networks and their biological counterpart is given. The introduction of these systems to increase the intelligence , and hence the autonomy of systems, is considered.