Adaptive Resonance Theory Microchips
IWANN '99 Proceedings of the International Work-Conference on Artificial and Natural Neural Networks: Foundations and Tools for Neural Modeling
Hi-index | 0.00 |
In this paper, the potential of adaptive resonance theory (ART) networks for the dependable control of autonomous systems is considered. First a short survey about existing ART network approaches is given. A combination of such networks with counterpropagation networks is described which provides fast access to control procedures corresponding to the different classes of situations to be treated. Moreover, it is discussed how the observed success or failing of such a procedure can be utilized to influence the learning of the ART network.