作者: A.M. Cakmakci , C. Isik
DOI: 10.1109/ISUMA.1995.527714
关键词:
摘要: Introduces a two-level modular neuro-fuzzy network based on incentive games where the modules are organized as autonomous local optimizers in leader-follower game hierarchy. Incentive-reaction pairs used measure for capacity and responsiveness assessment of each follower module. Learning within is performed traditional error-based manner (e.g. backpropagation). The allocation targets incentives to module, other hand, independent connection weights; that purpose. Two important advantages new architecture its physically significant module outputs context-based enhancement it makes backpropagation.