An ensemble learning and problem solving architecture for airspace management

摘要: In this paper we describe the application of a novel learning and problem solving architecture to domain airspace management, where multiple requests for use need be reconciled managed automatically. The key feature our "Generalized Integrated Learning Architecture" (GILA) is set integrated reasoning (ILR) systems coordinated by central meta-reasoning executive (MRE). Each ILR learns independently from same training example contributes problem-solving in concert with other ILRs as directed MRE. Formal evaluations show that system performs well or better than humans after data. Further, GILA outperforms any individual run isolation, thus demonstrating power ensemble solving.