Flexible Object Architectures for Hybrid Neural Processing Systems
James A. Crowder · AIAA Infotech@Aerospace 2010 · 2010
This paper introduces an initial object architecture and prototype for the flexible, hybrid genetic-neural processing environment called ELYSE, the Evolving, Life-like Yielding, Symbiotic Environment. This architecture will allow the system to dynamically adapt its structure as it evolves and learns more about the types of environments it must deal with. The architecture accommodates a variety of memory classes and algorithm methods. The basic building blocks of ELYSE, the fuzzy, genetic perceptron, may be added or deleted from the system, depending on the complexity of the classes of information the system must process. Presented will be a theoretical description of dynamic adaptation along with the object architecture and high-level requirements for the system.