A Knowledge Base for a Neural Guidance System

We propose an autonomous guidance system which can be understood as an expert system implemented as a neural network. The use of a neural architecture, rather than the von Neumann architecture, remedies many of the limitations of traditional expert systems. The proposal focuses on one component of the system, the knowledge base. Key-words: Neural Networks, Distributed Representations, Dynamic Link Architecture, Schema Theory, Robot Guidance, Expert System. Main Topics: Representation of Symbols, Relationships, Production Rules. 1 Introduction Mobile creatures are guided by knowledge contained in their brains. A brain can be viewed as a neural network that behaves as an expert system in the domain of mundane behavior. Neural networks offer functions that are difficult to implement in traditional expert systems. Unlike traditional systems, where a designer fixes the meanings of symbols, neural networks represent symbols in a continuous and extensible manner [ MacLennan, 1991 ] . The e..