Characteristics of connectionist knowledge representation

Connectionism--the use of neural networks for knowledge representation and inference--has profound implications for the representation and processing of information because it provides a fundamentally new view of knowledge. However, its progress is impeded by the lack of a unifying theoretical construct corresponding to the idea of a calculus (or formal system) in traditional approaches to knowledge representation. Such a construct, called a simulacrum, is proposed here, and its basic properties are explored. We find that although exact classification is impossible, several other useful, robust kinds of classification are permitted. The representation of structured information and constituent structure are considered, and we find a basis for more flexible rule-like processing than that permitted by conventional methods. We discuss briefly logical issues such as decidability and computability and show that they require reformulation in this new context. Throughout we discuss the implications for artificial intelligence and cognitive science of this new theoretical framework.