Connectionism, Knowledge Representation, and Effective Reasoning

Human cognitive agents are capable of representing highly structured knowledge and drawing a variety of inferences based on such knowledge with remarkable efficiency — almost as if by reflex. These inferences are by no means trivial and support a broad range of cognitive activity such as classifying and recognizing objects, understanding spoken and written language, and performing commonsense reasoning. Any serious attempt at understanding intelligence must provide a detailed computational account of how such knowledge may be represented and such inferences drawn with requisite efficiency. In this talk we will discuss some work within the connectionist framework that attempts to offer such an account.