Dynamics of Emergent Computation in DUAL

Human cognitive processes exhibit three important qualities: flexibility, efficiency, and context sensitivity. The paper argues that these properties can be achieved in cognitive models by a combination of emergent computation and computational dynamics. We discuss the possibilities of building such models on the basis of DUAL — a distributed cognitive architecture. Computation in DUAL emerges from the collective behaviour of a great number of specialised agents running in parallel and interacting through a network of relations. The agents work at individual speeds reflecting their relevance to the context. Moreover, new agents and new relations can be created in the course of computation. In this way the particular set of agents engaged in a cognitive task and the pattern of their interaction is formed dynamically. An example of such dynamic emergent computation — mapping between two symbolic structures — is discussed in more detail.