Multiple Workspaces as an Architecture for Cognition
Proceedings of AAAI 2008 Fall Symposium on Biologically Inspired Cognitive Architectures, The AAAI Press, 2008
In this paper we describe insights for theories of natural intelligence that arise from recent advances in architectures for robot intelligence. In particular we advocate a sketch theory for the study of both natural and artificial intelligence that consists of a set of constraints on architectures. The sketch includes the use of multiple shared workspaces, parallel asynchronous refinement of shared representations, statistical integration of evidence within and across modalities, massively parallel prediction and content addressable memory to allow binding across workspaces.