Multiple Workspaces as an Architecture for Cognition

[wyatthawes08bica] Jeremy Wyatt and Nick Hawes. Multiple Workspaces as an Architecture for Cognition. In Biologically Inspired Cognitive Architectures: Papers from the 2008 AAAI Fall Symposium. To appear. November 2008. [pdf] [bib]

Abstract. 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.

Download:

pdf (58 KB) $bib$ bib

Links: [Google Scholar] [CiteSeer]