Behavioral and Brain Sciences



Open Peer Commentary

Will the neural blackboard architecture scale up to semantics?


Michael G. Dyer a1
a1 University of California at Los Angeles, Computer Science Department, UCLA, Los Angeles CA 90095 dyer@cs.ucla.edu http://www.cs.ucla.edu/~dyer/

Article author query
dyer mg   [PubMed][Google Scholar] 

Abstract

The neural blackboard architecture is a localist structured connectionist model that employs a novel connection matrix to implement dynamic bindings without requiring propagation of temporal synchrony. Here I note the apparent need for many distinct matrices and the effect this might have for scale-up to semantic processing. I also comment on the authors' initial foray into the symbol grounding problem.