Search
 
loader loading subjects...
cover
Implementing First-Order Variables in a Graphical Cognitive Architecture
Paul Rosenbloom
119 - 124
10.3233/978-1-60750-661-4-119
Frontiers in Artificial Intelligence and Applications
Volume 221: Biologically Inspired Cognitive Architectures 2010
Abstract

Graphical cognitive architectures implement their functionality through localized message passing among computationally limited nodes. First-order variables – particularly universally quantified ones – while critical for some potential architectural mechanisms, can be quite difficult to implement in such architectures. A new implementation strategy based on message decomposition in graphical models is presented that yields tractability while preserving key symmetries in the graphs concerning how quantified variables are represented and how symbols, probabilities and signals are processed.

$35.00 / €27.50 / £22.00
Add PDF to cart