Cognitive architectures can be symbolic, connectionist, or hybrid. Some cognitive architectures or models are based on a set of generic rules, as, e.g., the Information Processing Language (e.g.
Soar is a general cognitive architecture for developing intelligent systems. Soar requires knowledge to solve various problems. It acquires knowledge using chunking mechanism. The system learns reflexively when impasses have been resolved.
Soar (also known as SOAR) is a symbolic cognitive architecture, created by John Laird, Allen Newell, and Paul Rosenbloom at Carnegie Mellon University. ...
From Cognitive Architectures, a project by MeeSook Hyun, Eric W. Miller, Joseph Phillips, and Ryan Smith; University of Michigan Artificial Intelligence Laboratory.
In 1988 Fodor and Pylyshyn published their critique of the connectionist approach to cognitive architecture and sparked a furious debate that has raged for well over a decade.
Less common, however, is the idea that perhaps working memory constraints are adaptive. For example, it may be that within our own cognitive architecture, it is simply more efficient to base behavior on relatively less data.
 See also: Artificial intelligence, Agent, Knowledge, Planning, Cognitive science
  
|
RSS
