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. |
Year | DOI | Venue |
---|---|---|
2010 | 10.3233/978-1-60750-660-7-119 | BICA |
Keywords | Field | DocType |
first order,graphical model,cognitive architecture,message passing | Graph,Computer science,First order,Theoretical computer science,Artificial intelligence,Graphical model,Cognitive architecture,Cognition,Machine learning,Message passing | Conference |
Volume | ISSN | Citations |
221 | 0922-6389 | 3 |
PageRank | References | Authors |
0.53 | 5 | 1 |
Name | Order | Citations | PageRank |
---|---|---|---|
Paul S. Rosenbloom | 1 | 1416 | 284.53 |