Abstract | ||
---|---|---|
The authors describe a connectionist network which is not a neural net in which knowledge is distributed globally via the connections of functionally simple nodes. The technique combines constraint propagation with analogical or eidetic representations. It represents an alternative to the atomistic signals-to-symbols paradigm in which a one-to-one correspondence is assumed to exist between symbols and the concepts they represent |
Year | DOI | Venue |
---|---|---|
1988 | 10.1109/CVPR.1988.196331 | CVPR |
Keywords | Field | DocType |
artificial intelligence,knowledge engineering,pattern recognition,visual perception,connectionist network,constraint propagation,eidetic representations,partially occluded objects,perceptual grouping,layout,testing,computational modeling,shape,machine intelligence,spatial resolution,machine vision,prototypes,neural networks,image recognition,neural net | Computer vision,Local consistency,Pattern recognition,Computer science,Artificial intelligence,Knowledge engineering,Artificial neural network,Perception,Machine learning,Visual perception,Connectionism | Conference |
Volume | Issue | ISSN |
1988 | 1 | 1063-6919 |
Citations | PageRank | References |
3 | 0.91 | 6 |
Authors | ||
3 |
Name | Order | Citations | PageRank |
---|---|---|---|
Rearick, T.C. | 1 | 3 | 0.91 |
Frawley, J.L. | 2 | 3 | 0.91 |
Cortopassi, P.P. | 3 | 3 | 0.91 |