Abstract | ||
---|---|---|
A recently developed mathematical semantic theory explains the relationship between knowledge and its representation in connectionist systems. The semantic theory is based upon category theory, the mathematical theory of structure. A product of its explanatory capability is a set of principles to guide the design of future neural architectures and enhancements to existing designs. We claim that this mathematical semantic approach to network design is an effective basis for advancing the state of the art. We offer two experiments to support this claim. One of these involves multispectral imaging using data from a satellite camera. |
Year | DOI | Venue |
---|---|---|
2009 | 10.1016/j.neucom.2009.03.008 | Neurocomputing |
Keywords | Field | DocType |
semantic theory,stack intervals,art 1,mathematical semantic approach,multispectral imaging,network design,category theory,mathematical semantic theory,effective basis,explanatory capability,mathematical semantics,mathematical theory,connectionist system,future neural architecture,multispectral images | Architecture,Network planning and design,Computer science,Mathematical theory,Multispectral image,Denotational semantics,Semantic theory of truth,Category theory,Artificial intelligence,Machine learning,Connectionism | Journal |
Volume | Issue | ISSN |
72 | 13-15 | Neurocomputing |
Citations | PageRank | References |
6 | 0.84 | 13 |
Authors | ||
6 |
Name | Order | Citations | PageRank |
---|---|---|---|
Michael J. Healy | 1 | 29 | 5.53 |
Richard D. Olinger | 2 | 6 | 0.84 |
Robert J. Young | 3 | 6 | 0.84 |
Shawn E. Taylor | 4 | 10 | 2.78 |
Thomas Caudell | 5 | 6 | 0.84 |
Kurt W. Larson | 6 | 15 | 1.50 |