DocumentCode :
2785991
Title :
Perceptual semantics: the construction of meaning in artificial devices
Author :
Pustejovsky, James
Author_Institution :
Dept. of Comput. Sci., Brandeis Univ., Waltham, MA, USA
fYear :
1990
fDate :
5-7 Sep 1990
Firstpage :
86
Abstract :
The design of an artificial device that can acquire its own perceptually grounded meanings for internally represented control structure is discussed. A perceptual semantics, in which perceptual routines are mapped onto innate conceptual operators, is described. Entities and relations in the environment take on `meaning´ for the device in three forms: the connotation, which is the internal encoding of an object within a syntactic discrimination lattice; the annotation, which is a procedural encoding of how connotations are translated into action/perception; and the denotation, which is the action associated with a procedure within the action-percept feedback loop. The author argues against model-theoretic interpretations for semantics of devices interacting within their environment, and in favor of pragmatically determined models of meaning
Keywords :
adaptive control; cognitive systems; computer vision; feedback; learning systems; robots; action-percept feedback loop; annotation; artificial devices; conceptual representation; denotation; innate conceptual operators; internal encoding; internally represented control structure; perceptual routines; perceptual semantics; perceptually grounded meanings; procedural encoding; robot vision; robots; syntactic discrimination lattice; Artificial intelligence; Computer science; Encoding; Feedback loop; Grounding; Intelligent robots; Intelligent sensors; Lattices; Robot sensing systems; Testing;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Intelligent Control, 1990. Proceedings., 5th IEEE International Symposium on
Conference_Location :
Philadelphia, PA
ISSN :
2158-9860
Print_ISBN :
0-8186-2108-7
Type :
conf
DOI :
10.1109/ISIC.1990.128445
Filename :
128445
Link To Document :
بازگشت