Full-text

|| Go to publishers' web page for final fulltext/PDF. (see the Authoritative link as below)

URL: ftp://gracco.irmkant.rm.cnr.it/pub/angel...angelosi-connsci2.ps

Cached: PDF-257K    PS-1096K    PS.gz-120K

SAVE AS an easy-to-recall long filename:

Filename format: author--year--title   PDF-257K    PS-120K    :: About GZip'd PS

Filename format: author--year--title--journal|proceedings|...--pages   PDF-257K    PS-120K

Related links

Authoritative: http://dx.doi.org/10.1080/09540090050129763   (Publisher's PDF... likely be available here.)

CiteSeer: http://citeseer.ist.psu.edu/231604.html

Web search: Google Web Search   ::   Google Scholar

Within this site: Cited by (19)    References (18)

Abstract

Neural network models of categorical perception (compression of withincategory similarity and dilation of between-category differences) are applied to the symbol-grounding problem (of how to connect symbols with meanings) by connecting analogue sensorimotor projections to arbitrary symbolic representations via learned category-invariance detectors in a hybrid symbolic/non-symbolic system. Our nets are trained to categorize and name 50 2 50 pixel images (e.g. circles, ellipses, squares and rectangles) projected on to the receptive field of a 7 2 7 retina. They first learn to do prototype matching and then entry-level naming for the four kinds of stimuli, grounding their names directly in the input patterns via hidden-unit representations ('sensorimotor toil'). We show that a higher-level categorization (e.g. 'symmetric' versus 'asymmetric') can be learned in two very different ways: either (1) directly from the input, just as with the entry-level categories (i.e. by toil); or (2) indirectly, from Boolean combinations of the grounded category names in the form of propositions describing the higher-order category ('symbolic theft'). We analyse the architectures and input conditions that allow grounding (in the form of compression/ separation in internal similarity space) to be 'transferred' in this second way from directly grounded entry-level category names to higher-order category names. Such hybrid models have implications for the evolution and learning of language.

Keywords: SYMBOL GROUNDING CATEGORICAL PERCEPTION NEURAL NETWORKS PATTERN RECOGNITION

@article{cangelosi00fromRobotic,
  author={A. Cangelosi and A. Greco and S. Harnad},
  title={From robotic toil to symbolic theft: Grounding transfer from entry-level to higher-level categories},
  journal={Connection Science},
  year={2000},
  volume={12},
  number={2},
  pages={143-162},
  doi={10.1080/09540090050129763},
  url={http://www.isrl.uiuc.edu/~amag/langev/paper/cangelosi00fromRobotic.html},
  keywords={SYMBOL GROUNDING CATEGORICAL PERCEPTION NEURAL NETWORKS PATTERN RECOGNITION}
}

HOME   ::  Journal List   ::   Article	Comments to: junwang4 you-know-at gmail.com	Last update: 2/2/08