<> "The repository administrator has not yet configured an RDF license."^^ . <> . . "Learned Categorical Perception in Neural Nets: Implications for Symbol Grounding"^^ . "After people learn to sort objects into categories they see them differently. Members of\nthe same category look more alike and members of different categories look more different. This\nphenomenon of within-category compression and between-category separation in similarity space is\ncalled categorical perception (CP). It is exhibited by human subjects, animals and neural net models.\nIn backpropagation nets trained first to auto-associate 12 stimuli varying along a one-dimensional\ncontinuum and then to sort them into 3 categories, CP arises as a natural side-effect because of four\nfactors: (1) Maximal interstimulus separation in hidden-unit space during auto-association learning, (2)\nmovement toward linear separability during categorization learning, (3) inverse-distance repulsive force\nexerted by the between-category boundary, and (4) the modulating effects of input iconicity, especially\nin interpolating CP to untrained regions of the continuum. Once similarity space has been \"warped\" in\nthis way, the compressed and separated \"chunks\" have symbolic labels which could then be combined\ninto symbol strings that constitute propositions about objects. The meanings of such symbolic\nrepresentations would be \"grounded\" in the system's capacity to pick out from their sensory\nprojections the object categories that the propositions were about. "^^ . "1995" . . . "Academic Press"^^ . . . "Symbol Processors and Connectionist Network Models in Artificial Intelligence and Cognitive Modelling: Steps Toward Principled Integration"^^ . . . . . . . . . . . . . . . . . . . . "V."^^ . "Honavar"^^ . "V. Honavar"^^ . . "L."^^ . "Uhr"^^ . "L. Uhr"^^ . . "Stephen J."^^ . "Hanson"^^ . "Stephen J. Hanson"^^ . . "Joseph"^^ . "Lubin"^^ . "Joseph Lubin"^^ . . "Stevan"^^ . "Harnad"^^ . "Stevan Harnad"^^ . . . . . . "Learned Categorical Perception in Neural Nets: Implications for Symbol Grounding (HTML)"^^ . . . "harnad95.cpnets.html"^^ . . . "Learned Categorical Perception in Neural Nets: Implications for Symbol Grounding (Indexer Terms)"^^ . . . . . . "indexcodes.txt"^^ . . "HTML Summary of #1596 \n\nLearned Categorical Perception in Neural Nets: Implications for Symbol Grounding\n\n" . "text/html" . . . "Dynamical Systems" . . . "Neural Nets" . . . "Perceptual Cognitive Psychology" . .