<> "The repository administrator has not yet configured an RDF license."^^ . <> . . "Symbol Grounding is an Empirical Problem: Neural Nets are Just a Candidate Component"^^ . "\"Symbol Grounding\" is beginning to mean too many things to too many people. My own construal has always\nbeen simple: Cognition cannot be just computation, because computation is just the systematically interpretable manipulation of\nmeaningless symbols, whereas the meanings of my thoughts don't depend on their interpretability or interpretation by someone\nelse. On pain of infinite regress, then, symbol meanings must be grounded in something other than just their interpretability if they\nare to be candidates for what is going on in our heads. Neural nets may be one way to ground the names of concrete objects and\nevents in the capacity to categorize them (by learning the invariants in their sensorimotor projections). These grounded\nelementary symbols could then be combined into symbol strings expressing propositions about more abstract categories.\nGrounding does not equal meaning, however, and does not solve any philosophical problems. "^^ . "1993" . . . . . . . . "Stevan"^^ . "Harnad"^^ . "Stevan Harnad"^^ . . . . . . "Symbol Grounding is an Empirical Problem: Neural Nets are Just a Candidate Component (HTML)"^^ . . . "harnad93.cogsci.html"^^ . . . "Symbol Grounding is an Empirical Problem: Neural Nets are Just a Candidate Component (Indexer Terms)"^^ . . . . . . "indexcodes.txt"^^ . . "HTML Summary of #1588 \n\nSymbol Grounding is an Empirical Problem: Neural Nets are Just a Candidate Component\n\n" . "text/html" . . . "Artificial Intelligence" . . . "Dynamical Systems" . . . "Neural Nets" . . . "Perceptual Cognitive Psychology" . . . "Philosophy of Mind" . .