That's what I've been saying forever: www.cognitivealgorithm.info. But statistical / crudely neuromorphic methods of extracting / defining these features ) objects ) concepts are too coarse to scale. They are also too coarse for meaningful functional analysis, hence seemingly interminable confusion in AGI. Human mind / brain is too coarse :). Again, I think the key here is functional definition of intelligence ( = cognitive ability), & strictly incremental ( !coarse) derivation therefrom. That derivation should go from operations to incrementally complex algorithms, which in turn derive incrementally complex concepts from sensory data.
This post is my triumph of hope over experience :). On Sun, Jan 12, 2014 at 12:17 AM, Piaget Modeler <[email protected]>wrote: > > Roland Hausser agreed, and also mentioned his work > > Foundations of Computational Linguistics (FoCL), 3rd edition > available in soft cover and as an eBook. > > The official Springer web site is > > > http://link.springer.com/book/10.1007%2F978-3-642-41431-2<http://link.springer.com/book/10.1007/978-3-642-41431-2> > > ~PM > > 2014/1/11 Piaget Modeler <[email protected]> > > Now I'm looking at concept formation from perceptual input. I thought > this article was intriguing > since it intersects perception, language, and semiosis. > > Hierarchies in Dictionary Definition Space > > http://arxiv.org/pdf/0911.5703v1.pdf > > Conclusion: > > "All categories, even the most concrete are in fact abstractions, because > we must abstract from > particular cases, even concrete sensorimotor ones, in order to find the > invariant features that distin- > guish category members from nonmembers and allow us to do the right thing > with the right kind of > thing. But the more that categories are based on other categories, the > more abstract they become, > and this is reflected by the distances in our induced definitional space. > It is in the nature of words > to be amenable to combination and recombination in such a way as to define > or describe ever more > categories. Defining, like eating, is something we do. Our more concrete > categories are answerable > to the constraints of the sensorimotor word in which they are grounded, > but our more abstract cat- > egories are increasingly answerable only to combinations of other > categories, as we describe and > define them. In abstract mathematics, that constraint, though only formal, > is still a rigorous one. > In more hermeneutic discourse (e.g. constitutional law or theology) the > main constraint on words > increasingly becomes just other words. Our mental lexicon must encode the > meaning of all the words > we use in our thought and discourse. Hierarchies in dictionary space may > turn out to have counter- > parts in cognitive space." > > Keywords: categories, definition, dictionary, feedback vertex set, graph > theory, > language learning, lexicography, mental lexicon, semantics, symbol > grounding, > vocabulary, word meaning > > > Your Thoughts? > > ~PM > > > *AGI* | Archives <https://www.listbox.com/member/archive/303/=now> > <https://www.listbox.com/member/archive/rss/303/18407320-d9907b69> | > Modify<https://www.listbox.com/member/?&;>Your Subscription > <http://www.listbox.com> > ------------------------------------------- AGI Archives: https://www.listbox.com/member/archive/303/=now RSS Feed: https://www.listbox.com/member/archive/rss/303/21088071-f452e424 Modify Your Subscription: https://www.listbox.com/member/?member_id=21088071&id_secret=21088071-58d57657 Powered by Listbox: http://www.listbox.com
