--- abstract: |- Neural network models of categorical perception (compression of within-category similarity and dilation of between-category differences) are applied to the symbol-grounding problem (of how to connect symbols with meanings) by connecting analog sensorimotor projections to arbitrary symbolic representations via learned category-invariance detectors in a hybrid symbolic/nonsymbolic system. Our nets are trained to categorize and name 50x50 pixel images (e.g., circles, ellipses, squares and rectangles) projected onto the receptive field of a 7x7 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" vs. "asymmetric") can 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 analyze 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. altloc: - http://www.cogsci.soton.ac.uk/~harnad/Papers/Harnad/cangelosi-connsci2.ps chapter: ~ commentary: ~ commref: ~ confdates: ~ conference: ~ confloc: ~ contact_email: ~ creators_id: [] creators_name: - family: Cangelosi given: Angelo honourific: '' lineage: '' - family: Greco given: Alberto honourific: '' lineage: '' - family: Harnad given: Stevan honourific: '' lineage: '' date: 2000 date_type: published datestamp: 2001-06-26 department: ~ dir: disk0/00/00/16/47 edit_lock_since: ~ edit_lock_until: ~ edit_lock_user: ~ editors_id: [] editors_name: [] eprint_status: archive eprintid: 1647 fileinfo: /style/images/fileicons/application_postscript.png;/1647/2/cangelosi%2Dconnsci2.ps full_text_status: public importid: ~ institution: ~ isbn: ~ ispublished: pub issn: ~ item_issues_comment: [] item_issues_count: 0 item_issues_description: [] item_issues_id: [] item_issues_reported_by: [] item_issues_resolved_by: [] item_issues_status: [] item_issues_timestamp: [] item_issues_type: [] keywords: |- symbol grounding, categorical perception, neural networks, robotics, language, perceptual learning recognition lastmod: 2011-03-11 08:54:43 latitude: ~ longitude: ~ metadata_visibility: show note: ~ number: ~ pagerange: 143-162 pubdom: FALSE publication: Connection Science publisher: ~ refereed: TRUE referencetext: | Andrews, J., Livingston, K. & Harnad, S. (1998) Categorical perception effects induced by category learning. Journal of Experimental Psychology: Learning, Memory, and Cognition 24(3), 732-753. Cangelosi, A. & Harnad, S. (1998) The adaptive advantage of symbolic Theft over sensorimotor Toil: Grounding language in perceptual categories. Presented at the 2 nd International Conference on the Evolution of Language, London, April 1998. Submitted to the Journal Evolution of Communication. http://cogsci.soton.ac.uk/harnad/Papers/Harnad/harnad98.theft.toil.html Cangelosi A. & Parisi, D. (1998). The evolution of a 'language' in an evolving population of neural nets. Connection Science, 10(2), 83-97. Csato, L., Kovacs, G, Harnad, S. Pevtzow, R. & Lorincz, A. (submitted). Category learning, categorisation difficulty and categorical perception: Computational modules and behavioural evidence. Connection Science. Fodor, J.A. (1975). The Language of Thought, New York: Thomas Y. Crowell, Goldstone, R. (1994). Influences of categorization of perceptual discrimination. Journal of Experimental Psychology: General, 123, 178-200 Jacobs, R.A., & Kosslyn, S.M. (1994). Encoding shape and spatial relations: The role of receptive field size in coordinating complementary representations. Cognitive Science, 18, 361-386. Harnad, S (Ed.) (1987). Categorical Perception: The Groundwork of Cognition. New York, Cambridge University Press. Harnad, S. (1990). The Symbol Grounding Problem. Physica D, 42, 335-346 http://www.cogsci.soton.ac.uk/~harnad/Papers/Harnad/harnad90.sgproblem.html Harnad, S. (1993). Grounding symbols in the analog world with neural nets. Think, 2, 12-78. http://www.cogsci.soton.ac.uk/~harnad/Papers/Harnad/harnad93.symb.anal.net.html Harnad, S. (1995a) Does the mind piggy-back on robotic and symbolic capacity? In: H. Morowitz (Ed.) The Mind, the Brain, and Complex Adaptive Systems. Santa Fe Institute Studies in the Sciences of Complexity. Volume XXII. pp. 204-220. http://www.cogsci.soton.ac.uk/~harnad/Papers/Harnad/harnad95.mind.robot.html Harnad, S. (1995b) Grounding symbolic capacity in robotic capacity. In: L. Steels & R. Brooks (Eds.) The Artificial Life Route to Artificial Intelligence: Building Embodied Situated Agents. New Haven: Lawrence Erlbaum. pp. 277-286. http://www.cogsci.soton.ac.uk/~harnad/Papers/Harnad/harnad95.robot.html Harnad, S. (1996) The origin of words: A psychophysical hypothesis. In Velichkovsky B & Rumbaugh, D. (Eds.) Communicating Meaning: Evolution and Development of Language. NJ: Erlbaum: pp. 27-44. http://www.cogsci.soton.ac.uk/~harnad/Papers/Harnad/harnad96.word.origin.html Harnad, S., Hanson S.J., & Lubin J. (1991). Categorical perception and the evolution of supervised learning in neural nets. In D.W. Powers & L. Reeker (Eds.) Proceedings Ontology. http://www.cogsci.soton.ac.uk/~harnad/Papers/Harnad/harnad91.cpnets.html Harnad, S., Hanson, S.J. & Lubin, J. (1995) Learned categorical perception in neural nets: Implications for symbol grounding. In V. Honavar & L. Uhr (Eds,) Symbol Processors and Connectionist Network Models in Artificial Intelligence and Cognitive Modelling: Steps Toward Principled Integration. Academic Press. pp. 191-206. http://www.cogsci.soton.ac.uk/~harnad/Papers/Harnad/harnad95.cpnets.html Pevtzow, R. & Harnad, S. (1997) Warping Similarity Space in Category Learning by Human Subjects: The Role of Task Difficulty. In M. Ramscar, U. Hahn, E. Cambouropolos, & H. Pain (Eds.) Proceedings of SimCat 1997:Interdisciplinary Workshop on Similarity and Categorization. Department of Artificial Intelligence, Edinburgh University, pp. 189-195. http://www.cogsci.soton.ac.uk/~harnad/Papers/Harnad/harnad97.textures.html Pylyshyn, Z. W. (1984) Computation and cognition. Cambridge MA: MIT/Bradford Tijsseling A. & Harnad S. (1997). Warping Similarity Space in Category Learning by Backprop Nets. In M. Ramscar, U. Hahn, E. Cambouropolos, & H. Pain (Eds.) Proceedings of SimCat 1997:Interdisciplinary Workshop on Similarity and Categorization. Department of Artificial Intelligence, Edinburgh University, pp. 263- 269. http://www.cogsci.soton.ac.uk/~harnad/Papers/Harnad/harnad97.cpnets.html relation_type: [] relation_uri: [] reportno: ~ rev_number: 10 series: ~ source: ~ status_changed: 2007-09-12 16:39:23 subjects: - cog-psy - comp-sci-neural-nets succeeds: ~ suggestions: ~ sword_depositor: ~ sword_slug: ~ thesistype: ~ title: 'From Robotic Toil to Symbolic Theft: Grounding Transfer from Entry-Level to Higher-Level Categories' type: journalp userid: 63 volume: 12