Show simple item record

dc.contributor.authorCangelosi, A
dc.contributor.authorGreco, A
dc.contributor.authorHarnad, S
dc.date.accessioned2015-10-13T21:04:23Z
dc.date.available2015-10-13T21:04:23Z
dc.date.issued2000-06
dc.identifier.issn0954-0091
dc.identifier.issn1360-0494
dc.identifier.urihttp://hdl.handle.net/10026.1/3618
dc.description.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 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 × 50 pixel images (e.g. circles, ellipses, squares and rectangles) projected on to the receptive field of a 7 × 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.

dc.format.extent143-162
dc.language.isoen
dc.publisherInforma UK Limited
dc.subjectsymbol grounding
dc.subjectcategorical perception
dc.subjectneural networks
dc.subjectpattern recognition
dc.titleFrom robotic toil to symbolic theft: Grounding transfer from entry-level to higher-level categories1
dc.typeconference
dc.typeArticle
dc.typeProceedings Paper
plymouth.issue2
plymouth.volume12
plymouth.publisher-urlhttp://dx.doi.org/10.1080/09540090050129763
plymouth.publication-statusPublished
plymouth.journalConnection Science
dc.identifier.doi10.1080/09540090050129763
plymouth.organisational-group/Plymouth
plymouth.organisational-group/Plymouth/Faculty of Science and Engineering
plymouth.organisational-group/Plymouth/Research Groups
plymouth.organisational-group/Plymouth/Research Groups/Institute of Health and Community
plymouth.organisational-group/Plymouth/Research Groups/Marine Institute
dc.identifier.eissn1360-0494
dc.rights.embargoperiodNot known
rioxxterms.versionofrecord10.1080/09540090050129763
rioxxterms.licenseref.urihttp://www.rioxx.net/licenses/all-rights-reserved
rioxxterms.typeConference Paper/Proceeding/Abstract


Files in this item

Thumbnail
Thumbnail

This item appears in the following Collection(s)

Show simple item record


All items in PEARL are protected by copyright law.
Author manuscripts deposited to comply with open access mandates are made available in accordance with publisher policies. Please cite only the published version using the details provided on the item record or document. In the absence of an open licence (e.g. Creative Commons), permissions for further reuse of content should be sought from the publisher or author.
Theme by 
Atmire NV