Show simple item record

dc.contributor.authorBouvrie, Jacob Vincent
dc.contributor.authorRosasco, Lorenzo Andrea
dc.contributor.authorPoggio, Tomaso A.
dc.date.accessioned2014-10-24T14:24:08Z
dc.date.available2014-10-24T14:24:08Z
dc.date.issued2009
dc.identifier.issn1049-5258
dc.identifier.urihttp://hdl.handle.net/1721.1/91165
dc.description.abstractA goal of central importance in the study of hierarchical models for object recognition -- and indeed the visual cortex -- is that of understanding quantitatively the trade-off between invariance and selectivity, and how invariance and discrimination properties contribute towards providing an improved representation useful for learning from data. In this work we provide a general group-theoretic framework for characterizing and understanding invariance in a family of hierarchical models. We show that by taking an algebraic perspective, one can provide a concise set of conditions which must be met to establish invariance, as well as a constructive prescription for meeting those conditions. Analyses in specific cases of particular relevance to computer vision and text processing are given, yielding insight into how and when invariance can be achieved. We find that the minimal sets of transformations intrinsic to the hierarchical model needed to support a particular invariance can be clearly described, thereby encouraging efficient computational implementations.en_US
dc.description.sponsorshipUnited States. Defense Advanced Research Projects Agency (Contract FA8650-06-C-7632)en_US
dc.language.isoen_US
dc.publisherNeural Information Processing Systems Foundationen_US
dc.relation.isversionofhttp://papers.nips.cc/paper/3732-on-invariance-in-hierarchical-modelsen_US
dc.rightsArticle is made available in accordance with the publisher's policy and may be subject to US copyright law. Please refer to the publisher's site for terms of use.en_US
dc.sourceNeural Information Processing Systems Foundationen_US
dc.titleOn invariance in hierarchical modelsen_US
dc.typeArticleen_US
dc.identifier.citationBouvrie, Jake, Lorenzo Rosasco, and Tomaso Poggio. "On invariance in Hierarchical models." Advances in Neural Information Processing 22 (NIPS 2009).en_US
dc.contributor.departmentMassachusetts Institute of Technology. Center for Biological & Computational Learningen_US
dc.contributor.departmentMassachusetts Institute of Technology. Department of Brain and Cognitive Sciencesen_US
dc.contributor.departmentMcGovern Institute for Brain Research at MITen_US
dc.contributor.mitauthorBouvrie, Jacob Vincenten_US
dc.contributor.mitauthorRosasco, Lorenzo Andreaen_US
dc.contributor.mitauthorPoggio, Tomaso A.en_US
dc.relation.journalAdvances in Neural Information Processing Systems (NIPS)en_US
dc.eprint.versionFinal published versionen_US
dc.type.urihttp://purl.org/eprint/type/JournalArticleen_US
eprint.statushttp://purl.org/eprint/status/PeerRevieweden_US
dspace.orderedauthorsBouvrie, Jake; Rosasco, Lorenzo; Poggio, Tomasoen_US
dc.identifier.orcidhttps://orcid.org/0000-0002-3944-0455
dc.identifier.orcidhttps://orcid.org/0000-0001-6376-4786
dc.identifier.orcidhttps://orcid.org/0000-0001-6008-7417
mit.licensePUBLISHER_POLICYen_US


Files in this item

Thumbnail

This item appears in the following Collection(s)

Show simple item record