Show simple item record

dc.contributor.advisorTomaso Poggio.en_US
dc.contributor.authorHenry, Timothy G.en_US
dc.contributor.otherMassachusetts Institute of Technology. Department of Electrical Engineering and Computer Science.en_US
dc.date.accessioned2021-02-19T20:49:40Z
dc.date.available2021-02-19T20:49:40Z
dc.date.copyright2020en_US
dc.date.issued2020en_US
dc.identifier.urihttps://hdl.handle.net/1721.1/129905
dc.descriptionThesis: M. Eng., Massachusetts Institute of Technology, Department of Electrical Engineering and Computer Science, February, 2020en_US
dc.descriptionCataloged from student-submitted PDF of thesis.en_US
dc.descriptionIncludes bibliographical references (pages 71-73).en_US
dc.description.abstractVisual understanding results from a combined understanding of primitive visual attributes such as color, texture, and shape. This allows humans and other primates to generalize their understanding of objects to new combinations of attributes. For instance, one can understand that a pink elephant is an elephant even if they have never seen this particular combination of color and shape before. However, is it the case that deep neural networks (DNNs) are able to generalize to such novel combinations in object recognition or other related vision tasks? This thesis demonstrates that (1) the ability of DNNs to generalize to unseen attribute combinations increases with the increased diversity of combinations seen in training as a percentage of the total combination space, (2) this effect is largely independent of the specifics of the DNN architecture used, (3) while single-task and multi-task formulations of supervised attribute classification problems may lead to similar performance on seen combinations, single-task formulations have a superior ability to generalize to unseen combinations, and (4) DNNs demonstrating the ability to generalize well in this setting learn to do so by leveraging emergent hidden units that exhibit properties of attribute selectivity and invariance.en_US
dc.description.statementofresponsibilityby Timothy G. Henry.en_US
dc.format.extent73 pagesen_US
dc.language.isoengen_US
dc.publisherMassachusetts Institute of Technologyen_US
dc.rightsMIT theses may be protected by copyright. Please reuse MIT thesis content according to the MIT Libraries Permissions Policy, which is available through the URL provided.en_US
dc.rights.urihttp://dspace.mit.edu/handle/1721.1/7582en_US
dc.subjectElectrical Engineering and Computer Science.en_US
dc.titleGeneralization of deep neural networks to unseen attribute combinationsen_US
dc.typeThesisen_US
dc.description.degreeM. Eng.en_US
dc.contributor.departmentMassachusetts Institute of Technology. Department of Electrical Engineering and Computer Scienceen_US
dc.identifier.oclc1237411492en_US
dc.description.collectionM.Eng. Massachusetts Institute of Technology, Department of Electrical Engineering and Computer Scienceen_US
dspace.imported2021-02-19T20:49:10Zen_US
mit.thesis.degreeMasteren_US
mit.thesis.departmentEECSen_US


Files in this item

Thumbnail

This item appears in the following Collection(s)

Show simple item record