2026-09-19T05:57:59Zhttps://dspace.mit.edu/server/oai/requestoai:dspace.mit.edu:1721.1/1195892026-06-06T00:49:38Zcom_1721.1_7582com_1721.1_7581col_1721.1_131023
Tomaso Poggio.
Han, Yena
Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science.
Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science
2018-12-11T21:07:33Z
2018-12-11T21:07:33Z
2017
2017
http://hdl.handle.net/1721.1/119589
1066694254
Thesis: M. Eng., Massachusetts Institute of Technology, Department of Electrical Engineering and Computer Science, 2017.
Cataloged from PDF version of thesis.
Includes bibliographical references (pages 45-46).
This work first characterizes human invariant recognition in one-shot learning. By using novel stimuli, we address the question whether invariance to transformation emerges from experience and memorization of templates or from the brain instantly computing invariant representation. Our psychophysical experimental results suggest that human vision produces a representation that is robust in terms of scale change, but it needs experience for translation-invariance. Next, we examine the implication of the experimental data with regards to computational modeling. In particular, we confirm that the eccentricity-dependent model [16], where scale-invariance is built in the underlying architecture, reproduces the human data closely.
Funded by NSF STC award CCF-1231216
by Yena Han.
M.Eng.
46 pages
eng
Massachusetts Institute of Technology
MIT theses are protected by copyright. They may be viewed, downloaded, or printed from this source but further reproduction or distribution in any format is prohibited without written permission.
http://dspace.mit.edu/handle/1721.1/7582
Electrical Engineering and Computer Science.
Invariance properties of the human visual system in one-shot learning
Thesis
application/pdf
false
Publication
unknown
unknown
<Publication xmlns="https://www.openaire.eu/cerif-profile/1.1/" id="5689fffd-640b-4650-b1be-2aebf596a9af">
<Type xmlns="https://www.openaire.eu/cerif-profile/vocab/COAR_Publication_Types">http://purl.org/coar/resource_type/c_1843</Type>
<Language>eng</Language>
<Title>Invariance properties of the human visual system in one-shot learning</Title>
<PublishedIn>
<Publication>
</Publication>
</PublishedIn>
<PublicationDate>2017</PublicationDate>
<Authors>
<Author>
<DisplayName>Han, Yena</DisplayName>
<Affiliation>
<OrgUnit>
</OrgUnit>
</Affiliation>
</Author>
</Authors>
<Editors>
</Editors>
<Publishers>
<Publisher>
<DisplayName>Massachusetts Institute of Technology</DisplayName>
<OrgUnit />
</Publisher>
</Publishers>
<License>http://dspace.mit.edu/handle/1721.1/7582</License>
<Keyword>Electrical Engineering and Computer Science.</Keyword>
<Abstract>This work first characterizes human invariant recognition in one-shot learning. By using novel stimuli, we address the question whether invariance to transformation emerges from experience and memorization of templates or from the brain instantly computing invariant representation. Our psychophysical experimental results suggest that human vision produces a representation that is robust in terms of scale change, but it needs experience for translation-invariance. Next, we examine the implication of the experimental data with regards to computational modeling. In particular, we confirm that the eccentricity-dependent model [16], where scale-invariance is built in the underlying architecture, reproduces the human data closely.</Abstract>
<Access xmlns="http://purl.org/coar/access_right"
>
</Access>
</Publication>