2026-09-19T01:18:55Zhttps://dspace.mit.edu/server/oai/requestoai:dspace.mit.edu:1721.1/1298752026-06-06T00:49:35Zcom_1721.1_7582com_1721.1_7581col_1721.1_131023
Tomaso Poggio.
Dozier, Jamell(Jamell A.)
Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science.
Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science
2021-02-19T20:33:18Z
2021-02-19T20:33:18Z
2020
2020
https://hdl.handle.net/1721.1/129875
1237416359
Thesis: M. Eng., Massachusetts Institute of Technology, Department of Electrical Engineering and Computer Science, February, 2020
Cataloged from student-submitted PDF of thesis.
Includes bibliographical references (pages 69-70).
Visual cognition has long been the subject of curiosity within the realm of deep learning. While much research has gone into the development of neural network models that can at times outperform humans, the underlying principles behind truly understanding visual concepts remain elusive. Utilizing a multitask learning paradigm, we first explore the capacity for networks to generalize to understand visual reasoning concepts. We introduce a simplified visual reasoning dataset to train several network architectures, including a recently proposed model built specifically for relational reasoning. We collect the best performing networks and view their behavior on a neuronal level: visualizing task selectivity through patterns of activations from each network layer. Finally, we adjust our focus to a simpler form of visual reasoning involving the extraction of single attributes from attribute compositions. Here, we are able to both visualize and quantify the neuron task selectivity that leads to generalization.
by Jamell Dozier.
M.Eng.
M.Eng. Massachusetts Institute of Technology, Department of Electrical Engineering and Computer Science
70 pages
eng
Massachusetts Institute of Technology
MIT 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.
http://dspace.mit.edu/handle/1721.1/7582
Electrical Engineering and Computer Science.
Emergent patterns of task-specific neurons in deep neural networks
Thesis
application/pdf
2021-02-19T20:32:48Z
Publication
Master
EECS
unknown
unknown
<Publication xmlns="https://www.openaire.eu/cerif-profile/1.1/" id="521cf2c7-b198-44a8-a7b2-0daf58495fef">
<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>Emergent patterns of task-specific neurons in deep neural networks</Title>
<PublishedIn>
<Publication>
</Publication>
</PublishedIn>
<PublicationDate>2020</PublicationDate>
<Authors>
<Author>
<DisplayName>Dozier, Jamell(Jamell A.)</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>Visual cognition has long been the subject of curiosity within the realm of deep learning. While much research has gone into the development of neural network models that can at times outperform humans, the underlying principles behind truly understanding visual concepts remain elusive. Utilizing a multitask learning paradigm, we first explore the capacity for networks to generalize to understand visual reasoning concepts. We introduce a simplified visual reasoning dataset to train several network architectures, including a recently proposed model built specifically for relational reasoning. We collect the best performing networks and view their behavior on a neuronal level: visualizing task selectivity through patterns of activations from each network layer. Finally, we adjust our focus to a simpler form of visual reasoning involving the extraction of single attributes from attribute compositions. Here, we are able to both visualize and quantify the neuron task selectivity that leads to generalization.</Abstract>
<Access xmlns="http://purl.org/coar/access_right"
>
</Access>
</Publication>