2026-09-19T08:51:39Zhttps://dspace.mit.edu/server/oai/requestoai:dspace.mit.edu:1721.1/1195522026-06-06T00:56:20Zcom_1721.1_7582com_1721.1_7581col_1721.1_131023
Devavrat Shah.
Hager, Paul Andrew
Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science.
Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science
2018-12-11T20:39:49Z
2018-12-11T20:39:49Z
2018
2018
http://hdl.handle.net/1721.1/119552
1076273432
Thesis: M. Eng., Massachusetts Institute of Technology, Department of Electrical Engineering and Computer Science, 2018.
This electronic version was submitted by the student author. The certified thesis is available in the Institute Archives and Special Collections.
Cataloged from student-submitted PDF version of thesis.
Includes bibliographical references (page 21).
The field of machine learning (ML) has benefitted greatly from its relationship with the field of classical statistics. In support of that continued expansion, the following proposes an alternative perspective at the link between these fields. The link focuses on probabilistic graphical models in the context of reinforcement learning. Viewing certain algorithms as reinforcement learning gives one an ability to map ML concepts to statistics problems. Training a multi-layer nonlinear perceptron algorithm is equivalent to structure learning problems in probabilistic graphical models (PGMs). The technique of boosting weak rules into an ensemble is weighted sampling. Finally regularizing neural networks using the dropout technique is conditioning on certain observations in PGMs.
by Paul Andrew Hager.
M.Eng.
21 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.
Investigation of connection between deep learning and probabilistic graphical models
Thesis
application/pdf
false
Publication
unknown
unknown
<Publication xmlns="https://www.openaire.eu/cerif-profile/1.1/" id="f55cdcd5-8f75-430c-a6b5-bbc58aef9a19">
<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>Investigation of connection between deep learning and probabilistic graphical models</Title>
<PublishedIn>
<Publication>
</Publication>
</PublishedIn>
<PublicationDate>2018</PublicationDate>
<Authors>
<Author>
<DisplayName>Hager, Paul Andrew</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>The field of machine learning (ML) has benefitted greatly from its relationship with the field of classical statistics. In support of that continued expansion, the following proposes an alternative perspective at the link between these fields. The link focuses on probabilistic graphical models in the context of reinforcement learning. Viewing certain algorithms as reinforcement learning gives one an ability to map ML concepts to statistics problems. Training a multi-layer nonlinear perceptron algorithm is equivalent to structure learning problems in probabilistic graphical models (PGMs). The technique of boosting weak rules into an ensemble is weighted sampling. Finally regularizing neural networks using the dropout technique is conditioning on certain observations in PGMs.</Abstract>
<Access xmlns="http://purl.org/coar/access_right"
>
</Access>
</Publication>