Investigation of connection between deep learning and probabilistic graphical models
Author(s)
Hager, Paul Andrew
DownloadFull printable version (301.6Kb)
Other Contributors
Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science.
Advisor
Devavrat Shah.
Terms of use
Metadata
Show full item recordAbstract
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.
Description
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).
Date issued
2018Department
Massachusetts Institute of Technology. Department of Electrical Engineering and Computer SciencePublisher
Massachusetts Institute of Technology
Keywords
Electrical Engineering and Computer Science.