2026-09-18T19:30:33Zhttps://dspace.mit.edu/server/oai/request

oai:dspace.mit.edu:1721.1/1195112026-06-06T00:55:53Zcom_1721.1_7582com_1721.1_7581col_1721.1_131023

Cèsar Hidalgo. Baker, Bowen Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science. Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science 2018-12-11T20:38:11Z 2018-12-11T20:38:11Z 2017 2017 http://hdl.handle.net/1721.1/119511 1066344391 Thesis: M. Eng., Massachusetts Institute of Technology, Department of Electrical Engineering and Computer Science, 2017. 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 (pages 69-73). This thesis primarily focuses on the topic of efficient automated procedures for convolutional neural network (CNN) architecture search. We first introduce a novel approach for CNN architecture architecture using Q-learning, a popular value iteration algorithm from the reinforcement learning community for sequential decision problems. On the task of object classification, the Q-learning agent outperforms all human crafted models that are similar to those in the search space. By analysing the underlying weights of the agent, we are also able to uncover some of the design principles that the agent learned during the search process. Reinforcement learning is generally very sample inefficient; in the case of architecture search most approaches require thousands of unique models to be trained. In the second part of this thesis we introduce simple sequential regression models (SRM) to predict final performance of a candidate CNN from partially observed learning curves. We use these performance predictors and empirical variance estimates for practical early stopping of online optimization procedures. Our SRMs are state-of-the-art in performance prediction and early stopping. by Bowen Baker. M.Eng. 73 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. Towards practical neural network meta-modeling Thesis application/pdf Publication unknown unknown <Publication xmlns="https://www.openaire.eu/cerif-profile/1.1/" id="cfbbf0fb-fa8e-4f10-9dd3-97ad379ea987"> <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>Towards practical neural network meta-modeling</Title> <PublishedIn> <Publication> </Publication> </PublishedIn> <PublicationDate>2017</PublicationDate> <Authors> <Author> <DisplayName>Baker, Bowen</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 thesis primarily focuses on the topic of efficient automated procedures for convolutional neural network (CNN) architecture search. We first introduce a novel approach for CNN architecture architecture using Q-learning, a popular value iteration algorithm from the reinforcement learning community for sequential decision problems. On the task of object classification, the Q-learning agent outperforms all human crafted models that are similar to those in the search space. By analysing the underlying weights of the agent, we are also able to uncover some of the design principles that the agent learned during the search process. Reinforcement learning is generally very sample inefficient; in the case of architecture search most approaches require thousands of unique models to be trained. In the second part of this thesis we introduce simple sequential regression models (SRM) to predict final performance of a candidate CNN from partially observed learning curves. We use these performance predictors and empirical variance estimates for practical early stopping of online optimization procedures. Our SRMs are state-of-the-art in performance prediction and early stopping.</Abstract> <Access xmlns="http://purl.org/coar/access_right" > </Access> </Publication>