2026-09-18T17:33:34Zhttps://dspace.mit.edu/server/oai/requestoai:dspace.mit.edu:1721.1/1242422026-06-06T00:54:47Zcom_1721.1_7582com_1721.1_7581col_1721.1_131023
Leslie P. Kaelbling and Tomás Lozano-Pérez.
Gentili, Paolo(Paolo Y.)
Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science.
Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science
2020-03-24T15:35:58Z
2020-03-24T15:35:58Z
2019
2019
https://hdl.handle.net/1721.1/124242
1145013781
This electronic version was submitted by the student author. The certified thesis is available in the Institute Archives and Special Collections.
Thesis: M. Eng., Massachusetts Institute of Technology, Department of Electrical Engineering and Computer Science, 2019
Cataloged from student-submitted PDF version of thesis.
Includes bibliographical references (pages 49-51).
Deep learning models have found enormous success across a variety of displines, but training the parameters within these models generally requires huge amounts of labelled data. One technique to reduce the burden of this data requirement is meta-learning, which involves extracting knowledge from previously experienced tasks so we can train new tasks with less data. Another such technique is active learning, where we selectively query labels for examples to train on, which potentially allows us to train a new task with fewer labelled data points. We investigate the potential to use active learning in the meta-learning setting, combining the advantages of the two techniques and further reducing the requirements for labelled data. In particular, we consider several techniques for actively querying labels within the modular meta-learning framework. We apply these techniques to several empirical settings, finding significant advantages over a baseline of random queries.
by Paolo Gentili.
M.Eng.
M.Eng. Massachusetts Institute of Technology, Department of Electrical Engineering and Computer Science
51 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.
Active learning using meta-learned priors
Thesis
application/pdf
2020-03-24T15:35:57Z
Publication
Master
EECS
unknown
unknown
<Publication xmlns="https://www.openaire.eu/cerif-profile/1.1/" id="78ad701c-a159-4715-acbd-e3e586d8768f">
<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>Active learning using meta-learned priors</Title>
<PublishedIn>
<Publication>
</Publication>
</PublishedIn>
<PublicationDate>2019</PublicationDate>
<Authors>
<Author>
<DisplayName>Gentili, Paolo(Paolo Y.)</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>Deep learning models have found enormous success across a variety of displines, but training the parameters within these models generally requires huge amounts of labelled data. One technique to reduce the burden of this data requirement is meta-learning, which involves extracting knowledge from previously experienced tasks so we can train new tasks with less data. Another such technique is active learning, where we selectively query labels for examples to train on, which potentially allows us to train a new task with fewer labelled data points. We investigate the potential to use active learning in the meta-learning setting, combining the advantages of the two techniques and further reducing the requirements for labelled data. In particular, we consider several techniques for actively querying labels within the modular meta-learning framework. We apply these techniques to several empirical settings, finding significant advantages over a baseline of random queries.</Abstract>
<Access xmlns="http://purl.org/coar/access_right"
>
</Access>
</Publication>