Scalable black-box model explainability through low-dimensional visualizations
Name
1016448495-MIT.pdf
Description
Full printable version
Size
1.17 MB
Format
Adobe PDF
Checksum (MD5)
f979e92c1f8671ef6789ad1dc7783b3e
Author(s)
Sinha, Aradhana
Advisor(s)
Thomas Finley and Tomas Palacios.
Date Issued
2017
Publisher
Massachusetts Institute of Technology
Abstract
Two methods are proposed to provide visual intuitive explanations for how black-box models work. The first is a projection pursuit-based method that seeks to provide data-point specific explanations. The second is a generalized additive model approach that seeks to explain the model on a more holistic level, enabling users to visualize the contributions across all features at once. Both models incorporate visual and interactive elements designed to create an intuitive understanding of both the logic and limits of the model. Both explanation systems are designed to scale well to large datasets with many data points and many features.
Description
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 39-40).
Subjects
Electrical Engineering and Computer Science.
MIT Department
Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science
Terms of Use
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.
Persistent DSpace Link
