Scalable black-box model explainability through low-dimensional visualizations
Thesis: M. Eng., Massachusetts Institute of Technology, Department of Electrical Engineering and Computer Science, 2017.
| Main Author: | |
|---|---|
| Other Authors: | |
| Format: | Thesis |
| Language: | eng |
| Published: |
Massachusetts Institute of Technology
2018
|
| Subjects: | |
| Online Access: | http://hdl.handle.net/1721.1/113109 |
| _version_ | 1826197901395623936 |
|---|---|
| author | Sinha, Aradhana |
| author2 | Thomas Finley and Tomas Palacios. |
| author_facet | Thomas Finley and Tomas Palacios. Sinha, Aradhana |
| author_sort | Sinha, Aradhana |
| collection | MIT |
| description | Thesis: M. Eng., Massachusetts Institute of Technology, Department of Electrical Engineering and Computer Science, 2017. |
| first_indexed | 2024-09-23T10:55:22Z |
| format | Thesis |
| id | mit-1721.1/113109 |
| institution | Massachusetts Institute of Technology |
| language | eng |
| last_indexed | 2024-09-23T10:55:22Z |
| publishDate | 2018 |
| publisher | Massachusetts Institute of Technology |
| record_format | dspace |
| spelling | mit-1721.1/1131092022-01-13T07:54:01Z Scalable black-box model explainability through low-dimensional visualizations Sinha, Aradhana Thomas Finley and Tomas Palacios. Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science. Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science Electrical Engineering and Computer Science. 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). 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. by Aradhana Sinha. M. Eng. 2018-01-12T20:56:26Z 2018-01-12T20:56:26Z 2017 2017 Thesis http://hdl.handle.net/1721.1/113109 1016448495 eng 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 41 pages application/pdf Massachusetts Institute of Technology |
| spellingShingle | Electrical Engineering and Computer Science. Sinha, Aradhana Scalable black-box model explainability through low-dimensional visualizations |
| title | Scalable black-box model explainability through low-dimensional visualizations |
| title_full | Scalable black-box model explainability through low-dimensional visualizations |
| title_fullStr | Scalable black-box model explainability through low-dimensional visualizations |
| title_full_unstemmed | Scalable black-box model explainability through low-dimensional visualizations |
| title_short | Scalable black-box model explainability through low-dimensional visualizations |
| title_sort | scalable black box model explainability through low dimensional visualizations |
| topic | Electrical Engineering and Computer Science. |
| url | http://hdl.handle.net/1721.1/113109 |
| work_keys_str_mv | AT sinhaaradhana scalableblackboxmodelexplainabilitythroughlowdimensionalvisualizations |