Scalable black-box model explainability through low-dimensional visualizations

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.

Department dc:contributor.department

Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science

Grantor dc:publisher

Massachusetts Institute of Technology

Year dc:date.issued

2017

Author dc:creator

• Sinha, Aradhana

Advisor dc:contributor.advisor

• Thomas Finley and Tomas Palacios.

• Electrical Engineering and Computer Science.

Statement dc:rights

• 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.

Licence dc:rights.uri

• http://dspace.mit.edu/handle/1721.1/7582

Language dc:language.iso

eng

Handle dc:identifier.uri

http://hdl.handle.net/1721.1/113109

OAI identifier oai:identifier

oai:dspace.mit.edu:1721.1/113109