Skip to main content
U.S. flag

An official website of the United States government

Official websites use .gov
A .gov website belongs to an official government organization in the United States.

Secure .gov websites use HTTPS
A lock ( ) or https:// means you’ve safely connected to the .gov website. Share sensitive information only on official, secure websites.

Extending Explainable Boosting Machines to Scientific Image Data

Published

Author(s)

Daniel Schug, Sai Yerramreddy, Rich Caruana, Craig Greenberg, Justyna Zwolak

Abstract

As the deployment of computer vision technology becomes increasingly common in science, the need for explanations of the system and its output has become a focus of great concern. Driven by the pressing need for interpretable models in science, we propose the use of Explainable Boosting Machines (EBMs) for scientific image data. Inspired by an important application underpinning the development of quantum technologies, we apply EBMs to cold-atom soliton image data tabularized using Gabor Wavelet Transform-based techniques that preserve the spatial structure of the data. In doing so, we demonstrate the use of EBMs for image data for the first time and show that our approach provides explanations that are consistent with human intuition about the data.
Proceedings Title
Proceedings of the Machine Learning and the Physical Sciences Workshop, NeurIPS 2023
Conference Dates
December 10-16, 2023
Conference Location
New Orleans, LA, US
Conference Title
Workshop on Machine Learning and the Physical Sciences

Keywords

explainable boosting machines for image data, scientific data, explainable image processing, physics, Bose-Einstein Condensates

Citation

Schug, D. , Yerramreddy, S. , Caruana, R. , Greenberg, C. and Zwolak, J. (2023), Extending Explainable Boosting Machines to Scientific Image Data, Proceedings of the Machine Learning and the Physical Sciences Workshop, NeurIPS 2023 , New Orleans, LA, US, [online], https://tsapps.nist.gov/publication/get_pdf.cfm?pub_id=936910 (Accessed October 3, 2024)

Issues

If you have any questions about this publication or are having problems accessing it, please contact reflib@nist.gov.

Created November 30, 2023