Extending Explainable Boosting Machines to Scientific Image Data

TL;DR

This paper introduces the application of Explainable Boosting Machines (EBMs) to scientific image data, demonstrating their interpretability and effectiveness in a quantum technology context, specifically for cold-atom soliton images.

Contribution

The paper extends EBMs to handle image data in scientific applications, showcasing their interpretability and applicability in quantum physics research.

Findings

EBMs can be effectively applied to scientific image data.

The approach provides explanations aligned with human intuition.

First demonstration of EBMs for image data in scientific research.

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.