Visual explanations of machine learning model estimating charge states in quantum dots

TL;DR

This paper analyzes the explainability of a machine learning model used for charge state recognition in quantum dots, using gradient-weighted class activation mapping to improve understanding and performance, facilitating scalable quantum device automation.

Contribution

It introduces a method to interpret the black-box ML model for quantum dot charge state estimation, enhancing its accuracy and scalability through explainability techniques.

Findings

Gradient-weighted class activation mapping identifies key regions for predictions.

Explainability improves model performance with feedback from mapping results.

Approach is scalable with minimal additional simulation costs.

Abstract

Charge state recognition in quantum dot devices is important in the preparation of quantum bits for quantum information processing. Toward auto-tuning of larger-scale quantum devices, automatic charge state recognition by machine learning has been demonstrated. For further development of this technology, an understanding of the operation of the machine learning model, which is usually a black box, will be useful. In this study, we analyze the explainability of the machine learning model estimating charge states in quantum dots by gradient-weighted class activation mapping, which identified class-discriminative regions for the predictions. The model predicts the state based on the change transition lines, indicating that human-like recognition is realized. We also demonstrate improvements of the model by utilizing feedback from the mapping results. Due to the simplicity of our simulation and pre-processing methods, our approach offers scalability without significant additional simulation costs, demonstrating its suitability for future quantum dot system expansions.