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.
@article{arxiv.2210.15070,
title = {Visual explanations of machine learning model estimating charge states in quantum dots},
author = {Yui Muto and Takumi Nakaso and Motoya Shinozaki and Takumi Aizawa and Takahito Kitada and Takashi Nakajima and Matthieu R. Delbecq and Jun Yoneda and Kenta Takeda and Akito Noiri and Arne Ludwig and Andreas D. Wieck and Seigo Tarucha and Atsunori Kanemura and Motoki Shiga and Tomohiro Otsuka},
journal= {arXiv preprint arXiv:2210.15070},
year = {2024}
}