• DOI:10.48550/arXiv.2205.04051
• Corpus ID: 248571770

Unsupervised Learning of Rydberg Atom Array Phase Diagram with Siamese Neural Networks

@article{Patel2022UnsupervisedLO,
  title={Unsupervised Learning of Rydberg Atom Array Phase Diagram with Siamese Neural Networks},
  author={Zakaria Patel and Ejaaz Merali and Sebastian Johann Wetzel},
  journal={ArXiv},
  year={2022},
  volume={abs/2205.04051}
}

• Zakaria Patel, Ejaaz Merali, S. Wetzel
• Published 9 May 2022
• Computer Science
• ArXiv

. We introduce an unsupervised machine learning method based on Siamese Neural Networks (SNN) to detect phase boundaries. This method is applied to Monte-Carlo simulations of Ising-type systems and Rydberg atom arrays. In both cases the SNN reveals phase boundaries consistent with prior research. The combination of leveraging the power of feed-forward neural networks, unsupervised learning and the ability to learn about multiple phases without knowing about their existence provides a powerful method to explore new and unknown phases of matter. include a stacked Ising model and the Rydberg atom array. Subsequently, we describe how we prepare the input data using Monte Carlo simulations. We describe how Siamese neural networks are constructed and trained, and develop our framework to do unsupervised learning of phase transitions. Then we apply our method to both models and present the results in the form of the predicted underlying phase structure. Finally, we summarize our findings and place our method into the broader context of machine learning tools for phase recognition.