Precise nanofabrication represents a critical challenge to developing semiconductor quantum-dot qubits for practical quantum computation. Here, we design and train a convolutional neural network to interpret in-line scanning electron micrographs and quantify qualitative features affecting device functionality. The high-throughput strategy is exemplified by optimizing a model lithographic process within a five-dimensional design space and by demonstrating a new approach to address lithographic proximity effects. The present results emphasize the benefits of machine learning for developing robust processes, shortening development cycles, and enforcing quality control during qubit fabrication.
@article{arxiv.2012.08653,
title = {Optimization of Quantum-dot Qubit Fabrication via Machine Learning},
author = {Antonio B. Mei and Ivan Milosavljevic and Amanda L. Simpson and Valerie A. Smetanka and Colin P. Feeney and Shay M. Seguin and Sieu D. Ha and Wonill Ha and Matthew D. Reed},
journal= {arXiv preprint arXiv:2012.08653},
year = {2022}
}