Within this work, we will discuss our recent and promising advances in the development of machine learning assisted optimization schemes for plasmonic/photonic meta-structures design development. We will showcase that by coupling adversarial autoencoding network with topology optimization, it is possible to expand conventional meta-device design methodology to a global optimization space. In the second part of the talk, we will cover our recent effort on coupling machine learning classification/regression algorithms with quantum measurements. Particularly, we will show that the synergy between advanced machine learning assisted data analysis with quantum optical measurements dramatically reduces data collection time as well as increases the accuracy of the measurements.
The alert did not successfully save. Please try again later.
Zhaxylyk A. Kudyshev, Simeon Bogdanov, Alexander V. Kildishev, Alexandra Boltasseva, Vladimir M. Shalaev, "Machine learning assisted plasmonics and quantum optics," Proc. SPIE 11460, Metamaterials, Metadevices, and Metasystems 2020, 1146018 (20 August 2020); https://doi.org/10.1117/12.2567310