Non-Hermitian systems offer new platforms for unusual physical properties that can be flexibly manipulated by redistribution of the real and imaginary parts of refractive indices, whose presence breaks conventional wave propagation symmetries, leading to asymmetric reflection and symmetric transmission with respect to the wave propagation direction. Here, we use supervised and unsupervised learning techniques for knowledge acquisition in non-Hermitian systems which accelerate the inverse design process. In particular, we construct a deep learning model that relates the transmission and asymmetric reflection in non-conservative settings and propose sub-manifold learning to recognize non-Hermitian features from transmission spectra. The developed deep learning framework determines the feasibility of a desired spectral response for a given structure and uncovers the role of effective gain-loss parameters to tailor the spectral response. These findings offer a route for intelligent inverse design and contribute to the understanding of physical mechanism in general non-Hermitian systems.
|Original language||English (US)|
|State||Published - Jan 3 2023|
Bibliographical noteKAUST Repository Item: Exported on 2023-01-05
Acknowledged KAUST grant number(s): BAS/1/1626-01-01
Acknowledgements: The work described in here is supported by King Abdullah University of Science and Technology (KAUST) Artificial Intelligence Initiative Fund and KAUST Baseline Research Fund No. BAS/1/1626-01-01. K.S. acknowledges funding from European Social Fund (project No 09.3.3-LMT-K712-17- 0016) under grant agreement with the Research Council of Lithuania (LMTLT), and from the Spanish Ministerio de Ciencia e Innovación under grant No.385 (PID2019-109175GB-C21).