Strategical Deep Learning for Photonic Bound States in the Continuum (Laser Photonics Rev. 16(10)/2022). Issue 10 (11th October 2022)

• Record Type: Journal Article
• Authors: Ma, Xuezhi; Ma, Yuan; Cunha, Preston; Liu, Qiushi; Kudtarkar, Kaushik; Xu, Da; Wang, Jiafei; Chen, Yixin; Wong, Zi Jing; Liu, Ming; Hipwell, M. Cynthia; Lan, Shoufeng
• Is Part Of: Laser & photonics reviews. Volume 16:Issue 10(2022)
• Page Start: n/a
• Page End: n/a
• Publication Date: 2022-10-11
• Subjects: Lasers -- Periodicals; Photonics -- Periodicals; Lasers -- Périodiques; Photonique -- Périodiques; 621.36
• DOI: 10.1002/lpor.202270049
• Languages: English
• ISSNs: 1863-8880

Abstract

Abstract : Photonic Bound States in the Continuum In article number 2100658, Xuzhi Ma, Yuan Ma, Shoufeng Lan, and colleagues develop a universal deep learning strategy to design high‐finesse resonances with ultrasharp spectral features. Applying to photonic bound states in the continuum (BICs), they decompose a spectrum into a relatively smooth background and multiple spectral extremes with narrow linewidths, followed by an adaptive data acquisition method for high resolution. They further regulate such a nonlinear neural network with the physical meaning of resonances to prevent overfitting and local minima issues.