论文信息 - Calibration of a 2×2 Optical Switch Based on the Back-Propagation Artificial Neural Network

Calibration of a 2×2 Optical Switch Based on the Back-Propagation Artificial Neural Network

We propose a method to calibrate 2×2 dual-ring assisted Mach-Zehnder interferometer switches based on a back-propagation artificial neural network (BP-ANN). The DR-MZI switch can be set to the cross or bar state at any operating wavelength in a free spectral range with the BP-ANN based algorithm. It is an effective method that can be adopted for calibration of DR-MZI switch elements in a large-scale switch fabric.

Linjie Zhou | Jianping Chen | Liangjun Lu | Wei Gao

[1] Jimmy Ba,et al. Adam: A Method for Stochastic Optimization , 2014, ICLR.

[2] Toshiaki Koike-Akino,et al. Deep Neural Network Inverse Design of Integrated Nanophotonic Devices. , 2018, 1809.03555.

[3] M. Carminati,et al. Feedback-controlled tuning, switching, and locking of photonic integrated circuits , 2015, 2015 International Conference on Photonics in Switching (PS).

[4] Xinwan Li,et al. Low-power 2×2 silicon electro-optic switches based on double-ring assisted Mach-Zehnder interferometers. , 2014, Optics letters.

[5] Linjie Zhou,et al. 16 × 16 Silicon Optical Switch Based on Dual-Ring-Assisted Mach–Zehnder Interferometers , 2018, Journal of Lightwave Technology.

[6] Xinwan Li,et al. $4\times 4$ Silicon Optical Switches Based on Double-Ring-Assisted Mach–Zehnder Interferometers , 2015, IEEE Photonics Technology Letters.

[7] Lior Wolf,et al. Deep learning for the design of nano-photonic structures , 2018, 2018 IEEE International Conference on Computational Photography (ICCP).

[8] Yikai Su,et al. Fast and Wide-Range Wavelength Locking Based on a Two-Layer Neural Network in a Silicon Microring Switch , 2019, 2019 Optical Fiber Communications Conference and Exhibition (OFC).