A Robust MZI-Based Optical Neural Network Using QR Decomposition
Jian Lin, Kang Yang, Qiang Fu, Pengjun Wang, Shixun Dai, Weiwei Chen, Dejun Kong, Jun Li, Tingge Dai, Jianyi Yang · Journal of Lightwave Technology · 2024
In this paper, a robust MZI-based optical neural network using QR decomposition is proposed and investigated. To construct optical linear unit, (N2+N)/2 MZIs are required to achieveN×Nweight matrixWin the case of QR decomposition, while in the case of singular value decomposition,N2MZIs are needed. A two-layer MZI-based optical neural network using QR decomposition, in which each layer comprises the 4 × 4 optical linear unit and absolute activation function, is designed to identify the first four MNIST handwritten digit images to verify the feasibility of our proposal. A validation accuracy of 81.5% is obtained in the simulation. As a proof of concept, the designed MZI-based optical neural network using QR decomposition was fabricated an SOI platform. Experimental results show that, the measured validation accuracy is 72.5%. Under the same situation, the corresponding validation accuracy of the MZI-based optical neural network using singular value decomposition is estimated to be 67.25%. Compared to MZI-based optical neural network using singular value decomposition, the presented MZI-based optical neural network using QR decomposition needs fewer MZIs and has stronger robustness. If the size of the matrixWincreases, these advantages of the presented MZI-based optical neural network using QR decomposition will become more apparent.