Abstract

Increasing the layer number of on-chip photonic neural networks (PNNs) is essential to improve its model performance. However, the successive cascading of network hidden layers results in larger integrated photonic chip areas. To address this issue, we propose the optical neural ordinary differential equations (ON-ODEs) architecture that parameterizes the continuous dynamics of hidden layers with optical ODE solvers. The ON-ODE comprises the PNNs followed by the photonic integrator and optical feedback loop, which can be configured to represent residual neural networks (ResNets) and implement the function of recurrent neural networks with effectively reduced chip area occupancy. For the interference-based optoelectronic nonlinear hidden layer, the numerical experiments demonstrate that the single hidden layer ON-ODE can achieve approximately the same accuracy as the two-layer optical ResNets in image classification tasks. In addition, the ON-ODE improves the model classification accuracy for the diffraction-based all-optical linear hidden layer. The time-dependent dynamics property of ON-ODE is further applied for trajectory prediction with high accuracy.

© 2023 Optica Publishing Group

Optical solver for a system of ordinary differential equations based on an external feedback assisted microring resonator

Jie Hou, Jianji Dong, and Xinliang Zhang
Opt. Lett. 42(12) 2310-2313 (2017)

On-chip all-optical second-order ordinary differential equation solver based on a single microdisk resonator

Jiahao Zhou, Pengxing Guo, Jingsi Li, Bing Lu, Luan H. K. Duong, Weigang Hou, and Lei Guo
Opt. Express 31(21) 34154-34168 (2023)

Programmable low-threshold optical nonlinear activation functions for photonic neural networks

Ying Huang, Weiping Wang, Lei Qiao, Xiaoyan Hu, and Tao Chu
Opt. Lett. 47(7) 1810-1813 (2022)

High-frame-rate reconfigurable diffractive neural network based on superpixels

Yuan Qu, Hengyu Lian, Chunxu Ding, Huazhen Liu, Linxian Liu, and Jiamiao Yang
Opt. Lett. 48(19) 5025-5028 (2023)

Forward–forward training of an optical neural network

Ilker Oguz, Junjie Ke, Qifei Weng, Feng Yang, Mustafa Yildirim, Niyazi Ulas Dinc, Jih-Liang Hsieh, Christophe Moser, and Demetri Psaltis
Opt. Lett. 48(20) 5249-5252 (2023)