颂歌
人工神经网络
常微分方程
计算机科学
非线性系统
光学
炸薯条
光子学
残余物
微分方程
算法
人工智能
物理
数学
应用数学
数学分析
电信
量子力学
作者
Zhao Yun,Hang Chen,Min Lin,Haiou Zhang,Tao Yan,Xing Lin,Xing Lin,Qionghai Dai
出处
期刊:Optics Letters
[The Optical Society]
日期:2022-11-14
卷期号:48 (3): 628-628
被引量:2
摘要
Increasing the layer number of on-chip photonic neural networks (PNNs) is essential to improve its model performance. However, the successively 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-ODE) 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 (ResNet) and 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 ResNet in image classification tasks. Besides, the ONODE 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.
科研通智能强力驱动
Strongly Powered by AbleSci AI