Optical Neural Ordinary Differential Equations
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.
Code (0)
등록된 구현이 없습니다.
Tasks
image-classificationImage ClassificationTrajectory PredictionMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
Transport Effects on Multiple-Component Reactions in Optical Biosensors
Optical biosensors are often used to measure kinetic rate constants associated with chemical reactions. Such instruments operate in the \textit{surface-volume} configuration, in which ligand molecules are convected throu…
parameter estimationModelling Chemical Reaction Networks using Neural Ordinary Differential Equations
In chemical reaction network theory, ordinary differential equations are used to model the temporal change of chemical species concentration. As the functional form of these ordinary differential equations systems is der…
FormTracking Control of Optical Beam Transceivers using Mean Field Models
This paper proposes mean field models to maintain an accurate line-of-sight and tracking between transceivers mounted in mobile unmanned aerial vehicles (UAVs) platforms in the presence of underlying mechanical vibration…
Differential Equations for Continuous-Time Deep Learning
This short, self-contained article seeks to introduce and survey continuous-time deep learning approaches that are based on neural ordinary differential equations (neural ODEs). It primarily targets readers familiar with…
Deep LearningSurveyNeural Ordinary Differential Equations for Learning and Extrapolating System Dynamics Across Bifurcations
Forecasting system behaviour near and across bifurcations is crucial for identifying potential shifts in dynamical systems. While machine learning has recently been used to learn critical transitions and bifurcation stru…