Regularizing Image Classification Neural Networks with Partial Differential Equations
Differential equations can be used to design neural networks. For instance, neural ordinary differential equations (neural ODEs) can be considered as a continuous generalization of residual networks. In this work, we present a novel partial differential equation (PDE)-based approach for image classification, where we learn both a PDE's governing equation for image classification and its solution approximated by our neural network. In other words, the knowledge contained by the learned governing equation can be injected into the neural network which approximates the PDE solution function. Owing to the recent advancement of learning PDEs, the presented novel concept, called PR-Net, can be implemented. Our method shows comparable (or better) accuracy and robustness for various datasets and tasks in comparison with neural ODEs and Isometric MobileNet V3. For the efficient nature of PR-Net, it is suitable to be deployed in resource-scarce environments, e.g., deploying instead of MobileNet.
Code (0)
등록된 구현이 없습니다.
Tasks
Classificationimage-classificationImage ClassificationSimilar Papers 제목 키워드 기반
Jacobian Regularization Stabilizes Long-Term Integration of Neural Differential Equations
Hybrid models and Neural Differential Equations (NDE) are getting increasingly important for the modeling of physical systems, however they often encounter stability and accuracy issues during long-term integration. Trai…
Operator-learning-inspired Modeling of Neural Ordinary Differential Equations
Neural ordinary differential equations (NODEs), one of the most influential works of the differential equation-based deep learning, are to continuously generalize residual networks and opened a new field. They are curren…
image-classificationImage ClassificationImage GenerationOperator learning+2Hyena Neural Operator for Partial Differential Equations
Numerically solving partial differential equations typically requires fine discretization to resolve necessary spatiotemporal scales, which can be computationally expensive. Recent advances in deep learning have provided…
STEER: Simple Temporal Regularization For Neural ODEs
Training Neural Ordinary Differential Equations (ODEs) is often computationally expensive. Indeed, computing the forward pass of such models involves solving an ODE which can become arbitrarily complex during training. R…
Time SeriesTime Series AnalysisSTEER : Simple Temporal Regularization For Neural ODE
Training Neural Ordinary Differential Equations (ODEs) is often computationally expensive. Indeed, computing the forward pass of such models involves solving an ODE which can become arbitrarily complex during training. R…
Time SeriesTime Series Analysis