.png){kind=icon}
返回
FxTS-Net: Fixed-time stable learning framework for Neural ODEs
.png){kind=icon}
PRE
AI
DOI：10.1016/j.neunet.2025.107219.png)
.png){kind=icon}
原文求助.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
Neural Ordinary Differential Equations (Neural ODEs), as a novel category of modeling big data methods, cleverly link traditional neural networks and dynamical systems. However, it is challenging to ensure the dynamics system reaches a correctly predicted state within a user-defined fixed time. To address this problem, we propose anew method for training Neural ODEs using fixed-time stability (FxTS) Lyapunov conditions. Our framework, called FxTS-Net, is based on the novel FxTS loss (FxTS-Loss) designed on Lyapunov functions, which aims to encourage convergence to accurate predictions in a user-defined fixed time. We also provide an innovative approach for constructing Lyapunov functions to meet various tasks and network architecture requirements, achieved by leveraging supervised information during training. By developing amore precise time upper bound estimation for bounded non-vanishingly perturbed systems, we demonstrate that minimizing FxTS-Loss not only guarantees FxTS behavior of the dynamics but also input perturbation robustness. For optimizing FxTS-Loss, we also propose a learning algorithm, in which the simulated perturbation sampling method can capture sample points in critical regions to approximate FxTS-Loss. Experimentally, we find that FxTS-Net provides better prediction performance and better robustness under input perturbation.
Keyword:
Neural ODEs
Fixed-time stability
Adversarial robustness
期刊
IF:
6.3
论文数:
8.2K
被引数:
3.0W
机构
引用论文
Differential effects of plant root systems on nickel, copper and silver bioavailability in contaminated soil.png)
Chemosphere
ChemosphereIF0
PREAI
分享收藏Adaptive Decision Spatio-temporal neural ODE for traffic flow forecasting with Multi-Kernel Temporal Dynamic Dilation ConvolutionNEURAL NETWORKS
NEURAL NETWORKSIF6.3
PREAI
分享收藏分享收藏Adversarially robust neural networks with feature uncertainty learning and label embedding具有特征不确定性学习和标签嵌入的对抗鲁棒神经网络NEURAL NETWORKS
NEURAL NETWORKSIF6.3
PREAI
分享收藏Interaction of neutral and protonated Tamoxifen with the DPPC lipid bilayer using molecular dynamics simulationSteroids
SteroidsIF0
PREAI
分享收藏Exploiting dynamic spatio-temporal graph convolutional neural networks for citywide traffic flows prediction利用动态时空图卷积神经网络进行全市交通流预测NEURAL NETWORKS
NEURAL NETWORKSIF6.3
PREAI
分享收藏Perspectives of Molecularly Imprinted Polymer-Based Drug Delivery Systems in Ocular TherapyPolymers
OAAI
PolymersIF0
OAAI分享收藏
查看更多内容