中文
相关论文

相关论文: On Robustness of Neural Ordinary Differential Equa…

200 篇论文

Continuous-depth neural networks, such as the Neural Ordinary Differential Equations (ODEs), have aroused a great deal of interest from the communities of machine learning and data science in recent years, which bridge the connection…

机器学习 · 计算机科学 2022-01-05 Qunxi Zhu , Yifei Shen , Dongsheng Li , Wei Lin

In data-driven modeling of spatiotemporal phenomena careful consideration often needs to be made in capturing the dynamics of the high wavenumbers. This problem becomes especially challenging when the system of interest exhibits shocks or…

机器学习 · 计算机科学 2022-12-28 Alec J. Linot , Joshua W. Burby , Qi Tang , Prasanna Balaprakash , Michael D. Graham , Romit Maulik

This paper presents the Standalone Neural ODE (sNODE), a continuous-depth neural ODE model capable of describing a full deep neural network. This uses a novel nonlinear conjugate gradient (NCG) descent optimization scheme for training,…

机器学习 · 计算机科学 2022-06-09 Rym Jaroudi , Lukáš Malý , Gabriel Eilertsen , B. Tomas Johansson , Jonas Unger , George Baravdish

Neural networks can be fragile to input noise and adversarial attacks. In this work, we consider Convolutional Neural Ordinary Differential Equations (NODEs), a family of continuous-depth neural networks represented by dynamical systems,…

机器学习 · 计算机科学 2025-08-18 Muhammad Zakwan , Liang Xu , Giancarlo Ferrari-Trecate

Deep residual networks (ResNets) have shown state-of-the-art performance in various real-world applications. Recently, the ResNets model was reparameterized and interpreted as solutions to a continuous ordinary differential equation or…

机器学习 · 计算机科学 2022-09-23 Duo Yu , Hongyu Miao , Hulin Wu

Using vanilla NeuralODEs to model large and/or complex systems often fails due two reasons: Stability and convergence. NeuralODEs are capable of describing stable as well as instable dynamic systems. Selecting an appropriate numerical…

机器学习 · 计算机科学 2023-02-23 Tobias Thummerer , Lars Mikelsons

Recently, Neural Ordinary Differential Equations has emerged as a powerful framework for modeling physical simulations without explicitly defining the ODEs governing the system, but instead learning them via machine learning. However, the…

Neural ordinary differential equations (NODEs) are an effective approach for data-driven modeling of dynamical systems arising from simulations and experiments. One of the major shortcomings of NODEs, especially when coupled with explicit…

数值分析 · 数学 2025-12-30 Allen Alvarez Loya , Daniel A. Serino , J. W. Burby , Qi Tang

Accurately learning solution operators for time-dependent partial differential equations (PDEs) from sparse and irregular data remains a challenging task. Recurrent DeepONet extensions inherit the discrete-time limitations of…

计算工程、金融与科学 · 计算机科学 2025-07-04 Diab W. Abueidda , Mbebo Nonna , Panos Pantidis , Mostafa E. Mobasher

Neural ordinary differential equations (ODEs) are an emerging class of deep learning models for dynamical systems. They are particularly useful for learning an ODE vector field from observed trajectories (i.e., inverse problems). We here…

机器学习 · 计算机科学 2023-05-23 Katharina Ott , Michael Tiemann , Philipp Hennig

To derive the hidden dynamics from observed data is one of the fundamental but also challenging problems in many different fields. In this study, we propose a new type of interpretable network called the ordinary differential equation…

动力系统 · 数学 2020-10-19 Pipi Hu , Wuyue Yang , Yi Zhu , Liu Hong

Neural Ordinary Differential Equations (N-ODEs) are a powerful building block for learning systems, which extend residual networks to a continuous-time dynamical system. We propose a Bayesian version of N-ODEs that enables well-calibrated…

机器学习 · 计算机科学 2020-02-19 Andreas Look , Melih Kandemir

Random ordinary differential equations (RODEs), i.e. ODEs with random parameters, are often used to model complex dynamics. Most existing methods to identify unknown governing RODEs from observed data often rely on strong prior knowledge.…

数值分析 · 数学 2020-06-04 Junyu Liu , Zichao Long , Ranran Wang , Jie Sun , Bin Dong

Residual neural networks can be viewed as the forward Euler discretization of an Ordinary Differential Equation (ODE) with a unit time step. This has recently motivated researchers to explore other discretization approaches and train ODE…

机器学习 · 计算机科学 2019-07-02 Amir Gholami , Kurt Keutzer , George Biros

Time series with non-uniform intervals occur in many applications, and are difficult to model using standard recurrent neural networks (RNNs). We generalize RNNs to have continuous-time hidden dynamics defined by ordinary differential…

机器学习 · 计算机科学 2019-07-10 Yulia Rubanova , Ricky T. Q. Chen , David Duvenaud

Ordinary differential equations (ODEs) provide a powerful framework for modeling dynamic systems arising in a wide range of scientific domains. However, most existing ODE methods focus on a single system, and do not adequately address the…

统计方法学 · 统计学 2026-04-08 Shuoxun Xu , Zijian Guo , Brooke R. Staveland , Robert T. Knight , Lexin Li

A neural ordinary differential equation (neural ODE) is a machine learning model that is commonly described as a continuous-depth generalization of a residual network (ResNet) with a single residual block, or conversely, the ResNet can be…

机器学习 · 计算机科学 2025-10-14 Abdelrahman Sayed Sayed , Pierre-Jean Meyer , Mohamed Ghazel

Residual neural networks are state-of-the-art deep learning models. Their continuous-depth analog, neural ordinary differential equations (ODEs), are also widely used. Despite their success, the link between the discrete and continuous…

机器学习 · 统计学 2024-07-08 Pierre Marion , Yu-Han Wu , Michael E. Sander , Gérard Biau

Deep learning methods have achieved great success in solving computer vision tasks, and they have been widely utilized in artificially intelligent systems for image processing, analysis, and understanding. However, deep neural networks have…

机器学习 · 计算机科学 2022-11-23 Hanshu Yan

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 ordinary and…

机器学习 · 计算机科学 2024-01-09 Lars Ruthotto