paper-with-me

Papers

Parameter-varying neural ordinary differential equations with partition-of-unity networks

2022-10-01 · Kookjin Lee, Nathaniel Trask

In this study, we propose parameter-varying neural ordinary differential equations (NODEs) where the evolution of model parameters is represented by partition-of-unity networks (POUNets), a mixture of experts architecture. The proposed variant of NODEs, synthesized with POUNets, learn a meshfree partition of space and represent the evolution of ODE parameters using sets of polynomials associated to each partition. We demonstrate the effectiveness of the proposed method for three important tasks: data-driven dynamics modeling of (1) hybrid systems, (2) switching linear dynamical systems, and (3) latent dynamics for dynamical systems with varying external forcing.

📄 PDF Abstract BibTeX arXiv:2210.00368

Code (0)

등록된 구현이 없습니다.

Tasks

Mixture-of-ExpertsUnity

Similar Papers 제목 키워드 기반

Neural Generalized Ordinary Differential Equations with Layer-varying Parameters

2022-09-21 · Duo Yu, Hongyu Miao, Hulin Wu

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 different…

Computational Efficiency

Tunable Complexity Benchmarks for Evaluating Physics-Informed Neural Networks on Coupled Ordinary Differential Equations

2022-10-14 · Alexander New, Benjamin Eng, Andrea C. Timm, Andrew S. Gearhart

In this work, we assess the ability of physics-informed neural networks (PINNs) to solve increasingly-complex coupled ordinary differential equations (ODEs). We focus on a pair of benchmarks: discretized partial differen…

Automatically identifying ordinary differential equations from data

2023-04-21 · Kevin Egan, Weizhen Li, Rui Carvalho

Discovering nonlinear differential equations that describe system dynamics from empirical data is a fundamental challenge in contemporary science. Here, we propose a methodology to identify dynamical laws by integrating …

DenoisingregressionTime Series

Parameterized Neural Ordinary Differential Equations: Applications to Computational Physics Problems

2020-10-28 · Kookjin Lee, Eric J. Parish

This work proposes an extension of neural ordinary differential equations (NODEs) by introducing an additional set of ODE input parameters to NODEs. This extension allows NODEs to learn multiple dynamics specified by the…

Decoder

Neural Ordinary Differential Equations for Learning and Extrapolating System Dynamics Across Bifurcations

2025-07-25 · Eva van Tegelen, George van Voorn, Ioannis Athanasiadis, Peter van Heijster arxiv

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…