English
Related papers

Related papers: Time-Reversal Symmetric ODE Network

200 papers

In conventional ODE modelling coefficients of an equation driving the system state forward in time are estimated. However, for many complex systems it is practically impossible to determine the equations or interactions governing the…

Machine Learning · Statistics 2018-03-13 Markus Heinonen , Cagatay Yildiz , Henrik Mannerström , Jukka Intosalmi , Harri Lähdesmäki

Neural Ordinary Differential Equations (ODEs) represent a significant advancement at the intersection of machine learning and dynamical systems, offering a continuous-time analog to discrete neural networks. Despite their promise, deploying…

Numerical Analysis · Mathematics 2025-06-18 Matteo Caldana , Jan S. Hesthaven

Neural ordinary differential equations (ODEs) have been attracting increasing attention in various research domains recently. There have been some works studying optimization issues and approximation capabilities of neural ODEs, but their…

Machine Learning · Computer Science 2022-03-04 Hanshu Yan , Jiawei Du , Vincent Y. F. Tan , Jiashi Feng

Spatio-temporal forecasting is essential for real-world applications such as traffic management and urban computing. Although recent methods have shown improved accuracy, they often fail to account for dynamic deviations between current…

Machine Learning · Computer Science 2025-10-07 Haotian Gao , Zheng Dong , Jiawei Yong , Shintaro Fukushima , Kenjiro Taura , Renhe Jiang

We present a new microscopic ODE-based model for pedestrian dynamics: the Gradient Navigation Model. The model uses a superposition of gradients of distance functions to directly change the direction of the velocity vector. The velocity is…

Mathematical Physics · Physics 2014-06-11 Felix Dietrich , Gerta Köster

In artificial neural networks, weights are a static representation of synapses. However, synapses are not static, they have their own interacting dynamics over time. To instill weights with interacting dynamics, we use a model describing…

Neural and Evolutionary Computing · Computer Science 2023-01-11 Adam Kohan , Ed Rietman , Hava Siegelmann

We explore in detail a method to solve ordinary differential equations using feedforward neural networks. We prove a specific loss function, which does not require knowledge of the exact solution, to be a suitable standard metric to…

Computational Physics · Physics 2020-06-02 Liam L. H. Lau , Denis Werth

Orbital dynamics in time-reversal-symmetric centrosymmetric systems is examined theoretically. Contrary to common belief, we demonstrate that many aspects of orbital dynamics are qualitatively different from spin dynamics because the…

Mesoscale and Nanoscale Physics · Physics 2022-05-03 Seungyun Han , Hyun-Woo Lee , Kyoung-Whan Kim

Multiscale stochastic dynamical systems have been widely adopted to a variety of scientific and engineering problems due to their capability of depicting complex phenomena in many real world applications. This work is devoted to…

Machine Learning · Statistics 2024-01-02 Lingyu Feng , Ting Gao , Min Dai , Jinqiao Duan

Neural differential equations are a promising new member in the neural network family. They show the potential of differential equations for time series data analysis. In this paper, the strength of the ordinary differential equation (ODE)…

Machine Learning · Computer Science 2020-05-21 Mansura Habiba , Barak A. Pearlmutter

A dynamical system is said to be reversible if, given an output, the input can always be recovered in a well-posed manner. Nevertheless, we argue that reversible systems that have a time-reversal symmetry, such as the Nonlinear…

Analysis of PDEs · Mathematics 2020-05-20 Amir Sagiv , Adi Ditkowski , Roy H. Goodman , Gadi Fibich

Time-series forecasting models often encounter abrupt changes in a given period of time which generally occur due to unexpected or unknown events. Despite their scarce occurrences in the training set, abrupt changes incur loss that…

Machine Learning · Computer Science 2023-09-25 Junwoo Park , Jungsoo Lee , Youngin Cho , Woncheol Shin , Dongmin Kim , Jaegul Choo , Edward Choi

Residual networks (ResNets) are a deep learning architecture that substantially improved the state of the art performance in certain supervised learning tasks. Since then, they have received continuously growing attention. ResNets have a…

Machine Learning · Computer Science 2020-03-02 Johannes Müller

Modeling the traffic dynamics is essential for understanding and predicting the traffic spatiotemporal evolution. However, deriving the partial differential equation (PDE) models that capture these dynamics is challenging due to their…

Systems and Control · Electrical Eng. & Systems 2025-05-05 Zihang Wei , Yunlong Zhang , Chenxi Liu , Yang Zhou

Recent advances in stochastic differential equations (SDEs) have enabled robust modeling of real-world dynamical processes across diverse domains, such as finance, health, and systems biology. However, parameter estimation for SDEs…

Machine Learning · Computer Science 2026-01-29 Long Van Tran , Truyen Tran , Phuoc Nguyen

Spatiotemporal dynamics pervade the natural sciences, from the morphogen dynamics underlying patterning in animal pigmentation to the protein waves controlling cell division. A central challenge lies in understanding how controllable…

Pattern Formation and Solitons · Physics 2025-03-03 Matthew Ricci , Guy Pelc , Zoe Piran , Noa Moriel , Mor Nitzan

A broken time-reversal symmetry, i.e. broken detailed balance, is central to non-equilibrium physics and is a prerequisite for life. However, it turns out to be quite challenging to unambiguously define and quantify time-reversal symmetry…

Statistical Mechanics · Physics 2025-03-20 Cai Dieball , Aljaž Godec

Due to their dynamic properties such as irregular sampling rate and high-frequency sampling, Continuous Time Series (CTS) are found in many applications. Since CTS with irregular sampling rate are difficult to model with standard Recurrent…

Machine Learning · Computer Science 2025-03-13 C. Coelho , M. Fernanda P. Costa , L. L. Ferrás

This paper addresses the data-driven identification of latent dynamical representations of partially-observed systems, i.e., dynamical systems for which some components are never observed, with an emphasis on forecasting applications,…

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…

Machine Learning · Computer Science 2020-02-19 Andreas Look , Melih Kandemir