Zobrazeno 1 - 10
of 81
pro vyhledávání: '"Yaguchi, Takaharu"'
Deep learning has achieved great success in modeling dynamical systems, providing data-driven simulators to predict complex phenomena, even without known governing equations. However, existing models have two major limitations: their narrow focus on
Externí odkaz:
http://arxiv.org/abs/2410.11480
The operator learning has received significant attention in recent years, with the aim of learning a mapping between function spaces. Prior works have proposed deep neural networks (DNNs) for learning such a mapping, enabling the learning of solution
Externí odkaz:
http://arxiv.org/abs/2402.09018
Autor:
Matsubara, Takashi, Yaguchi, Takaharu
Physics-informed neural networks (PINNs) offer a novel and efficient approach to solving partial differential equations (PDEs). Their success lies in the physics-informed loss, which trains a neural network to satisfy a given PDE at specific points a
Externí odkaz:
http://arxiv.org/abs/2307.13869
Autor:
Matsubara, Takashi, Yaguchi, Takaharu
Publikováno v:
The Eleventh International Conference on Learning Representations (ICLR2023)
Many real-world dynamical systems are associated with first integrals (a.k.a. invariant quantities), which are quantities that remain unchanged over time. The discovery and understanding of first integrals are fundamental and important topics both in
Externí odkaz:
http://arxiv.org/abs/2210.00272
Publikováno v:
In Physica D: Nonlinear Phenomena December 2024 470 Part A
We propose a theoretical framework for investigating a modeling error caused by numerical integration in the learning process of dynamics. Recently, learning equations of motion to describe dynamics from data using neural networks has been attracting
Externí odkaz:
http://arxiv.org/abs/2112.14014
Autor:
Terakawa, Shunpei, Yaguchi, Takaharu
We derived a condition under which a coupled system consisting of two finite-dimensional Hamiltonian systems becomes a Hamiltonian system. In many cases, an industrial system can be modeled as a coupled system of some subsystems. Although it is known
Externí odkaz:
http://arxiv.org/abs/2112.13589
Definite integrals with parameters of holonomic functions satisfy holonomic systems of linear partial differential equations. When we restrict parameters to a one dimensional curve, the system becomes a linear ordinary differential equation (ODE) wit
Externí odkaz:
http://arxiv.org/abs/2111.10947
Many physical phenomena are described by Hamiltonian mechanics using an energy function (the Hamiltonian). Recently, the Hamiltonian neural network, which approximates the Hamiltonian as a neural network, and its extensions have attracted much attent
Externí odkaz:
http://arxiv.org/abs/2102.11923
Publikováno v:
35th Conference on Neural Information Processing Systems (NeurIPS 2021)
A neural network model of a differential equation, namely neural ODE, has enabled the learning of continuous-time dynamical systems and probabilistic distributions with high accuracy. The neural ODE uses the same network repeatedly during a numerical
Externí odkaz:
http://arxiv.org/abs/2102.09750