We develop a probabilistic Stokes flow framework, using physics informed Gaussian
processes, which can be used to solve both forward/inverse flow problems with missing …

Port-Hamiltonian systems (pHS) allow for a structure-preserving modeling of dynamical
systems. Coupling pHS via linear relations between input and output defines an overall …

We propose a meta-learning method for modeling Hamiltonian dynamics from a limited
number of data. Although Hamiltonian neural networks have been successfully used for …

Symmetries have proven useful in machine learning models, improving generalisation and
overall performance. At the same time, recent advancements in learning dynamical systems …

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 …

Hamiltonian mechanics is one of the cornerstones of natural sciences. Recently there has
been significant interest in learning Hamiltonian systems in a free-form way directly from …

Gaussian processes are powerful models for probabilistic machine learning and are often
employed because they can accurately quantify uncertainty, are analytically tractable, and …

Å lære ukjente dynamiske systemer er en kompleks oppgave som involverer å utlede den
underliggende systematferden fra observert data, uten forkunnskaper om de underliggende …

This paper focuses on a research question: How do we infer Hamiltonian vector fields under
uncertainty from data? One promising approach is a Gaussian process (GP) that can …

ガウス過程と物理現象のモデル化 Page 1 318 人 工 知 能 38 巻 3 号(2023 年 5 月) 1. はじめに
物理学や生物学などさまざまな自然科学分野にお いて,多くの自然現象のダイナミクスは常微分 …