English
Related papers

Related papers: AI Poincar\'e: Machine Learning Conservation Laws …

200 papers

The variational auto-encoder (VAE) is a popular method for learning a generative model and embeddings of the data. Many real datasets are hierarchically structured. However, traditional VAEs map data in a Euclidean latent space which cannot…

Machine Learning · Statistics 2019-11-27 Emile Mathieu , Charline Le Lan , Chris J. Maddison , Ryota Tomioka , Yee Whye Teh

This article is devoted to the study of a $2$-dimensional piecewise smooth (but possibly) discontinuous dynamical system, subject to a non-autonomous perturbation; we assume that the unperturbed system admits a homoclinic trajectory…

Dynamical Systems · Mathematics 2025-02-10 Alessandro Calamai , Matteo Franca , Michal Pospisil

We show that deep learning algorithms can be deployed to study bifurcations of particle trajectories. We demonstrate this for two physical systems, the unperturbed Duffing equation and charged particles in magnetic reversal by using the AI…

Computational Physics · Physics 2023-10-02 Morteza Mohseni

Precise trajectory tracking for legged robots can be challenging due to their high degrees of freedom, unmodeled nonlinear dynamics, or random disturbances from the environment. A commonly adopted solution to overcome these challenges is to…

Robotics · Computer Science 2025-09-01 Jing Cheng , Yasser G. Alqaham , Amit K. Sanyal , Zhenyu Gan

Lagrangian Neural Networks (LNNs) are a powerful tool for addressing physical systems, particularly those governed by conservation laws. LNNs can parametrize the Lagrangian of a system to predict trajectories with nearly conserved energy.…

Machine Learning · Computer Science 2025-07-29 Viviana Alejandra Diaz , Leandro Martin Salomone , Marcela Zuccalli

The Poincar\'e-Bendixson theorem plays an important role in the study of the qualitative behavior of dynamical systems on the plane; it describes the structure of limit sets in such systems. We prove a version of the Poincar\'e-Bendixson…

Dynamical Systems · Mathematics 2018-01-30 William Clark , Anthony Bloch , Leonardo Colombo

The spectacular results achieved in machine learning, including the recent advances in generative AI, rely on large data collections. On the opposite, intelligent processes in nature arises without the need for such collections, but simply…

Machine Learning · Computer Science 2024-02-12 Alessandro Betti , Marco Gori

Many important physical systems can be described as the evolution of a Hamiltonian system, which has the important property of being conservative, that is, energy is conserved throughout the evolution. Physics Informed Neural Networks and…

Machine Learning · Computer Science 2025-12-10 Harsh Choudhary , Chandan Gupta , Vyacheslav Kungurtsev , Melvin Leok , Georgios Korpas

Conservation laws are an inherent feature in many systems modeling real world phenomena, in particular, those modeling biological and chemical systems. If the form of the underlying dynamical system is known, linear algebra and algebraic…

Numerical Analysis · Mathematics 2024-03-11 Tracey Oellerich , Maria Emelianenko

Application of artificial intelligence (AI), and more specifically machine learning, to the physical sciences has expanded significantly over the past decades. In particular, science-informed AI, also known as scientific AI or inductive…

Exploring chaotic systems via Poincar\'e sections has proven essential in dynamical systems, yet measuring their characteristics poses challenges to identify the various dynamical regimes considered. In this paper, we propose a new approach…

Chaotic Dynamics · Physics 2024-09-23 André Farinha Bósio , Iberê Luiz Caldas , Ricardo Luiz Viana , Yves Elskens

We introduce a data-driven method for learning the equations of motion of mechanical systems directly from position measurements, without requiring access to velocity data. This is particularly relevant in system identification tasks where…

Systems and Control · Electrical Eng. & Systems 2025-05-28 Martine Dyring Hansen , Elena Celledoni , Benjamin Kwanen Tapley

Inferring universal laws of the environment is an important ability of human intelligence as well as a symbol of general AI. In this paper, we take a step toward this goal such that we introduce a new challenging problem of inferring…

Artificial Intelligence · Computer Science 2018-11-30 Siyu Huang , Zhi-Qi Cheng , Xi Li , Xiao Wu , Zhongfei Zhang , Alexander Hauptmann

A machine-learning approach called "reservoir computing" has been used successfully for short-term prediction and attractor reconstruction of chaotic dynamical systems from time series data. We present a theoretical framework that describes…

Chaotic Dynamics · Physics 2018-08-01 Zhixin Lu , Brian R. Hunt , Edward Ott

Recently, there has been an increasing interest in modelling and computation of physical systems with neural networks. Hamiltonian systems are an elegant and compact formalism in classical mechanics, where the dynamics is fully determined…

Numerical Analysis · Mathematics 2022-06-28 Elena Celledoni , Andrea Leone , Davide Murari , Brynjulf Owren

We present that, instead of establishing the equations of motion, one can model-freely reveal the dynamical properties of a black-box system using a learning machine. Trained only by a segment of time series of a state variable recorded at…

Machine Learning · Computer Science 2022-04-15 Hong Zhao

Poincar\'e maps play a fundamental role in nonlinear dynamics and chaos theory, offering a means to reduce the dimensionality of continuous dynamical systems by tracking the intersections of trajectories with lower-dimensional section…

Instrumentation and Methods for Astrophysics · Physics 2026-01-21 A. K. de Almeida , Daniele Mortari

Many different models of the physical world exhibit chaotic dynamics, from fluid flows and chemical reactions to celestial mechanics. The study of the three-body problem (3BP) and its many different families of unstable periodic orbits…

Dynamical Systems · Mathematics 2025-12-04 Owen M. Brook , Jason J. Bramburger , Davide Amato , Urban Fasel

The intrinsic nature of a problem usually suggests a first suitable method to deal with it. Unfortunately, the apparent ease of application of these initial approaches may make their possible flaws seem to be inherent to the problem and…

Classical Analysis and ODEs · Mathematics 2022-02-17 Victoriano Carmona , Fernando Fernández-Sánchez

We describe a machine-learning system that uses linear vector-space based techniques for inference from observations to extend previous work on model construction for particle physics (Valdes-Perez 96, 94, Kocabas 91). The program searches…

High Energy Physics - Phenomenology · Physics 2007-05-23 Oliver Schulte , Mark S. Drew