paper-with-me

홈 › Papers

Mastering high-dimensional dynamics with Hamiltonian neural networks

2020-07-28 · Scott T. Miller, John F. Lindner, Anshul Choudhary, Sudeshna Sinha, William L. Ditto

We detail how incorporating physics into neural network design can significantly improve the learning and forecasting of dynamical systems, even nonlinear systems of many dimensions. A map building perspective elucidates the superiority of Hamiltonian neural networks over conventional neural networks. The results clarify the critical relation between data, dimension, and neural network learning performance.

📄 PDF Abstract BibTeX arXiv:2008.04214

Code (0)

등록된 구현이 없습니다.

Tasks

RelationVocal Bursts Intensity Prediction

Similar Papers 제목 키워드 기반

Learning Hamiltonian Dynamics at Scale: A Differential-Geometric Approach

2025-09-29 · Katharina Friedl, Noémie Jaquier, Alyx Liao, Danica Kragic arxiv

Embedding physical intuition into network architectures allows the learning of dynamics that enforce fundamental properties, such as energy conservation laws, thereby leading to physically-plausible predictions. Yet, sca…

Physical Intuition

Data-Driven Identification of Quadratic Representations for Nonlinear Hamiltonian Systems using Weakly Symplectic Liftings

2023-08-02 · Süleyman Yıldız, Pawan Goyal, Thomas Bendokat, Peter Benner

We present a framework for learning Hamiltonian systems using data. This work is based on a lifting hypothesis, which posits that nonlinear Hamiltonian systems can be written as nonlinear systems with cubic Hamiltonians.…

Position

Identify Then Project: Contrastive Learning of Latent Dynamics from Partial Observations with Port-Hamiltonian Structure

2026-05-15 · Peilun Li, Kaiyuan Tan, Daniel Moyer, Thomas Beckers arxiv

Identifying latent state representations and dynamics is essential when direct modeling in observation space is infeasible, particularly under partial and high-dimensional observations. In such settings, representation l…

Representation LearningContrastive Learning

Machine Learning a Molecular Hamiltonian for Predicting Electron Dynamics

2020-07-19 · Harish S. Bhat, Karnamohit Ranka, Christine M. Isborn

We develop a computational method to learn a molecular Hamiltonian matrix from matrix-valued time series of the electron density. As we demonstrate for three small molecules, the resulting Hamiltonians can be used for el…

BIG-bench Machine LearningCPUTime SeriesTime Series Analysis

Hamiltonian Generative Networks

2019-09-30 · ICLR 2020 1 · Peter Toth, Danilo Jimenez Rezende, Andrew Jaegle, Sébastien Racanière 외

The Hamiltonian formalism plays a central role in classical and quantum physics. Hamiltonians are the main tool for modelling the continuous time evolution of systems with conserved quantities, and they come equipped wit…

Reinforcement Learning