English
Related papers

Related papers: Hamiltonian Neural Networks with Automatic Symmetr…

200 papers

Diversity conveys advantages in nature, yet homogeneous neurons typically comprise the layers of artificial neural networks. Here we construct neural networks from neurons that learn their own activation functions, quickly diversify, and…

Machine Learning · Computer Science 2023-09-01 Anshul Choudhary , Anil Radhakrishnan , John F. Lindner , Sudeshna Sinha , William L. Ditto

Concise, accurate descriptions of physical systems through their conserved quantities abound in the natural sciences. In data science, however, current research often focuses on regression problems, without routinely incorporating…

Computational Physics · Physics 2020-02-05 Tom Bertalan , Felix Dietrich , Igor Mezić , Ioannis G. Kevrekidis

Binary Neural Network (BNN) converts full-precision weights and activations into their extreme 1-bit counterparts, making it particularly suitable for deployment on lightweight mobile devices. While binary neural networks are typically…

Machine Learning · Computer Science 2025-01-08 Jun Chen , Jingyang Xiang , Tianxin Huang , Xiangrui Zhao , Yong Liu

We present a physical interpretation of machine learning functions, opening up the possibility to control properties of statistical systems via the inclusion of these functions in Hamiltonians. In particular, we include the predictive…

High Energy Physics - Lattice · Physics 2021-02-17 Dimitrios Bachtis , Gert Aarts , Biagio Lucini

Neural networks that synergistically integrate data and physical laws offer great promise in modeling dynamical systems. However, iterative gradient-based optimization of network parameters is often computationally expensive and suffers…

Machine Learning · Computer Science 2026-04-16 Atamert Rahma , Chinmay Datar , Felix Dietrich

Identifying the underlying dynamics of physical systems can be challenging when only provided with observational data. In this work, we consider systems that can be modelled as first-order ordinary differential equations. By assuming a…

Systems and Control · Electrical Eng. & Systems 2024-01-03 Sigurd Holmsen , Sølve Eidnes , Signe Riemer-Sørensen

Measurement data is often sampled irregularly i.e. not on equidistant time grids. This is also true for Hamiltonian systems. However, existing machine learning methods, which learn symplectic integrators, such as SympNets [20] and…

Machine Learning · Computer Science 2025-09-22 Konrad Janik , Peter Benner

Machine learning techniques are employed to perform the full characterization of a quantum system. The particular artificial intelligence technique used to learn the Hamiltonian is called physics informed neural network (PINN). The idea…

The incorporation of appropriate inductive bias plays a critical role in learning dynamics from data. A growing body of work has been exploring ways to enforce energy conservation in the learned dynamics by encoding Lagrangian or…

Robotics · Computer Science 2021-11-15 Yaofeng Desmond Zhong , Biswadip Dey , Amit Chakraborty

Here we present Symplectically Integrated Symbolic Regression (SISR), a novel technique for learning physical governing equations from data. SISR employs a deep symbolic regression approach, using a multi-layer LSTM-RNN with mutation to…

Machine Learning · Computer Science 2022-09-07 Daniel M. DiPietro , Bo Zhu

Representing and learning from graphs is essential for developing effective machine learning models tailored to non-Euclidean data. While Graph Neural Networks (GNNs) strive to address the challenges posed by complex, high-dimensional graph…

Quantum Physics · Physics 2025-01-15 Wenxuan Wang

We propose a perturbation algorithm for Hamiltonian systems on a Lie algebra $\mathbb{V}$, so that it can be applied to non-canonical Hamiltonian systems. Given a Hamiltonian system that preserves a subalgebra $\mathbb{B}$ of $\mathbb{V}$,…

Dynamical Systems · Mathematics 2021-01-06 Lorenzo Valvo , Michel Vittot

In this work, we introduce a hypergraph representation learning framework called Hypergraph Neural Networks (HNN) that jointly learns hyperedge embeddings along with a set of hyperedge-dependent embeddings for each node in the hypergraph.…

Machine Learning · Computer Science 2023-01-02 Ryan Aponte , Ryan A. Rossi , Shunan Guo , Jane Hoffswell , Nedim Lipka , Chang Xiao , Gromit Chan , Eunyee Koh , Nesreen Ahmed

Despite the successes of machine learning methods in physical sciences, prediction of the Hamiltonian, and thus electronic properties, is still unsatisfactory. Here, based on graph neural network architecture, we present an extendable…

Materials Science · Physics 2023-01-12 Mao Su , Ji-Hui Yang , Hong-Jun Xiang , Xin-Gao Gong

A deep understanding of the intricate interactions between particles within a system is a key approach to revealing the essential characteristics of the system, whether it is an in-depth analysis of molecular properties in the field of…

High Energy Physics - Lattice · Physics 2024-12-17 Ru Geng , Yixian Gao , Jian Zu , Hong-Kun Zhang

The symmetries play important roles in physical systems. We study the symmetries of a Hamiltonian system by investigating the asymmetry of the Hamiltonian with respect to certain algebras. We define the asymmetry of an operator with respect…

Quantum Physics · Physics 2020-01-29 Hui-Hui Qin , Shao-Ming Fei , Chang-Pu Sun

We consider the learning and prediction of nonlinear time series generated by a latent symplectic map. A special case is (not necessarily separable) Hamiltonian systems, whose solution flows give such symplectic maps. For this special case,…

Machine Learning · Computer Science 2021-06-15 Renyi Chen , Molei Tao

Hidden Markov models (HMMs) and partially observable Markov decision processes (POMDPs) form a useful tool for modeling dynamical systems. They are particularly useful for representing environments such as road networks and office…

Artificial Intelligence · Computer Science 2013-01-30 Hagit Shatkay

Real-world visual data exhibit intrinsic hierarchical structures that can be represented effectively in hyperbolic spaces. Hyperbolic neural networks (HNNs) are a promising approach for learning feature representations in such spaces.…

Computer Vision and Pattern Recognition · Computer Science 2024-02-08 Ahmad Bdeir , Kristian Schwethelm , Niels Landwehr

Many physical systems can be best understood as sets of discrete data with associated relationships. Where previously these sets of data have been formulated as series or image data to match the available machine learning architectures,…