中文
相关论文

相关论文: A logical re-conception of neural networks: Hamilt…

200 篇论文

Artificial and biological neural networks (ANNs and BNNs) can encode inputs in the form of combinations of individual neurons' activities. These combinatorial neural codes present a computational challenge for direct and efficient analysis…

神经与进化计算 · 计算机科学 2022-10-20 Thomas F Burns , Irwansyah

This paper offers a new perspective on Artificial Neural Networks (ANNs) architecture. Traditional ANNs commonly use tree-like or DAG structures for simplicity, which can be preset or determined by Neural Architecture Search (NAS). Yet,…

机器学习 · 计算机科学 2025-06-05 Xinshun Liu , Yizhi Fang , Yichao Jiang

We explore the use of graph neural networks (GNNs) to model spatial processes in which there is no a priori graphical structure. Similar to finite element analysis, we assign nodes of a GNN to spatial locations and use a computational…

We present a form of algebraic reasoning for computational objects which are expressed as graphs. Edges describe the flow of data between primitive operations which are represented by vertices. These graphs have an interface made of…

计算机科学中的逻辑 · 计算机科学 2010-07-23 Lucas Dixon , Ross Duncan , Aleks Kissinger

We explore the use of Physics Informed Neural Networks to analyse nonlinear Hamiltonian Dynamical Systems with a first integral of motion. In this work, we propose an architecture which combines existing Hamiltonian Neural Network…

机器学习 · 计算机科学 2023-08-09 Vedanta Thapar

Hypergraphs are a powerful abstraction for representing higher-order interactions between entities of interest. To exploit these relationships in making downstream predictions, a variety of hypergraph neural network architectures have…

机器学习 · 计算机科学 2023-06-21 Yuxin Wang , Quan Gan , Xipeng Qiu , Xuanjing Huang , David Wipf

Neighborhood regression has been a successful approach in graphical and structural equation modeling, with applications to learning undirected and directed graphical models. We extend these ideas by defining and studying an algebraic…

统计理论 · 数学 2019-02-07 Arash A. Amini , Bryon Aragam , Qing Zhou

In traditional Graph Neural Networks (GNNs), the assumption of a fixed embedding manifold often limits their adaptability to diverse graph geometries. Recently, Hamiltonian system-inspired GNNs have been proposed to address the dynamic…

机器学习 · 计算机科学 2024-07-25 Jiaxu Liu , Xinping Yi , Tianle Zhang , Xiaowei Huang

There has been increasing interest in methodologies that incorporate physics priors into neural network architectures to enhance their modeling capabilities. A family of these methodologies that has gained traction are Hamiltonian neural…

经典物理 · 物理学 2024-12-05 Ignacio Puiggros T. , A. Srikantha Phani

In this article we study the possibilities of recovering the structure of port-Hamiltonian systems starting from ``unlabelled'' ordinary differential equations describing mechanical systems. The algorithm we suggest solves the problem in…

计算工程、金融与科学 · 计算机科学 2023-04-26 Vladimir Salnikov , Antoine Falaize , Daria Loziienko

With a view to bridging the gap between deep learning and symbolic AI, we present a novel end-to-end neural network architecture that learns to form propositional representations with an explicitly relational structure from raw pixel data.…

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…

材料科学 · 物理学 2023-01-12 Mao Su , Ji-Hui Yang , Hong-Jun Xiang , Xin-Gao Gong

We propose a general framework to extract microscopic interactions from raw configurations with deep neural networks. The approach replaces the modeling Hamiltonian by the neural networks, in which the interaction is encoded. It can be…

计算物理 · 物理学 2020-08-19 Lingxiao Wang , Yin Jiang , Kai Zhou

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…

高能物理 - 格点 · 物理学 2024-12-17 Ru Geng , Yixian Gao , Jian Zu , Hong-Kun Zhang

To make progress in science, we often build abstract representations of physical systems that meaningfully encode information about the systems. The representations learnt by most current machine learning techniques reflect statistical…

Many real world network problems often concern multivariate nodal attributes such as image, textual, and multi-view feature vectors on nodes, rather than simple univariate nodal attributes. The existing graph estimation methods built on…

机器学习 · 统计学 2013-04-23 Mladen Kolar , Han Liu , Eric P. Xing

Embedding-based methods for reasoning in knowledge hypergraphs learn a representation for each entity and relation. Current methods do not capture the procedural rules underlying the relations in the graph. We propose a simple…

机器学习 · 计算机科学 2021-02-19 Bahare Fatemi , Perouz Taslakian , David Vazquez , David Poole

When learning dynamical systems from data, embedding physical structure can constrain the solution space and improve generalization, but many physics-informed models assume access to the full system state. This limits their use in partially…

机器学习 · 计算机科学 2026-05-25 Sunniva Meltzer , Sølve Eidnes , Alexander Johannes Stasik

Hypergraphs provide a natural way to represent polyadic relationships in network data. For large hypergraphs, it is often difficult to visually detect structures within the data. Recently, a scalable polygon-based visualization approach was…

图形学 · 计算机科学 2024-07-30 Peter Oliver , Eugene Zhang , Yue Zhang

Graphs can model networked data by representing them as nodes and their pairwise relationships as edges. Recently, signal processing and neural networks have been extended to process and learn from data on graphs, with achievements in tasks…

机器学习 · 计算机科学 2021-10-07 Maosheng Yang , Elvin Isufi , Geert Leus
‹ 上一页 1 2 3 10 下一页 ›