中文
相关论文

相关论文: Neural Networks with Local Converging Inputs (NNLC…

200 篇论文

Neural Networks (NNs) are the method of choice for building learning algorithms. Their popularity stems from their empirical success on several challenging learning problems. However, most scholars agree that a convincing theoretical…

数值分析 · 数学 2021-01-01 Ronald DeVore , Boris Hanin , Guergana Petrova

We propose Weak and Entropy PINNs (WE-PINNs) for the approximation of entropy solutions to nonlinear hyperbolic conservation laws. Standard physics-informed neural networks enforce governing equations in strong differential form, an…

State of the art models using deep neural networks have become very good in learning an accurate mapping from inputs to outputs. However, they still lack generalization capabilities in conditions that differ from the ones encountered during…

计算与语言 · 计算机科学 2018-08-28 Alexey Romanov , Chaitanya Shivade

Neural networks have been used to solve different types of large data related problems in many different fields.This project takes a novel approach to solving the Navier-Stokes Equations for turbulence by training a neural network using…

数值分析 · 计算机科学 2018-08-22 Megan McCracken

Network representation learning aims to generate an embedding for each node in a network, which facilitates downstream machine learning tasks such as node classification and link prediction. Current work mainly focuses on transductive…

社会与信息网络 · 计算机科学 2023-06-02 Meng Liu , Yong Liu

We explore unique considerations involved in fitting ML models to data with very high precision, as is often required for science applications. We empirically compare various function approximation methods and study how they scale with…

机器学习 · 计算机科学 2023-02-01 Eric J. Michaud , Ziming Liu , Max Tegmark

Neural networks can emulate nonlinear physical systems with high accuracy, yet they may produce physically-inconsistent results when violating fundamental constraints. Here, we introduce a systematic way of enforcing nonlinear analytic…

计算物理 · 物理学 2021-03-10 Tom Beucler , Michael Pritchard , Stephan Rasp , Jordan Ott , Pierre Baldi , Pierre Gentine

This paper analyzes local convergence of the block Newton (BN) method introduced in [5, 6] for one-dimensional shallow neural network approximation to functions and diffusion-reaction problems. The BN method consists of the 2x2 block…

数值分析 · 数学 2026-03-13 Zhiqiang Cai , Anastassia Doktorova , Robert D. Falgout , César Herrera

High dimensional data analysis for exploration and discovery includes three fundamental tasks: dimensionality reduction, clustering, and visualization. When the three associated tasks are done separately, as is often the case thus far,…

机器学习 · 计算机科学 2020-12-02 Stan Z. Li , Lirong Wu , Zelin Zang

Despite prior advances in PINNs, significant challenges remain in localized solid mechanics problems because of the limitations of single network formulations in simultaneous resolution of smooth global responses and near-tip singularities,…

计算物理 · 物理学 2025-10-22 Zhihong Lai , Luyang Zhao , Qian Shao

We study the mathematical theory of second order systems with two species, arising in the dynamics of interacting particles subject to linear damping, to nonlocal forces and to external ones, and resulting into a nonlocal version of the…

偏微分方程分析 · 数学 2022-10-13 Marco Di Francesco , Simone Fagioli , Valeria Iorio

Neural networks are a popular tool for modeling sequential data but they generally do not treat time as a continuous variable. Neural ODEs represent an important exception: they parameterize the time derivative of a hidden state with a…

机器学习 · 计算机科学 2021-06-15 Sam Greydanus , Stefan Lee , Alan Fern

We investigate the use of deep neural networks to control complex nonlinear dynamical systems, specifically the movement of a rigid body immersed in a fluid. We solve the Navier Stokes equations with two way coupling, which gives rise to…

机器学习 · 计算机科学 2022-06-02 Brener Ramos , Felix Trost , Nils Thuerey

We proposed a framework for solving inverse problems in differential equations based on neural networks and automatic differentiation. Neural networks are used to approximate hidden fields. We analyze the source of errors in the framework…

数值分析 · 数学 2024-12-20 Kailai Xu , Eric Darve

The existing paradox between theory and computational experiment for weak solutions of systems of conservation laws in higher space dimensions is arguably resolved. Apparently successful computations are identified with underlying…

偏微分方程分析 · 数学 2024-08-28 Michael Sever

A recent series of theoretical works showed that the dynamics of neural networks with a certain initialisation are well-captured by kernel methods. Concurrent empirical work demonstrated that kernel methods can come close to the performance…

机器学习 · 计算机科学 2021-06-11 Maria Refinetti , Sebastian Goldt , Florent Krzakala , Lenka Zdeborová

We develop a corrective mechanism for neural network approximation: the total available non-linear units are divided into multiple groups and the first group approximates the function under consideration, the second group approximates the…

机器学习 · 计算机科学 2020-06-23 Guy Bresler , Dheeraj Nagaraj

We propose a conservative energy method based on neural networks with subdomains for solving variational problems (CENN), where the admissible function satisfying the essential boundary condition without boundary penalty is constructed by…

数值分析 · 数学 2023-01-12 Yizheng Wang , Jia Sun , Wei Li , Zaiyuan Lu , Yinghua Liu

Neural Networks are used today in numerous security- and safety-relevant domains and are, as such, a popular target of attacks that subvert their classification capabilities, by manipulating the network parameters. Prior work has introduced…

机器学习 · 计算机科学 2021-09-10 Amel Nestor Docena , Thomas Wahl , Trevor Pearce , Yunsi Fei

We address the study of a class of 1D nonlocal conservation laws from a numerical point of view. First, we present an algorithm to numerically integrate them and prove its convergence. Then, we use this algorithm to investigate various…

数值分析 · 数学 2013-03-26 Paulo Amorim , Rinaldo M. Colombo , Andreia Teixeira