Neural Networks for Stationary and Evolutionary Variational Problems
用于稳态和进化变分问题的神经网络
基本信息
- 批准号:2424801
- 负责人:
- 金额:$ 20.96万
- 依托单位:
- 依托单位国家:美国
- 项目类别:Continuing Grant
- 财政年份:2024
- 资助国家:美国
- 起止时间:2024-03-01 至 2026-07-31
- 项目状态:未结题
- 来源:
- 关键词:
项目摘要
Artificial neural networks have become one of the dominant models in data science, used in applications from image classification to natural language processing. Their empirical success in these diverse fields has sparked interest in further applying such models in new directions, such as numerical analysis and scientific computing. This project is aimed at developing a deeper understanding of the capabilities and limitations of the role of neural network models used for numerical analysis and scientific computing, particularly when compared with more classic tools. This is essential in enabling neural network models to be widely deployed in sensitive fields across engineering domains. Graduate students will be trained as part of this project, modern tools from data science and deep learning will be incorporated into graduate curricula, and outreach activities are planned to attract undergraduates as well as underrepresented groups in STEM into this research area.The focus of this work is on the use of neural network models in numerical algorithms used in models based on the calculus of variations, targeting two case studies. The first is related to functionals that exhibit the Lavrentiev gap phenomena, where an energy gap between the lowest energy achievable by shallow neural networks and more general functions is considered. The second is the Allen-Cahn equation, where the solution strategy of physics-inspired neural networks is analyzed. In the second problem, the adaptivity of neural networks to low-dimensional moving interfaces plays a key role when comparing to e.g. fixed mesh finite element methods. The theoretical results are intended to better understand two fundamental challenges. The first is whether the adaptivity of neural networks can be harnessed for the numerical approximation of spatially very inhomogeneous variational problems. The second seeks to understand the precise situations in which neural network solvers are not expected to outperform traditional solvers.This award reflects NSF's statutory mission and has been deemed worthy of support through evaluation using the Foundation's intellectual merit and broader impacts review criteria.
人工神经网络已经成为数据科学中的主要模型之一,应用于从图像分类到自然语言处理的各种应用中。他们在这些不同领域取得的经验成功激发了人们在数值分析和科学计算等新方向进一步应用这些模型的兴趣。这个项目的目的是加深对用于数值分析和科学计算的神经网络模型的能力和局限性的理解,特别是与更经典的工具相比。这对于使神经网络模型能够广泛应用于工程领域的敏感领域是至关重要的。作为该项目的一部分,将对研究生进行培训,将数据科学和深度学习的现代工具纳入研究生课程,并计划开展推广活动,以吸引本科生以及STEM中未被充分代表的群体进入该研究领域。本工作的重点是在基于变分的模型中使用神经网络模型,以两个案例研究为目标。第一类是与呈现拉夫伦蒂耶夫能隙现象的泛函有关,其中考虑了浅层神经网络所能达到的最低能量与更一般函数之间的能隙。其次是Allen-Cahn方程,分析了物理启发神经网络的求解策略。在第二个问题中,与固定网格有限元方法相比,神经网络对低维运动界面的适应性起着关键作用。理论结果旨在更好地理解两个根本挑战。第一个问题是能否利用神经网络的自适应能力对空间上非常不齐次的变分问题进行数值逼近。第二个奖项旨在了解神经网络解算器不会超越传统解算器的确切情况。这一奖项反映了NSF的法定使命,并通过使用基金会的智力优势和更广泛的影响审查标准进行评估,被认为值得支持。
项目成果
期刊论文数量(0)
专著数量(0)
科研奖励数量(0)
会议论文数量(0)
专利数量(0)
数据更新时间:{{ journalArticles.updateTime }}
{{
item.title }}
{{ item.translation_title }}
- DOI:
{{ item.doi }} - 发表时间:
{{ item.publish_year }} - 期刊:
- 影响因子:{{ item.factor }}
- 作者:
{{ item.authors }} - 通讯作者:
{{ item.author }}
数据更新时间:{{ journalArticles.updateTime }}
{{ item.title }}
- 作者:
{{ item.author }}
数据更新时间:{{ monograph.updateTime }}
{{ item.title }}
- 作者:
{{ item.author }}
数据更新时间:{{ sciAawards.updateTime }}
{{ item.title }}
- 作者:
{{ item.author }}
数据更新时间:{{ conferencePapers.updateTime }}
{{ item.title }}
- 作者:
{{ item.author }}
数据更新时间:{{ patent.updateTime }}
Stephan Wojtowytsch其他文献
Minimum norm interpolation by perceptra: Explicit regularization and implicit bias
感知的最小范数插值:显式正则化和隐式偏差
- DOI:
10.48550/arxiv.2311.06138 - 发表时间:
2023 - 期刊:
- 影响因子:0
- 作者:
Jiyoung Park;Ian Pelakh;Stephan Wojtowytsch - 通讯作者:
Stephan Wojtowytsch
Optimal bump functions for shallow ReLU networks: Weight decay, depth separation and the curse of dimensionality
浅层 ReLU 网络的最佳凹凸函数:权重衰减、深度分离和维数灾难
- DOI:
10.48550/arxiv.2209.01173 - 发表时间:
2022 - 期刊:
- 影响因子:0
- 作者:
Stephan Wojtowytsch - 通讯作者:
Stephan Wojtowytsch
Connected Coulomb columns: analysis and numerics
连接库仑柱:分析和数值
- DOI:
10.1088/1361-6544/ac022f - 发表时间:
2020 - 期刊:
- 影响因子:1.7
- 作者:
P. Dondl;M. Novaga;Stephan Wojtowytsch;Steve Wolff - 通讯作者:
Steve Wolff
Stochastic Gradient Descent with Noise of Machine Learning Type Part II: Continuous Time Analysis
- DOI:
10.1007/s00332-023-09992-0 - 发表时间:
2021-06 - 期刊:
- 影响因子:3
- 作者:
Stephan Wojtowytsch - 通讯作者:
Stephan Wojtowytsch
Stochastic Gradient Descent with Noise of Machine Learning Type Part I: Discrete Time Analysis
- DOI:
10.1007/s00332-023-09903-3 - 发表时间:
2021-05 - 期刊:
- 影响因子:3
- 作者:
Stephan Wojtowytsch - 通讯作者:
Stephan Wojtowytsch
Stephan Wojtowytsch的其他文献
{{
item.title }}
{{ item.translation_title }}
- DOI:
{{ item.doi }} - 发表时间:
{{ item.publish_year }} - 期刊:
- 影响因子:{{ item.factor }}
- 作者:
{{ item.authors }} - 通讯作者:
{{ item.author }}
{{ truncateString('Stephan Wojtowytsch', 18)}}的其他基金
Neural Networks for Stationary and Evolutionary Variational Problems
用于稳态和进化变分问题的神经网络
- 批准号:
2307273 - 财政年份:2023
- 资助金额:
$ 20.96万 - 项目类别:
Continuing Grant
相似国自然基金
军民两用即兴网(Ad Hoc Networks)的研究
- 批准号:60372093
- 批准年份:2003
- 资助金额:26.0 万元
- 项目类别:面上项目
相似海外基金
Molecular Control of Thermomechanics and Shape-Morphing of Dynamic Covalent Polymer Networks
热机械的分子控制和动态共价聚合物网络的形状变形
- 批准号:
2406256 - 财政年份:2024
- 资助金额:
$ 20.96万 - 项目类别:
Standard Grant
Collaborative Research: AF: Medium: Foundations of Oblivious Reconfigurable Networks
合作研究:AF:媒介:遗忘可重构网络的基础
- 批准号:
2402851 - 财政年份:2024
- 资助金额:
$ 20.96万 - 项目类别:
Continuing Grant
Cooperativity Driven Communication through Noncovalent Networks in Biomimetic Systems
仿生系统中通过非共价网络的协作驱动通信
- 批准号:
2404149 - 财政年份:2024
- 资助金额:
$ 20.96万 - 项目类别:
Standard Grant
EAGER: Search-Accelerated Markov Chain Monte Carlo Algorithms for Bayesian Neural Networks and Trillion-Dimensional Problems
EAGER:贝叶斯神经网络和万亿维问题的搜索加速马尔可夫链蒙特卡罗算法
- 批准号:
2404989 - 财政年份:2024
- 资助金额:
$ 20.96万 - 项目类别:
Standard Grant
Collaborative Research: Spintronics Enabled Stochastic Spiking Neural Networks with Temporal Information Encoding
合作研究:自旋电子学支持具有时间信息编码的随机尖峰神经网络
- 批准号:
2333881 - 财政年份:2024
- 资助金额:
$ 20.96万 - 项目类别:
Standard Grant
Collaborative Research: Spintronics Enabled Stochastic Spiking Neural Networks with Temporal Information Encoding
合作研究:自旋电子学支持具有时间信息编码的随机尖峰神经网络
- 批准号:
2333882 - 财政年份:2024
- 资助金额:
$ 20.96万 - 项目类别:
Standard Grant
Collaborative Research: Liquid Crystal-Templated Chemical Vapor Polymerization of Complex Nanofiber Networks
合作研究:复杂纳米纤维网络的液晶模板化学气相聚合
- 批准号:
2322900 - 财政年份:2024
- 资助金额:
$ 20.96万 - 项目类别:
Standard Grant
Place-Based, Human-Centered Networks to Enhance Community Resilience and Equity
以地方为基础、以人为本的网络,以增强社区的弹性和公平性
- 批准号:
2242719 - 财政年份:2024
- 资助金额:
$ 20.96万 - 项目类别:
Standard Grant
The International Political Thought of Women’s Regional Networks
妇女区域网络的国际政治思想
- 批准号:
DE240101244 - 财政年份:2024
- 资助金额:
$ 20.96万 - 项目类别:
Discovery Early Career Researcher Award
Deep Adder Networks on Edge Devices
边缘设备上的深加法器网络
- 批准号:
FT230100549 - 财政年份:2024
- 资助金额:
$ 20.96万 - 项目类别:
ARC Future Fellowships