检索结果-南通市图书馆

维普期刊数据库评论

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

AI助力打造科学研究新范式

中国科学院院刊 2024年第1期39卷 10-16页

作者：鄂维南北京大学北京100871 北京科学智能研究院北京100084

科学研究的目的是发现基本原理和解决实际问题。尽管人类在发现基本原理和解决实际问题上已经取得了巨大成就,但有效工具和有效科研组织模式的缺乏仍然是制约科研效率的主要瓶颈。人工智能(AI)的迅速发展为改变这种状况提供了新的可能... 详细信息

科学研究的目的是发现基本原理和解决实际问题。尽管人类在发现基本原理和解决实际问题上已经取得了巨大成就,但有效工具和有效科研组织模式的缺乏仍然是制约科研效率的主要瓶颈。人工智能(AI)的迅速发展为改变这种状况提供了新的可能。近年来,深度学习方法在科学研究领域大放异彩,不仅助力解决了一些核心科学问题,扩展了科学方法,也开始带动科学研究从传统的“作坊模式”转向“平台模式”。目前,我国已在人工智能驱动的科学(AI for Science)领域打下良好基础,应把握机遇,争取引领科技创新,为人类的科技发展作出贡献。

关键词：人工智能驱动的科学研究科学计算安卓模式

维普期刊数据库博看期刊

exponential convergence of the deep neural network approximation for analytic functions Dedicated to Professor Ta Tsien Li on the Occasion of His 80th Birthday

在线全文

学校读者我要写书评

暂无评论

Science China Mathematics 2018年第10期61卷 1733-1740页

作者： weinan e Qingcan Wang Department of Mathematics and PACM Princeton University Princeton NJ 08544 USA Center for Big Data Research Peking University Beijing 100871 China Beijing Institute of Big Data Research Beijing 100871 China Program in Applied and Computational Mathematics Princeton University Princeton NJ 08544 USA

We prove that for analytic functions in low dimension, the convergence rate of the deep neural network approximation is exponential.

关键词： neural networks approximation theory analytic functions

The elastic Continuum Limit of the Tight Binding Model

在线全文

学校读者我要写书评

暂无评论

Chinese Annals of Mathematics,Series B 2007年第6期28卷 665-676页

作者： weinan e Jianfeng LU Department of Mathematics and Program in Applied and Computational Mathematics Princeton University Princeton NJ 08544 USA Program in Applied and Computational Mathematics Princeton University Princeton NJ 08544 USA

The authors consider the simplest quantum mechanics model of solids, the tight binding model, and prove that in the continuum limit, the energy of tight binding model converges to that of the continuum elasticity model obtained using Cauchy-Born rule. The technique in this paper is based mainly on spectral perturbation theory for large matrices.

关键词： Continuum limit elasticity theory Cauchy-Born rule Tight binding model

Convergence of a Stochastic Method for the Modeling of Polymeric Fluids

在线全文

学校读者我要写书评

暂无评论

Acta Mathematicae Applicatae Sinica 2002年第4期18卷 529-536页

作者： weinan e Department of Mathematics and PACM Princeton University Princeton NJ 08544 USA

We present a convergence analysis of a stochastic method for numerical modeling of complex fluids using Brownian configuration fields (BCF) for shear flows. The analysis takes into account the special structure of the stochastic partial differential equations for shear flows. We establish the optimal rate of convergence. We also analyze the nature of the error by providing its leading order asymptotics.

关键词： Brownian Configuration Fields (BCF) convergence analysis dumbbell model

Optimization-Based String Method for Finding Minimum energy Path

在线全文

学校读者我要写书评

暂无评论

Communications in Computational Physics 2013年第7期14卷 265-275页

作者： Amit Samanta weinan e Program in Applied and Computational Mathematics Princeton UniversityPrincetonNew JerseyUSA Department of Mathematics and Program in Applied and Computational Mathematics Princeton UniversityPrincetonNew JerseyUSA Beijing International Center for Mathematical Research Peking UniversityBeijingChina

We present an efficient algorithm for calculating the minimum energy path(MeP)and energy barriers between local minima on a multidimensional potential energy surface(PeS).Such paths play a central role in the understanding of transition pathways between metastable *** method relies on the original formulation of the string method[***.B,66,052301(2002)],*** evolve a smooth curve along a direction normal to the *** algorithm works by performing minimization steps on hyperplanes normal to the *** the problem of finding MeP on the PeS is remodeled as a set of constrained minimization *** provides the flexibility of using minimization algorithms faster than the steepest descent method used in the simplified string method[***.,126(16),164103(2007)].At the same time,it provides a more direct analog of the finite temperature string *** applicability of the algorithm is demonstrated using various examples.

关键词： Rare events string method minimum energy path dislocation nucleation

A comparative analysis of optimization and generalization properties of two-layer neural network and random feature models under gradient descent dynamics

维普期刊数据库评论

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Science China Mathematics 2020年第7期63卷 1235-1258页

作者： weinan e Chao Ma Lei Wu Department of Mathematics Princeton UniversityPrincetonNJ 08544USA The Program in Applied and Computational Mathematics Princeton UniversityNJ 08544USA Beijing Institute of Big Data Research Beijing 100871China

A fairly comprehensive analysis is presented for the gradient descent dynamics for training two-layer neural network models in the situation when the parameters in both layers are *** initialization schemes as well as general regimes for the network width and training data size are *** the overparametrized regime,it is shown that gradient descent dynamics can achieve zero training loss exponentially fast regardless of the quality of the *** addition,it is proved that throughout the training process the functions represented by the neural network model are uniformly close to those of a kernel *** general values of the network width and training data size,sharp estimates of the generalization error are established for target functions in the appropriate reproducing kernel Hilbert space.

关键词： two-layer neural network random feature model Gram matrix generalization error

Machine learning from a continuous viewpoint,I

在线全文

学校读者我要写书评

暂无评论

Science China Mathematics 2020年第11期63卷 2233-2266页

作者： weinan e Chao Ma Lei Wu Department of Mathematics Princeton UniversityPrincetonNJ 08544USA The Program in Applied and Computational Mathematics Princeton UniversityPrincetonNJ 08544USA Beijing Institute of Big Data Research Beijing 100871China

We present a continuous formulation of machine learning,as a problem in the calculus of variations and differential-integral equations,in the spirit of classical numerical *** demonstrate that conventional machine learning models and algorithms,such as the random feature model,the two-layer neural network model and the residual neural network model,can all be recovered(in a scaled form)as particular discretizations of different continuous *** also present examples of new models,such as the flow-based random feature model,and new algorithms,such as the smoothed particle method and spectral method,that arise naturally from this continuous *** discuss how the issues of generalization error and implicit regularization can be studied under this framework.

关键词： machine learning continuous formulation flow-based model gradient flow particle approximation

Mean field limit of a dynamical model of polymer systems

在线全文

学校读者我要写书评

暂无评论

Science China Mathematics 2013年第12期56卷 2591-2598页

作者： e weinan SHeN Hao School of Mathematical Sciences and BICMR Peking University Department of Mathematics and PACM Princeton UniversityPrinceton NJ 08544 USA Program in Applied and Computational Mathematics Princeton UniversityPrinceton NJ 08544 USA

This paper provides a mathematically rigorous foundation for self-consistent mean field theory of the polymeric physics. We study a new model for dynamics of mono-polymer systems. every polymer is regarded as a string of points which are moving randomly as Brownian motions and under elastic forces. every two points on the same string or on two different strings also interact under a pairwise potential V. The dynamics of the system is described by a system of N coupled stochastic partial differential equations （SPDes）. We show that the mean field limit as N -＋ c~ of the system is a self-consistent McKean-Vlasov type equation, under suitable assumptions on the initial and boundary conditions and regularity of V. We also prove that both the SPDe system of the polymers and the mean field limit equation are well-posed.

关键词： polymers mean field limit stochastic PDes McKean-Vlasov equation

The Deep Ritz Method: A Deep Learning-Based Numerical Algorithm for Solving Variational Problems

在线全文

学校读者我要写书评

暂无评论

Communications in Mathematics and Statistics 2018年第1期6卷 1-12页

作者： weinan e Bing Yu The Beijing Institute of Big Data Research BeijingChina Department of Mathematics and PACM Princeton UniversityPrincetonNJUSA School of Mathematical Sciences and BICMR Peking UniversityBeijingChina School of Mathematical Sciences Peking UniversityBeijingChina

We propose a deep learning-based method,the Deep Ritz Method,for numerically solving variational problems,particularly the ones that arise from par-tial differential *** Deep Ritz Method is naturally nonlinear,naturally adaptive and has the potential to work in rather high *** framework is quite simple and fits well with the stochastic gradient descent method used in deep *** illustrate the method on several problems including some eigenvalue problems.

关键词： Deep Ritz Method Variational problems PDe eigenvalue problems