检索结果-内蒙古大学图书馆

DPA-2:a large atomic model as a multitask learner

npj Computational Materials 2024年第1期10卷 185-199页

作者： Duo Zhang Xinzijian Liu Xiangyu Zhang Chengqian Zhang Chun Cai Hangrui Bi Yiming Du Xuejian Qin Anyang Peng Jiameng Huang Bowen Li Yifan Shan Jinzhe Zeng Yuzhi Zhang Siyuan Liu Yifan Li Junhan Chang Xinyan Wang Shuo Zhou Jianchuan Liu Xiaoshan Luo Zhenyu Wang Wanrun Jiang Jing Wu Yudi Yang Jiyuan Yang Manyi Yang Fu-Qiang Gong Linshuang Zhang Mengchao Shi Fu-Zhi Dai Darrin M.York Shi Liu Tong Zhu Zhicheng Zhong Jian Lv Jun Cheng Weile Jia Mohan Chen Guolin Ke Weinan E Linfeng Zhang Han Wang AI for Science Institute BeijingP.R.China DP Technology BeijingP.R.China Academy for Advanced Interdisciplinary Studies Peking UniversityBeijingP.R.China State Key Lab of Processors Institute of Computing TechnologyChinese Academy of SciencesBeijingP.R.China University of Chinese Academy of Sciences BeijingP.R.China HEDPS CAPTCollege of EngineeringPeking UniversityBeijingP.R.China Ningbo Institute of Materials Technology and Engineering Chinese Academy of SciencesNingboP.R.China CAS Key Laboratory of Magnetic Materials and Devices and Zhejiang Province Key Laboratory of Magnetic Materials and Application Technology Chinese Academy of SciencesNingboP.R.China School of Electronics Engineering and Computer Science Peking UniversityBeijingP.R.China Shanghai Engineering Research Center of Molecular Therapeutics&New Drug Development School of Chemistry and Molecular EngineeringEast China Normal UniversityShanghaiP.R.China Laboratory for Biomolecular Simulation Research Institute for Quantitative Biomedicine and Department of Chemistry and Chemical BiologyRutgers UniversityPiscatawayNJUSA Department of Chemistry Princeton UniversityPrincetonNJUSA College of Chemistry and Molecular Engineering Peking UniversityBeijingP.R.China Yuanpei College Peking UniversityBeijingP.R.China School of Electrical Engineering and Electronic Information Xihua UniversityChengduP.R.China State Key Laboratory of Superhard Materials College of PhysicsJilin UniversityChangchunP.R.China Key Laboratory of Material Simulation Methods&Software of Ministry of Education College of PhysicsJilin UniversityChangchunP.R.China International Center of Future Science Jilin UniversityChangchunP.R.China Key Laboratory for Quantum Materialsof Zhejiang Province Department of PhysicsSchool of ScienceWestlake UniversityHangzhouP.R.China Atomistic Simulations Italian Institute of TechnologyGenovaItaly State Key Laboratory of Physical Chemistry of Solid Surface iChEMCollege of Chemistry and Chemical EngineeringXiame

The rapid advancements in artificial intelligence(AI)are catalyzing transformative changes in atomic modeling,simulation,and ***-driven potential energy models havedemonstrated the capability to conduct large-scale,long-duration simulations with the accuracy of ab initio electronic structure ***,the model generation process remains a bottleneck for large-scale *** propose a shift towards a model-centric ecosystem,wherein a large atomic model(LAM),pretrained across multiple disciplines,can be efficiently fine-tuned and distilled for various downstream tasks,thereby establishing a new framework for molecular *** this study,we introduce the DPA-2 architecture as a prototype for ***-trained on a diverse array of chemical and materials systemsusing a multi-task approach,DPA-2demonstrates superior generalization capabilities across multiple downstream tasks compared to the traditional single-task pre-training and fine-tuning *** approach sets the stage for the development and broad application of LAMs in molecular and materials simulation research.

关键词： DPA establishing thereby

来源：评论

学校读者我要写书评

暂无评论

Intrinsic mechanical behavior of MgAgSb thermoelectric material:An ab initio study

引用

Journal of Materiomics 2020年第1期6卷 24-32页

作者： Guodong Li Qi An Umut Aydemir Sergey I.Morozov Bo Duan Pengcheng Zhai Qingjie Zhang William A.Goddard Ⅲ Hubei Key Laboratory of Theory and Application of Advanced Materials Mechanics School of ScienceWuhan University of TechnologyWuhan430070China State Key Laboratory of Advanced Technology for Materials Synthesis and Processing Wuhan University of TechnologyWuhan430070China Department of Chemical and Materials Engineering University of Nevada RenoRenoNV89557USA Department of Chemistry Koc UniversitySariyerIstanbul34450Turkey Boron and Advanced Materials Research Center Koc UniversitySariyerIstanbul34450Turkey Department of Computer Simulation and Nanotechnology South Ural State UniversityChelyabinsk454080Russia Materials and Process Simulation Center California Institute of TechnologyPasadenaCA91125USA

α-MgAgSb based thermoelectric(TE)device attracts much attention for its commercial application because it shows an extremely high conversion efficiency of ~8.5% under a temperature difference of 225 ***,the mechanical behavior of α-MgAgSb is another serious consideration for its engineering ***,we apply density functional theory(DFT)simulations to examine the intrinsic mechanical properties of all three MgAgSb phases,including elastic properties,shear-stress-shear-strain relationships,deformation and failure mechanism under ideal shear and biaxial shear *** find that the ideal shear strength of α-MgAgSb is 3.25 GPa along the most plausible(100)<010>slip *** strength is higher than that of β-MgAgSb(0.80 GPa)and lower than that of γ-MgAgSb(3.43 GPa).The failure of α-MgAgSb arises from the stretching and breakage of MgeSb bond α-MgAgSb under pure shear load,while it arises from the softening of MgeAg bond and the breakage of AgeSb bond under biaxial shear *** suggests that the deformation mechanism changes significantly under different loading conditions.

关键词： MgAgSb thermoelectric materials Density functional theory Ideal strength Deformation mechanism

来源：评论

学校读者我要写书评

暂无评论

DPA-2: a large atomic model as a multi-task learner

arXiv

引用

arXiv 2023年

作者： Zhang, Duo Liu, Xinzijian Zhang, Xiangyu Zhang, Chengqian Cai, Chun Bi, Hangrui Du, Yiming Qin, Xuejian Peng, Anyang Huang, Jiameng Li, Bowen Shan, Yifan Zeng, Jinzhe Zhang, Yuzhi Liu, Siyuan Li, Yifan Chang, Junhan Wang, Xinyan Zhou, Shuo Liu, Jianchuan Luo, Xiaoshan Wang, Zhenyu Jiang, Wanrun Wu, Jing Yang, Yudi Yang, Jiyuan Yang, Manyi Gong, Fu-Qiang Zhang, Linshuang Shi, Mengchao Dai, Fu-Zhi York, Darrin M. Liu, Shi Zhu, Tong Zhong, Zhicheng Lv, Jian Cheng, Jun Jia, Weile Chen, Mohan Ke, Guolin Weinan, E. Zhang, Linfeng Wang, Han AI for Science Institute Beijing100080 China DP Technology Beijing100080 China Academy for Advanced Interdisciplinary Studies Peking University Beijing100871 China State Key Lab of Processors Institute of Computing Technology Chinese Academy of Sciences Beijing100871 China University of Chinese Academy of Sciences Beijing100871 China HEDPS CAPT College of Engineering Peking University Beijing100871 China Ningbo Institute of Materials Technology and Engineering Chinese Academy of Sciences Ningbo315201 China CAS Key Laboratory of Magnetic Materials and Devices Zhejiang Province Key Laboratory of Magnetic Materials and Application Technology Chinese Academy of Sciences Ningbo315201 China School of Electronics Engineering and Computer Science Peking University Beijing100871 China Shanghai Engineering Research Center of Molecular Therapeutics & New Drug Development School of Chemistry and Molecular Engineering East China Normal University Shanghai200062 China Laboratory for Biomolecular Simulation Research Institute for Quantitative Biomedicine Department of Chemistry and Chemical Biology Rutgers University PiscatawayNJ08854 United States Department of Chemistry Princeton University PrincetonNJ08540 United States College of Chemistry and Molecular Engineering Peking University Beijing100871 China Yuanpei College Peking University Beijing100871 China School of Electrical Engineering and Electronic Information Xihua University Chengdu610039 China State Key Laboratory of Superhard Materials College of Physics Jilin University Changchun130012 China Key Laboratory of Material Simulation Methods & Software of Ministry of Education College of Physics Jilin University Changchun130012 China International Center of Future Science Jilin University Changchun130012 China Key Laboratory for Quantum Materials of Zhejiang Province Department of Physics School of Science Westlake University Zhejiang Hangzhou310030 China Atomistic Simulations Italia

The rapid advancements in artificial intelligence (AI) are catalyzing transformative changes in atomic modeling, simulation, and design. AI-driven potential energy models have demonstrated the capability to conduct large-scale, long-duration simulations with the accuracy of ab initio electronic structure methods. However, the model generation process remains a bottleneck for large-scale applications. We propose a shift towards a model-centric ecosystem, wherein a large atomic model (LAM), pre-trained across multiple disciplines, can be efficiently fine-tuned and distilled for various downstream tasks, thereby establishing a new framework for molecular modeling. In this study, we introduce the DPA-2 architecture as a prototype for LAMs. Pre-trained on a diverse array of chemical and materials systems using a multi-task approach, DPA-2 demonstrates superior generalization capabilities across multiple downstream tasks compared to the traditional single-task pre-training and fine-tuning methodologies. Our approach sets the stage for the development and broad application of LAMs in molecular and materials simulation research. Copyright © 2023, The Authors. All rights reserved.

关键词： Multi-task learning

来源：评论

学校读者我要写书评

暂无评论

AlphaStock: A buying-winners-and-selling-losers investment strategy using interpretable deep reinforcement attention networks

arXiv

引用

arXiv 2019年

作者： Wang, Jingyuan Zhang, Yang Tang, Ke Wu, Junjie Xiong, Zhang MOE Engineering Research Center of Advanced Computer Application Technology School of Computer Science Engineering Beihang University Beijing China Institute of Economics School of Social Sciences Tsinghua University Beijing China Beijing Key Laboratory of Emergency Support Simulation Technologies for City Operations School of Economics and Management Beihang University Beijing China Beijing Advanced Innovation Center for BDBC Beihang University Beijing China

Recent years have witnessed the successful marriage of finance innovations and AI techniques in various finance applications including quantitative trading (QT). Despite great research efforts devoted to leveraging deep learning (DL) methods for building better QT strategies, existing studies still face serious challenges especially from the side of finance, such as the balance of risk and return, the resistance to extreme loss, and the interpretability of strategies, which limit the application of DL-based strategies in real-life financial markets. In this work, we propose AlphaStock, a novel reinforcement learning (RL) based investment strategy enhanced by interpretable deep attention networks, to address the above challenges. Our main contributions are summarized as follows: i) We integrate deep attention networks with a Sharpe ratio-oriented reinforcement learning framework to achieve a risk-return balanced investment strategy;ii) We suggest modeling interrelationships among assets to avoid selection bias and develop a cross-asset attention mechanism;iii) To our best knowledge, this work is among the first to offer an interpretable investment strategy using deep reinforcement learning models. The experiments on long-periodic U.S. and Chinese markets demonstrate the effectiveness and robustness of AlphaStock over diverse market states. It turns out that AlphaStock tends to select the stocks as winners with high long-term growth, low volatility, high intrinsic value, and being undervalued recently. Copyright © 2019, The Authors. All rights reserved.

关键词： Strategic planning

来源：评论

学校读者我要写书评

暂无评论

A CLASS OF TWO-STEP CONTINUITY RUNGE-KUTTA METHODS FOR SOLVING SINGULAR DELAY DIFFERENTIAL EQUATIONS AND ITS STABILITY ANALYSIS

引用

Journal of Computational Mathematics 2005年第6期23卷 647-656页

作者： Xin Leng De-gui Liu Xiao-qiu Song Li-rong Chen Beijing Institute of Computer Application and Simulation Technology 100854 China Beijing Institute of Applied Physics and Computational Mathematics 100088 China

In this paper, a class of two-step continuity Runge-Kutta（TSCRK） methods for solving singular delay differential equations（DDEs） is presented. Analysis of numerical stability of this methods is given. We consider the two distinct cases：（i）τ≥ h, （ii）τ 〈 h, where the delay τ and step size h of the two-step continuity Runge-Kutta methods are both constant. The absolute stability regions of some methods are plotted and numerical examples show the efficiency of the method.

关键词： Analysis of numerical stability Singular delay differential equations Two-step continuity Runge-Kutta methods

来源：评论

学校读者我要写书评

暂无评论

Hybrid Petri nets of scheduling and supervisory control integrated system in process industry

Hybrid Petri nets of scheduling and supervisory control inte...

引用

International Conference on Machine Learning and Cybernetics (ICMLC)

作者： Ya-Li Wu Ding Liu Jian-Chao Zeng School of Automation and Information Engineering Xi''an University of Technology Xi'an Shaanxi China Division of System Simulation and Computer Application Taiyuan Heavy Machinery Institute Taiyuan Shanxi China

ISBN: (纸本)0780384032

Production scheduling and supervisory control are the key to real computer integrated manufacturing system in process industry. A new kind of hybrid Petri nets model named hierarchical extended hybrid Petri nets model is proposed to model scheduling and supervisory control integrated system in process industry. Firstly, the definition of hierarchical extended hybrid Petri nets is given. Then the enabled condition and evolution rule are described in detail. At last an example is given to show the modeling process of hybrid Petri nets.

关键词： Petri nets Job shop scheduling Supervisory control Electrical equipment industry Industrial control Processor scheduling Manufacturing industries Production systems computer integrated manufacturing computer industry

来源：评论

学校读者我要写书评

暂无评论

Class of modified parallel combined methods of real-time numerical simulation for a stiff system

引用

Chinese Journal of Systems Engineering and Electronics 2004年第3期000卷

A class of modified parallel combined methods of real-time numerical simulation are presented for a stiff dynamic system. By combining the parallelism across the system with the parallelism across the method, and relaxing the dependence of stage value computation on sampling time of input function, a class of modified real-time parallel combined methods are constructed. Stiff and nonstiff subsystems are solved in parallel on a parallel computer by a parallel Rosenbrock method and a parallel RK method, respectively. Their order conditions and convergences are discussed. The numerical simulation experiments show that this class of modified algorithms can get high speed and efficiency.

关键词： stiff system real-time numerical simulation parallel combined method

来源：评论

学校读者我要写书评

暂无评论

MODIFIED PARALLEL ROSENBROCK METHODS FOR STIFF DIFFERENTIAL EQUATIONS

引用

Journal of Computational Mathematics 2002年第1期20卷 23-34页

作者： Xue-nian Cao Shou-fu Li De-gui Liu Institute for Computational and Applied Mathematics Xiangtan UniversityXiangtan 411105China Beijing Institute of Computer Application and Simulation Technology Beijing 100854China

Presents a class of modified parallel Rosenbrock methods (MPROW) which possesses more free parameters to improve further the various properties of the methods and will be similarly written as MPROW. Information on par... 详细信息

关键词： numerical analysis stiff ordinary differential equations Rosenbrock methods parallel algorithms

来源：评论

学校读者我要写书评

暂无评论

Modeling and simulation of hybrid dynamical systems with generalized differential Petri nets

Modeling and simulation of hybrid dynamical systems with gen...

引用

IEEE International Symposium on Intelligent Control (ISIC)

作者： Yali Wu Weimin Wu Jianchao Zeng Guoji Sun Hongye Su Jian Chu System Engineering Institute Xi''an Jiaotong University Xi'an China Institute of Advanced Process Control National Laboratory of Industrial Control Technology Zhejiang University Hangzhou China Division of System Simulation and Computer Application Taipan Heavy Machinery Institute Taipan China

There has been considerable interest in the modeling and simulation of hybrid dynamic systems (HDS). As an effective modeling tool of discrete event dynamic systems, Petri nets have a dual nature of a graphical tool and a mathematical object. In this paper, an extension of Petri net named generalized differential Petri nets (GDPN) is proposed to model HDS that have a combination of discrete-event evolution and continuous state evolution. Differential place and differential transition defined by Demongodin et al. (1998) are used to model the numeral simulation of the continuous dynamic process, and the weights defined on the directed arcs that connects the differential transitions and places are extended from real numbers to real matrices. The marking of differential place are also enlarged from real numbers to real vectors. Then the evolution rules and modeling method of HDS with GDPN are introduced. Two examples are used to illustrate the modeling power of GDPN in HDS.

关键词： Petri nets Power system modeling Supervisory control Discrete event systems Process control Computational modeling computer simulation Mathematical model Chemical processes Continuous time systems

来源：评论

学校读者我要写书评

暂无评论

Parallel Rosenbrock Methods for DifferentialAlgebraic Equations

引用

Journal of Systems Engineering and Electronics 2001年第2期12卷 73-81页

作者： Fei Jinggao Beijing institute of computer application and simulation technology 100854, P. R. China Beijing Institute of Computer Application and Simulation Technology 100854 P. R. China

A class of parallel Rosenbrock methods for differential algebraic equations are presented in this paper. The local truncation errors are defined and the order conditions are established by using the DA-trees and DA-series. The paper also deals with the convergence of the parallel Rosenbrock methods for h -> 0 and states the bounds for the global errors of the methods. Some particular methods are obtained by solving the order equations and a numerical example is given, from which the theoretical orders are actually observed.

关键词： D Differential- algebraic system Par algorithm Rosenbrock algorithm Rosenbrock method Convergence.

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：