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

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

Machine learning-based prediction of acute coronary syndrome using only the pre-hospital 12-lead electrocardiogram

引用

Nature Communications 2020年第1期11卷 3966-3966页

作者： Al-Zaiti, Salah Besomi, Lucas Bouzid, Zeineb Faramand, Ziad Frisch, Stephanie Martin-Gill, Christian Gregg, Richard Saba, Samir Callaway, Clifton Sejdić, Ervin Department of Acute & Tertiary Care Nursing University of Pittsburgh Pittsburgh PA United States Department of Emergency Medicine University of Pittsburgh Pittsburgh PA United States Division of Cardiology School of Medicine University of Pittsburgh Pittsburgh PA United States Department of Electrical and Computer Engineering University of Pittsburgh Pittsburgh PA United States University of Pittsburgh Medical Center (UPMC) Pittsburgh PA United States Advanced Algorithms Development Research Center Philips Healthcare Andover MA United States Department of Biomedical Informatics University of Pittsburgh Pittsburgh PA United States Department of Intelligent Systems University of Pittsburgh Pittsburgh PA United States

Prompt identification of acute coronary syndrome is a challenge in clinical practice. The 12-lead electrocardiogram (ECG) is readily available during initial patient evaluation, but current rule-based interpretation approaches lack sufficient accuracy. Here we report machine learning-based methods for the prediction of underlying acute myocardial ischemia in patients with chest pain. Using 554 temporal-spatial features of the 12-lead ECG, we train and test multiple classifiers on two independent prospective patient cohorts (n = 1244). While maintaining higher negative predictive value, our final fusion model achieves 52% gain in sensitivity compared to commercial interpretation software and 37% gain in sensitivity compared to experienced clinicians. Such an ultra-early, ECG-based clinical decision support tool, when combined with the judgment of trained emergency personnel, would help to improve clinical outcomes and reduce unnecessary costs in patients with chest pain. © 2020, The Author(s).

关键词： Acute coronary syndromes Diagnostic markers

来源：评论

学校读者我要写书评

暂无评论

Ten new insights in climate science 2024

One Earth

引用

One Earth 2025年

作者： Schaeffer, Roberto Schipper, E. Lisa F. Ospina, Daniel Mirazo, Paula Alencar, Ane Anvari, Mehrnaz Artaxo, Paulo Biresselioglu, Mehmet Efe Blome, Tanja Boeckmann, Melanie Brink, Ebba Broadgate, Wendy Bustamante, Mercedes Cai, Wenju Canadell, Josep G. Cardinale, Roberto Chidichimo, Maria Paz Ditlevsen, Peter Eicker, Ursula Feron, Sarah Fikru, Mahelet G. Fuss, Sabine Gaye, Amadou T. Gustafsson, Örjan Harring, Niklas He, Cheng Hebden, Sophie Heilemann, Adrian Hirota, Marina Janardhanan, Nandakumar Juhola, Sirkku Jung, Tae Yong Kejun, Jiang Kilkiș, Şiir Kumarasinghe, Nilushi Lapola, David Lee, June-Yi Levis, Carolina Lusambili, Adelaide Maasakkers, Joannes D. MacIntosh, Claire Mahmood, Jemilah Mankin, Justin S. Marchegiani, Pía Martin, Maria Mukherji, Aditi Muñoz-Erickson, Tischa A. Niazi, Zeenat Nyangon, Joseph Pandipati, Santosh Perera, Amarasinghage T.D. Persad, Geeta Persson, Åsa Redman, Aaron Riipinen, Ilona Rockström, Johan Roffe, Sarah Roy, Joyashree Sakschewski, Boris Samset, Bjørn H. Schlosser, Peter Sharifi, Ayyoob Shih, Wan-Yu Sioen, Giles B. Sokona, Youba Stammer, Detlef Suk, Sunhee Thiam, Djiby Thompson, Vikki Tullos, Erin van Westen, René M. Vargas Falla, Ana Maria Vecellio, Daniel J. Worden, John Wu, Henry C. Xu, Chi Yang, Yang Zachariah, Mariam Zhang, Zhen Ziervogel, Gina Federal University of Rio de Janeiro Rio de Janeiro Brazil University of Bonn Bonn Germany Future Earth Secretariat Stockholm Sweden Arizona State University Tempe AZ United States Amazon Environmental Research Institute (IPAM) Brasilia Brazil Fraunhofer Institute for Algorithms and Scientific Computing SCAI St. Augustin Germany Potsdam Institute for Climate Impact Research (PIK) Potsdam Germany University of São Paulo São Paulo Brazil İzmir University of Economics İzmir Turkey Climate Service Center Germany (GERICS) Helmholtz-Zentrum Hereon Hamburg Germany University of Bremen Bremen Germany Lund University Lund Sweden University of Brasilia Brasilia Brazil Ocean University of China Qingdao China Xiamen University Xiamen China Commonwealth Scientific and Industrial Research Organisation (CSIRO) Environment Canberra ACT Australia University College London London United Kingdom National Scientific and Technical Research Council (CONICET) Buenos Aires Argentina National University of San Martin Buenos Aires Argentina University of Copenhagen Copenhagen Denmark Concordia University Montreal QC Canada University of Groningen Groningen Netherlands Missouri University of Science and Technology Rolla MO United States Mercator Research Institute on Global Commons and Climate Change (MCC) Berlin Germany Humboldt-University of Berlin Berlin Germany Cheikh Anta Diop University Dakar Senegal Stockholm University Stockholm Sweden University of Gothenburg Gothenburg Sweden Institute of Epidemiology Helmholtz Zentrum München—German Research Center for Environmental Health (GmbH) Neuherberg Germany European Space Agency (ESA) - European Centre for Space Applications and Telecommunications (ECSAT) Oxford United Kingdom Federal University of Santa Catarina Florianopolis Brazil Institute for Global Environmental Strategies (IGES) Hayama Japan University of Helsinki Helsinki Finland Yonsei University Graduate Seoul South Korea Chinese Academy of Macroeconomic

The years 2023 and 2024 were characterized by unprecedented warming across the globe, underscoring the urgency of climate action. Robust science advice for decision makers on subjects as complex as climate change requires deep cross- and interdisciplinary understanding. However, navigating the ever-expanding and diverse peer-reviewed literature on climate change is enormously challenging for individual researchers. We elicited expert input through an online questionnaire (188 respondents from 45 countries) and prioritized 10 key advances in climate-change research with high policy relevance. The insights span a wide range of areas, from changes in methane and aerosol emissions to the factors shaping citizens’ acceptance of climate policies. This synthesis and communications effort forms the basis for a science-policy report distributed to party delegations ahead of the 29th session of the Conference of the Parties (COP29) to inform their positions and arguments on critical issues, including heat-adaptation planning, comprehensive mitigation strategies, and strengthened governance in energy-transition minerals value chains. © 2025 The Authors

关键词： adaptation climate policy climate science governance just transition mitigation resilience science policy

来源：评论

学校读者我要写书评

暂无评论

EXTENSION AND APPLICATION OF SHIP DESIGN OPTIMIZATION CODE (SHIPDOC)

引用

NAVAL ENGINEERS JOURNAL 1984年第3期96卷 177-190页

作者： RICHARDSON, WM WHITE, WN William M:. Richardsonhas been employed as a naval architect in the Surface Effect Ship Division of the David Taylor Naval Ship Research and Development Center (DTNSRDC) where he has worked since 1975 in the areas of SES structural loads estimation and optimal ship design. Upon first coming to DTNSRDC he worked in the Ship Dynamics Simulation Branch on ACV submarine and hydrofoil simulations. While at Mare Island Naval Shipyard (MINS) he was a member of the Engineering Computer Applications Branch where he was responsible for the development of algorithms and programs for the solution of naval architectural problems including ship design flooding effects and submarine overhaul scheduling. Before coming to MINS he was employed as a naval architect in the Hull Scientific Branch of the Boston Naval Shipyard's Design Division. He obtained an B.S. degree in Naval Architecture and Marine Engineering from M.I.T. and is a member of SNAME. William N:. Whiteis a senior naval architect in the Advance Vehicles Branch of the Naval Sea Systems Command where he is responsible for the design of all surface effect ships and air cushion vehicles. Previous to his current assignment he was with PMS-304 the Navy's Surface Effect Ship Project Office. There he was the manager for machinery and system integration for the 3000 ton SES acquisition program. His earliest advanced ship experience was acquired while employed by the David Taylor Naval Ship Research and Development Center starting in 1970. Here he worked on the Navy's hydrofoil and air cushion vehicle programs. Mr. White started his career as a student trainee at the Boston Naval Shipyard in 1961 and transferred to Mare Island Naval Shipyard in 1964 where he worked on the Navy's Polaris program. He graduated from the University of Michigan with a Master's Degree in Naval Architecture and is a member of the SNAME and ASNE.

An existing nonlinear ship design optimization program designated SHIPDOC has been extended and a new surface effect ship (SES) description input file is being developed under the sponsorship of the Naval Sea Systems Command's surface ship concept formulation (CONFORM) program. SHIPDOC is currently being used in support of several feasibility and preliminary level SES designs. The program has several novel features including an open-ended, user-created ship description and the potential to model all types of ships both enhanced and conventional, surfaced and submerged. This capability has been combined with a nonlinear optimization algorithm that solves for the minimum weight ship subject to user controlled constraints. This paper presents a brief overall description of SHIPDOC and its current capabilities followed by a synopsis of ship types, both surface and submerged, which have been designed with the program in order to illustrate SHIPDOC's practical design capability.

关键词：

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：