检索结果-内蒙古大学图书馆

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

学校读者我要写书评

暂无评论

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

Regional coverage monitoring planning technology for multi-UAV based on pruning PSO 2nd

学校读者我要写书评

暂无评论

Regional coverage monitoring planning technology for multi-U...

2nd International Conference on Smart Vehicular technology, Transportation, Communication and Applications, VTCA 2018

作者： Wang, KaiXuan Shen, YuTing Zhang, FuQuan Liang, Zhuo Song, ZhiGuo Pan, YanPeng China Academy of Launch Vehicle Technology Beijing100076 China The 54th Research Institute of China Electronics Technology Group Corporation Shijiazhuang050000 China Fujian Provincial Key Laboratory of Information Processing and Intelligent Control Minjiang University Fuzhou350121 China Digital Performance and Simulation Technology Lab School of Computer Science and Technology Beijing Institute of Technology Beijing100081 China

ISBN: (纸本)9783030045845

In recent years, with the application and gradual popularization of UAV technology in many fields, the normalization of UAV aerial photography has become a common phenomenon. There are few studies on Multi-UAV regional coverage monitoring. In this study, PSO algorithm based on pruning can be used to solve optimization problem, the multi-agent technology solve the problem of UAV group for self-perception and decision-making, the UAV group, namely multi-agent particles, can automatically initialize the perception agent particle whether meet the requirements of the iteration, whether to need to be pruned, and decide to optimize the iteration or increase the agent number, Finally, simulation verification shows that the optimized algorithm can finish the work faster under the premise of guaranteeing the effect. © Springer Nature Switzerland AG 2019.

关键词： Unmanned aerial vehicles (UAV)

Automated cross-sectional view selection in CT angiography of aortic dissections with uncertainty awareness and retrospective clinical annotations

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Pepe, Antonio Egger, Jan Codari, Marina Willemink, Martin J. Gsaxner, Christina Li, Jianning Roth, Peter M. Mistelbauer, Gabriel Schmalstieg, Dieter Fleischmann, Dominik Graz University of Technology Institute of Computer Graphics and Vision Inffeldgasse 16/II Graz8010 Austria Stanford University School of Medicine 3D and Quantitative Imaging Lab 300 Pasteur Drive StanfordCA94305 United States Laboratory Graz Austria Girardetstraße 2 Essen45131 Germany Otto-von-Guericke University Department of Simulation and Graphics. Universitätsplatz 2 Magdeburg39106 Germany

Objective: Surveillance imaging of chronic aortic diseases, such as dissections, relies on obtaining and comparing cross-sectional diameter measurements at predefined aortic landmarks, over time. Due to a lack of robust tools, the orientation of the cross-sectional planes is defined manually by highly trained operators. We show how manual annotations routinely collected in a clinic can be efficiently used to ease this task, despite the presence of a non-negligible interoperator variability in the measurements. Impact: Ill-posed but repetitive imaging tasks can be eased or automated by leveraging imperfect, retrospective clinical annotations. Methodology: In this work, we combine convolutional neural networks and uncertainty quantification methods to predict the orientation of such cross-sectional planes. We use clinical data randomly processed by 11 operators for training, and test on a smaller set processed by 3 independent operators to assess interoperator variability. Results: Our analysis shows that manual selection of cross-sectional planes is characterized by 95% limits of agreement (LOA) of 10.6◦ and 21.4◦ per angle. Our method showed to decrease static error by 3.57◦ (40.2%) and 4.11◦ (32.8%) against state of the art and LOA by 5.4◦ (49.0%) and 16.0◦ (74.6%) against manual processing. Conclusion: This suggests that pre-existing annotations can be an inexpensive resource in clinics to ease ill-posed and repetitive tasks like cross-section extraction for surveillance of aortic dissections. Copyright © 2021, The Authors. All rights reserved.

关键词： Blood vessels

Cuckoo search algorithm based on stochastic gradient descent 5th

学校读者我要写书评

暂无评论

Cuckoo search algorithm based on stochastic gradient descent

5th Euro-China Conference on Intelligent Data Analysis and Applications, ECC 2018

作者： Tian, Yuan Liang, Yong-quan Peng, Yan-jun Princeton University PrincetonNJ08544 United States College of Computer Science and Engineering Shandong University of Science and Technology Qingdao China Provincial Key Laboratory for Information Technology of Wisdom Mining of Shandong Province Shandong University of Science and Technology Qingdao China Experimental Teaching Center of National Virtual Simulation for Security Mining Shandong University of Science and Technology Qingdao China

ISBN: (纸本)9783030037659

Cuckoo Search (CS) is a global search algorithm for solving multi-objective optimization problems. Cuckoo Search algorithm is easy to implement and has a few number of control parameters, excellent search path and strong optimization capability. It has been successfully applied to practical problems, such as engineering optimization. To improve the refining ability and convergence rate of CS algorithm, solve the problem of slow convergence rate and unstable search accuracy in later stage, this paper proposes a Cuckoo Search Algorithm based on Stochastic Gradient Descent (SGDCS). This algorithm uses Stochastic Gradient Descent to enhance the search of the local optimum, convergence process and algorithm adaptability, which improves the calculation accuracy and convergence rate of cuckoo search algorithm. The simulation experiments show that the proposed algorithm is simple and efficient, efficiently improves the performances on calculation accuracy and convergence rate on the basis of maintaining the advantages of the standard CS algorithm. © Springer Nature Switzerland AG 2019.

关键词： Multiobjective optimization

An Enterprise Competitiveness Assessment Method Based on Ensemble Learning 16th

学校读者我要写书评

暂无评论

An Enterprise Competitiveness Assessment Method Based on Ens...

16th Web Information Systems and Applications Conference, WISA 2019

作者： Chang, Yaomin Li, Yuzheng Chen, Chuan Cao, Bin Li, Zhenxing School of Data and Computer Science Sun Yat-sen University Guangzhou China Guangdong Key Laboratory for Big Data Analysis and Simulation of Public Opinion Sun Yat-sen University Guangzhou China Information Technology Co. Ltd. Beijing China

ISBN: (纸本)9783030309510

It is of great significance to assess the competitiveness of enterprises based on big data. The current methods cannot help corporate strategists to judge the status quo and prospects of enterprises’ development at a relatively low cost. In order to make full use of big data to evaluate enterprise competitiveness, this paper proposes an enterprise competitiveness assessment method based on ensemble learning. The experimental results show that our method has a significant improvement in the task of the enterprise competitiveness assessment. © 2019, Springer Nature Switzerland AG.

关键词： Data mining

Hadoop perfect file: A fast access container for small files with direct in disc metadata access

学校读者我要写书评

暂无评论

arXiv 2019年

作者： Tchaye-Kondi, Jude Zhai, Yanlong Lin, Kwei-Jay Zhu, Liehuang Tao, Wenjun Yang, Kai School of Computer Science Beijing Institute of Technology Beijing100081 China Department of Electrical Engineering and Computer Science University of California IrvineCA92697 United States Science and Technology on Special System Simulation Laboratory Beijing Simulation Center Beijing China

Storing and processing massive small files is one of the major challenges for the Hadoop Distributed File System (HDFS). In order to provide fast data access, the NameNode (NN) in HDFS maintains the metadata of all files in its main-memory. Hadoop performs well with a small number of large files that require relatively little metadata in the NN’s memory. But for a large number of small files, Hadoop has problems such as NN memory overload caused by the huge metadata size of these small files. We present a new type of archive file, Hadoop Perfect File (HPF), to solve HDFS’s small files problem by merging small files into a large file on HDFS. Existing archive files offer limited functionality and have poor performance when accessing a file in the merged file due to the fact that during metadata lookup it is necessary to read and process the entire index file(s). In contrast, HPF file can directly access the metadata of a particular file from its index file without having to process it entirely. The HPF index system uses two hash functions: file’s metadata are distributed through index files by using a dynamic hash function and, for each index file, we build an order preserving perfect hash function that preserves the position of each file’s metadata in the index file. The HPF design will only read the part of the index file that contains the metadata of the searched file during its access. HPF file also supports the file appending functionality after its creation. Our experiments show that HPF can be more than 40% faster file’s access from the original HDFS. If we don’t consider the caching effect, HPF’s file access is around 179% faster than MapFile and 11294% faster than HAR file. If we consider caching effect, HPF is around 35% faster than MapFile and 105% faster than HAR file. Copyright © 2019, The Authors. All rights reserved.

关键词： File organization

A Comparison Study of Tracking Differentiator and Robust Exact Differentiator

学校读者我要写书评

暂无评论

A Comparison Study of Tracking Differentiator and Robust Exa...

Chinese Automation Congress (CAC)

作者： Juan Wang Hehong Zhang Gaoxi Xiao Zhihong Dan Song Zhang Yunde Xie College of Mathematics and Computer Science Fuzhou University Fuzhou China School of Electrical and Electronic Engineering Nanyang Technological University Singapore Singapore Singapore Science and Technology on Altitude Simulation Laboratory AECC Sichuan Gas Turbine Establishment of China Mianyang China Beijing Rail Transit Technology Equipment Group Co. Ltd Beijing China

ISBN: (数字)9781728176871

ISBN: (纸本)9781728176888

This paper presents a comparison study of two commonly-used differentiators, namely tracking differentiator (TD) and robust exact differentiator (RED) in both the frequency and the time domains. Specifically, we compare their performances in filtering and differentiation estimation for a large number of inputs with different levels of noises. Meanwhile, the parameter adaptability regarding different inputs for the two differentiators is tested. Furthermore, the efficiency of the two algorithms are evaluated respectively by the hardware. The results show that TD outperforms RED in quickness, smoothness, and noise-tolerance with no overshoots, while RED has advantageous exactness and robustness in the filtering and algorithm's simplicity. Also, TD has a better parameter adaptability and tolerance to signal frequency's variations whereas the performance of RED is heavily dependent on parameter setting. To overcome the overshoot problem in RED, an enhancement by adoption of the transition function is proposed. These results shall provide useful tips for selecting appropriate differentiators in real-life engineering, and designing new differentiators as well.

关键词： Estimation Signal to noise ratio Time-frequency analysis Time-domain analysis Signal processing algorithms Frequency estimation Turbines

Coordinated Multi-Valve Disturbance-Rejection Pressure Control for High-Altitude Test Stands via Exterior Penalty Functions

学校读者我要写书评

暂无评论

arXiv 2025年

作者： Louyue, Zhang Xin, Li Chao, Zhai Duoqi, Shi Hehong, Zhang Zhihong, Dan Xi, Wang Jiashuai, Liu Gaoxi, Xiao School of Energy and Power Engineering Beihang University Beijing100191 China School of Automation China University of Geosciences Wuhan430074 China College of Computer and Data Science Fuzhou University Fuzhou350108 China Science and Technology on Altitude Simulation Laboratory Sichuan Gas Turbine Establishment Aero Engine Corporation of China Sichuan Mianyang621000 China Institute for Aero Engine Tsinghua University Beijing100084 China School of Electrical and Electronic Engineering Nanyang Technological University 639798 Singapore

High-altitude simulation test benches for aero engines employ multi-chamber, multi-valve intake systems that demand effective decoupling and strong disturbance rejection during transient tests. This paper proposes a coordinated active disturbance rejection control (ADRC) scheme based on external penalty functions. The chamber-pressure safety limit is formulated as an inequality-constrained optimization problem, and an exponential penalty together with a gradient-based algorithm is designed for dynamic constraint relaxation, with guaranteed global convergence. A coordination term is then integrated into a distributed ADRC framework to yield a multi-valve coordinated ADRC controller, whose asymptotic stability is established via Lyapunov theory. Hardware-in-the-loop simulations using MATLAB/Simulink and a PLC demonstrate that, under ±3 kPa pressure constraints, chamber V2’s maximum error is 1.782 kPa (77.1% lower than PID control), and under a 180 kg/s2 flow-rate disturbance, valve oscillations decrease from ±27% to ±5%. These results confirm the superior disturbance-rejection and decoupling performance of the proposed method. Copyright © 2025, The Authors. All rights reserved.

关键词： Disturbance rejection

Quantum simulation for High-Energy Physics

学校读者我要写书评

暂无评论

PRX Quantum 2023年第2期4卷 027001-027001页

作者： Christian W. Bauer Zohreh Davoudi A. Baha Balantekin Tanmoy Bhattacharya Marcela Carena Wibe A. de Jong Patrick Draper Aida El-Khadra Nate Gemelke Masanori Hanada Dmitri Kharzeev Henry Lamm Ying-Ying Li Junyu Liu Mikhail Lukin Yannick Meurice Christopher Monroe Benjamin Nachman Guido Pagano John Preskill Enrico Rinaldi Alessandro Roggero David I. Santiago Martin J. Savage Irfan Siddiqi George Siopsis David Van Zanten Nathan Wiebe Yukari Yamauchi Kübra Yeter-Aydeniz Silvia Zorzetti Physics Division Lawrence Berkeley National Laboratory Berkeley California 94720 USA Department of Physics Maryland Center for Fundamental Physics and the NSF Institute for Robust Quantum Simulation University of Maryland College Park Maryland 20742 USA Department of Physics University of Wisconsin Madison Wisconsin 53706 USA T-2 Los Alamos National Laboratory Los Alamos New Mexico 87545 USA Fermi National Accelerator Laboratory Batavia Illinois 60510 USA Enrico Fermi Institute University of Chicago Chicago Illinois 60637 USA Kavli Institute for Cosmological Physics University of Chicago Chicago Illinois 60637 USA Department of Physics University of Chicago Chicago Illinois 60637 USA Department of Physics and Illinois Center for the Advanced Study of the Universe and Illinois Quantum Information Science and Technology Center University of Illinois Urbana Illinois 61801 USA QuEra Computing Inc Boston Massachusetts 02135 USA Department of Mathematics University of Surrey Guildford Surrey GU2 7XH United Kingdom Center for Nuclear Theory Department of Physics and Astronomy Stony Brook University New York 11794-3800 USA Department of Physics Brookhaven National Laboratory Upton New York 11973 USA Peng Huanwu Center for Fundamental Theory Hefei Anhui 230026 China Interdisciplinary Center for Theoretical Study University of Science and Technology of China Hefei Anhui 230026 China Pritzker School of Molecular Engineering Chicago Quantum Exchange and Kadanoff Center for Theoretical Physics University of Chicago Illinois 60637 USA qBraid Co. Harper Court 5235 Chicago Illinois 60615 USA Department of Physics Harvard University Cambridge Massachusetts 02138 USA Department of Physics and Astronomy University of Iowa Iowa City Iowa 52242 USA Duke Quantum Center Duke University Durham North Carolina 27701 USA Department of Electrical and Computer Engineering Duke University Durham North Carolina 27708 USA Department of Physics Duke University

It is for the first time that quantum simulation for high-energy physics (HEP) is studied in the U.S. decadal particle-physics community planning, and in fact until recently, this was not considered a mainstream topic in the community. This fact speaks of a remarkable rate of growth of this subfield over the past few years, stimulated by the impressive advancements in quantum information sciences (QIS) and associated technologies over the past decade, and the significant investment in this area by the government and private sectors in the U.S. and other countries. High-energy physicists have quickly identified problems of importance to our understanding of nature at the most fundamental level, from tiniest distances to cosmological extents, that are intractable with classical computers but may benefit from quantum advantage. They have initiated, and continue to carry out, a vigorous program in theory, algorithm, and hardware co-design for simulations of relevance to the HEP mission. This Roadmap is an attempt to bring this exciting and yet challenging area of research to the spotlight, and to elaborate on what the promises, requirements, challenges, and potential solutions are over the next decade and beyond.

关键词： Quantum simulation