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

Insights into the structural properties of SARS-CoV-2 main protease

引用

Current Research in Structural Biology 2022年 4卷 349-355页

作者： Akbayrak, Ibrahim Yagiz Caglayan, Sule Irem Kurgan, Lukasz Uversky, Vladimir N. Coskuner-Weber, Orkid Materials Sciences and Technologies Turkish-German University Sahinkaya Caddesi No. 106 Beykoz Istanbul 34820 Turkey Molecular Biotechnology Turkish-German University Sahinkaya Caddesi No. 106 Beykoz Istanbul 34820 Turkey Department of Computer Science Virginia Commonwealth University Richmond 23284 VA United States Molecular Medicine USF Health Byrd Alzheimer's Research Institute Morsani College of Medicine University of South Florida Tampa FL United States Laboratory of New Methods in Biology Institute for Biological Instrumentation of the Russian Academy of Sciences Federal Research Center “Pushchino Scientific Center for Biological Research of the Russian Academy of Sciences” Pushchino Russian Federation

SARS-CoV-2 is the infectious agent responsible for the coronavirus disease since 2019, which is the viral pneumonia pandemic worldwide. The structural knowledge on SARS-CoV-2 is rather limited. These limitations are also applicable to one of the most attractive drug targets of SARS-CoV-2 proteins – namely, main protease M^pro, also known as 3C-like protease (3CL^pro). This protein is crucial for the processing of the viral polyproteins and plays crucial roles in interfering viral replication and transcription. In fact, although the crystal structure of this protein with an inhibitor was solved, M^pro conformational dynamics in aqueous solution is usually studied by molecular dynamics simulations without special sampling techniques. We conducted replica exchange molecular dynamics simulations on M^pro in water and report the dynamic structures of M^pro in an aqueous environment including root mean square fluctuations, secondary structure properties, radius of gyration, and end-to-end distances, chemical shift values, intrinsic disorder characteristics of M^pro and its active sites with a set of computational tools. The active sites we found coincide with the currently known sites and include a new interface for interaction with a protein partner. © 2022 The Authors

关键词： Dynamics Replica exchange MD simulations SARS-CoV-2 main protease

来源：评论

学校读者我要写书评

暂无评论

When to Update Your Model: Constrained Model-based Reinforcement Learning

arXiv

引用

arXiv 2022年

作者： Ji, Tianying Luo, Yu Sun, Fuchun Jing, Mingxuan He, Fengxiang Huang, Wenbing Department of Computer Science and Technology Tsinghua University China Science & Technology on Integrated Information System Laboratory Institute of Software Chinese Academy of Sciences China JD Explore Academy *** Inc China Gaoling School of Artificial Intelligence Renmin University of China China Beijing Key Laboratory of Big Data Management and Analysis Methods Beijing China

Designing and analyzing model-based RL (MBRL) algorithms with guaranteed monotonic improvement has been challenging, mainly due to the interdependence between policy optimization and model learning. Existing discrepancy bounds generally ignore the impacts of model shifts, and their corresponding algorithms are prone to degrade performance by drastic model updating. In this work, we first propose a novel and general theoretical scheme for a non-decreasing performance guarantee of MBRL. Our follow-up derived bounds reveal the relationship between model shifts and performance improvement. These discoveries encourage us to formulate a constrained lower-bound optimization problem to permit the monotonicity of MBRL. A further example demonstrates that learning models from a dynamically-varying number of explorations benefit the eventual returns. Motivated by these analyses, we design a simple but effective algorithm CMLO1 (Constrained Model-shift Lower-bound Optimization), by introducing an event-triggered mechanism that flexibly determines when to update the model. Experiments show that CMLO surpasses other state-of-the-art methods and produces a boost when various policy optimization methods are employed. © 2022, CC BY-NC-SA.

关键词： Constrained optimization

来源：评论

学校读者我要写书评

暂无评论

Design and implementation of a novel approach for long-lived particle reconstruction in LHCb experiment at CERN

引用

computer Physics Communications 2025年

作者： Piotr Kulczycki Grzegorz Gołaszewski Tomasz Szumlak Szymon Łukasik AGH University of Krakow Faculty of Physics and Applied Computer Science Division for Information Technology and Systems Research Polish Academy of Sciences Systems Research Institute Centre of Information Technology for Data Analysis Methods

The subject of this paper is the improvement of the procedure to reconstruct long-lived particles in the LHCb (Large Hadron Collider beauty) experiment, one of the main experiments conducted by the European Organization for Nuclear Research CERN in Geneva. The goal of this procedure is to detect or, in other words, reconstruct long-lived particle tracks, based on observations obtained from measurement modules placed far apart, with a primary focus of eliminating erroneously created tracks, the so-called ghost-tracks. The investigated method is carried out by pairing proper trajectories and two autonomous filtering algorithms that are based on the nonparametric estimation of a distribution density as well as an autoencoder, a neural network designated for unsupervised learning. The values obtained from these two algorithms founded on complementary methodologies, mathematical statistics and computational intelligence, are combined with the t-norm. As a result, the number of ghost-tracks is reduced threefold when compared with the method primarily used. To evaluate the results of the designed procedure, a measure of the reconstruction quality, without the information whether a given track is real or only a ghost, is additionally created and effectively applied. Illustrative interpretations make it easier to potentially employ the method elaborated here to research tasks of similar conditions.

关键词： data analysis LHCb experiment long-lived particle ghost-track elimination computational intelligence numerical algorithm

来源：评论

学校读者我要写书评

暂无评论

Recurrence in dense-time AMS assertions

arXiv

引用

arXiv 2020年

作者： Sanyal, Sayandeep da Costa, Antonio Anastasio Bruto Dasgupta, Pallab Formal Methods Laboratory Department of Computer Science and Engineering Indian Institute of Technology Kharagpur India

The notion of recurrence over continuous or dense time, as required for expressing Analog and Mixed-Signal (AMS) behaviours, is fundamentally different from what is offered by the recurrence operators of SystemVerilog Assertions (SVA). This article introduces the formal semantics of recurrence over dense time and provides a methodology for the runtime verification of such properties using interval arithmetic. Our property language extends SVA with dense real-time intervals and predicates containing real-valued signals. We provide a tool kit which interfaces with off-the-shelf EDA tools through standard VPI. Copyright © 2020, The Authors. All rights reserved.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

Efficient Visual Perception of Human-Robot Walking Environments Using Semi-Supervised Learning

Efficient Visual Perception of Human-Robot Walking Environme...

引用

IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)

作者： Dmytro Kuzmenko Oleksii Tsepa Andrew Garrett Kurbis Alex Mihailidis Brokoslaw Laschowski Department of Mathematics National University of Kyiv-Mohyla Academy Kyiv Ukraine Department of Mathematical Methods of System Analysis Igor Sikorsky Kyiv Polytechnic Institute Kyiv Ukraine Department of Computer Science University of Toronto Toronto Canada Department of Systems Design Engineering University of Waterloo Waterloo Canada Temerty Faculty of Medicine University of Toronto Toronto Canada Institute of Biomedical Engineering University of Toronto Toronto Canada Toronto Rehabilitation Institute Toronto Canada Department of Mechanical and Industrial Engineering Robotics Institute University of Toronto Toronto Canada

Convolutional neural networks trained using supervised learning can improve visual perception for human-robot walking. These advances have been possible due to largescale datasets like ExoNet and StairNet - the largest open-source image datasets of real-world walking environments. However, these datasets require vast amounts of manually annotated data, the development of which is time consuming and labor intensive. Here we present a novel semi-supervised learning system (ExoNet-SSL) that uses over 1.2 million unlabelled images from ExoNet to improve training efficiency. We developed a deep learning model based on mobile vision transformers and trained the model using semi-supervised learning for image classification. Compared to standard supervised learning (98.4%), our ExoNet-SSL system was able to maintain high prediction accuracy (98.8%) when tested on previously unseen environments, while requiring 35% fewer labelled images during training. These results show that semi-supervised learning can improve training efficiency by leveraging large amounts of unlabelled data and minimize the size requirements for manually annotated images. Future research $\text{will}$ focus on model deployment for onboard real-time inference and control of human-robot walking.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Evaluating Interpolation and Extrapolation Performance of Neural Retrieval Models

arXiv

引用

arXiv 2022年

作者： Zhan, Jingtao Xie, Xiaohui Mao, Jiaxin Liu, Yiqun Guo, Jiafeng Zhang, Min Ma, Shaoping Department of Computer Science and Technology Beijing National Research Center for Information Science and Technology Tsinghua University Beijing100084 China Beijing Key Laboratory of Big Data Management and Analysis Methods Gaoling School of Artificial Intelligence Renmin University of China Beijing100872 China CAS Key Lab of Network Data Science and Technology Institute of Computing Technology Chinese Academy of Sciences Beijing China

A retrieval model should not only interpolate the training data but also extrapolate well to the queries that are different from the training data. While neural retrieval models have demonstrated impressive performance on ad-hoc search benchmarks, we still know little about how they perform in terms of interpolation and extrapolation. In this paper, we demonstrate the importance of separately evaluating the two capabilities of neural retrieval models. Firstly, we examine existing ad-hoc search benchmarks from the two perspectives. We investigate the distribution of training and test data and find a considerable overlap in query entities, query intent, and relevance labels. This finding implies that the evaluation on these test sets is biased toward interpolation and cannot accurately reflect the extrapolation capacity. Secondly, we propose a novel evaluation protocol to separately evaluate the interpolation and extrapolation performance on existing benchmark datasets. It resamples the training and test data based on query similarity and utilizes the resampled dataset for training and evaluation. Finally, we leverage the proposed evaluation protocol to comprehensively revisit a number of widely-adopted neural retrieval models. Results show models perform differently when moving from interpolation to extrapolation. For example, representation-based retrieval models perform almost as well as interaction-based retrieval models in terms of interpolation but not extrapolation. Therefore, it is necessary to separately evaluate both interpolation and extrapolation performance and the proposed resampling method serves as a simple yet effective evaluation tool for future IR studies. Copyright © 2022, The Authors. All rights reserved.

关键词： Extrapolation

来源：评论

学校读者我要写书评

暂无评论

From tests of discrete symmetries to medical imaging with J-PET detector 22

From tests of discrete symmetries to medical imaging with J-...

引用

22nd Particles and Nuclei International Conference, PANIC 2021

作者： Moskal, P. Baran, J. Chug, N. Curceanu, C. Czerwiński, E. Dadgar, M. Dulski, K. Gajewski, J. Gajos, A. Gorgol, M. Hiesmayr, B.C. Jasińska, B. Kacprzak, K. Kaplon, L. Karimi, H. Klimaszewski, K. Konieczka, P. Korcyl, G. Kozik, T. Krawczyk, N. Krzemień, W. Kubicz, E. Kumar, D. Niedźwiecki, S. Panek, D. Parzych, S. Perez del Rio, E. Raczyński, L. Raj, J. Ruciński, A. Sharma, S. Shivani Shopa, R.Y. Silarski, M. Skurzok, M. Stępień, E.L. Szczepanek, M. Tayefi, F. Wiślicki, W. Faculty of Physics Astronomy and Applied Computer Science Jagiellonian University Poland Total-Body Jagiellonian-PET Laboratory Jagiellonian University Kraków Poland Theranostics Center Jagiellonian University Cracow Poland INFN Laboratori Nazionali di Frascati Frascati Italy Institute of Nuclear Physics Polish Academy of Sciences Kraków Poland Department of Nuclear Methods Institute of Physics Maria Curie-Sklodowska University Lublin Poland Faculty of Physics University of Vienna Vienna Austria Department of Complex Systems National Centre for Nuclear Research Otwock-Świerk Poland High Energy Physics Division National Centre for Nuclear Research Otwock-Świerk Poland

We present results on CPT symmetry tests in decays of positronium performed with the precision at the level of 10−4, and positronium images determined with the prototype of the J-PET tomograph. The first full scale prototype apparatus consists of 192 plastic scintillator strips read out from both ends with vacuum tube photomultipliers. Signals produced by photomultipliers are probed in the amplitude domain and are digitized by FPGA based readout boards in triggerless mode. In this contribution we report on the first two- and three-photon positronium images and tests of CPT symmetry in positronium decays. © Copyright owned by the author(s) under the terms of the Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License (CC BY-NC-ND 4.0)

关键词： Positrons

来源：评论

学校读者我要写书评

暂无评论

Intelligent waste sorting for sustainable environment: A hybrid deep learning and transfer learning model

引用

Gondwana Research 2024年

作者： Kumar Lilhore, Umesh Simaiya, Sarita Dalal, Surjeet Radulescu, Magdalena Balsalobre-Lorente, Daniel Department of Computer Science and Engineering Galgotias University Greater Noida Uttar Pradesh India Department of Computer Science and Engineering Amity University Gurugram Haryana India Institute of Doctoral and Post-Doctoral Studies University Lucian Blaga of Sibiu Sibiu Romania UNEC Research Methods Application Center Azerbaijan State University of Economics (UNEC) Baku 1001 Istiqlaliyyat Str. 6 Azerbaijan Department of Applied Economics I University Castilla-La Mancha Spain Department of Management Faculty of Economics and Management Czech University of Life Sciences Prague Prague 16500 Czech Republic Economic Research Center (WCERC) Western Caspian University Baku Azerbaijan

The significance of waste disposal, classification, and monitoring has dramatically increased due to the increase in industrial development and the progress of intelligent urbanization. Since the last few decades, the utilization of Deep learning techniques has grown increasingly in waste management research. The efficiency of a waste reuse and recycling process relies on its capacity to restore resources to their original state, thereby minimizing pollution and promoting an ecologically sustainable framework. Selecting the optimal deep-learning method for classifying and predicting waste is challenging and time-consuming. This paper proposed intelligent garbage categorization using Bidirectional Long Short-Term Memory (Bi-LSTM) and CNN-based transfer learning to improve environmental sustainability. Organic and recyclable garbage are separated. To simplify trash categorization, a hybrid model combines TL-based CNN and Bi-LSTM. This study extensively examined the suggested technique with numerous CNN computational methods, including VGG-19, ResNet-34, AlexNet, ResNet-50, and VGG-16, using the ’TrashNet Waste’ database. Key findings show that our hybrid model outperforms existing models. Our classification accuracy is 96.78 %, 5.27 % higher than the best model. Our model also reduces misclassification by 7.25 %, proving its reliability. This comprehensive examination examined the computer models’ trash classification performance and provided specific viewpoints. The results explain each technique's pros and cons and show how useful they are in real-world circumstances. Waste classification is practical and sophisticated with a hybrid model. The effectiveness and cleverness of this model improve sustainable environmental practices. The proposed method's excellent performance suggests its seamless integration into practical waste management solutions. © 2024 International Association for Gondwana Research

关键词： Convolutional neural network (CNN) Deep learning Smart Waste Management Transfer Learning Waste classification

来源：评论

学校读者我要写书评

暂无评论

Development of software for calculating the results of medicinal substances bioequivalence 2

Development of software for calculating the results of medic...

引用

2nd International Scientific Conference on Metrological Support of Innovative Technologies, ICMSIT II-2021

作者： Shalaginova, N.V. Mikhlyakova, E.A. Gribkov, D.N. Mikhailina, A.V. Lebedeva, E.V. Department of Applied Mathematics and Computer Science Vyatka State University Kirov Russia Secondary School with In-depth Study of Individual Subjects of Stulovo Kirov Russia Vyatka State University Kirov Russia Department of Informatics and Records Management Orel State Institute of Culture Orel Russia Department of Economics and Management Orel State Institute of Culture Orel Russia Department of Algebra and Mathematical Methods in Economy of Orel State University Named after I.S. Turgenev Orel Russia

International organizations have adopted and recognized drug standards, which should be guided by developers in the field of pharmacology. In practice, there is a problem: how to determine whether a reproduced drug sample really satisfies the world standard for its pharmacological action. It is required to implement an algorithm for checking and confirming the bioequivalence of drugs. The purpose of the study is to automate the verification of standards using an appropriate algorithm, i.e. to develop an application for calculating the results of medicinal substances bioequivalence. The methodology is based on the assumption that the identity in the sense of the created effect of the pharmacokinetic curves of the drug concentration in the blood versus time for the test drug and the standard means their therapeutic equivalence. Research methods include Python programming, use of libraries for data visualization;Visual Studio is an application development environment. The desired algorithm and requirements for the developed application are formulated in the results of the study, based on the study of theoretical issues of determining the medicinal substances bioequivalence. Finally, conclusions about the efficiency of the software are made and options for its improvement are proposed. © Published under licence by IOP Publishing Ltd.

关键词： Data visualization

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：