检索结果-内蒙古大学图书馆

Accurate machine learning force fields via experimental and simulation data fusion

npj computational Materials 2024年第1期10卷 2512-2521页

作者： Sebastien Röcken Julija Zavadlav Department of Engineering Physics and Computation Multiscale Modeling of Fluid MaterialsTUM School of Engineering and DesignTechnical University of MunichMunichGermany Munich Data Science Institute Technical University of MunichMunichGermany

Machine Learning(ML)-based force fields are attracting ever-increasing interest due to their capacity to span spatiotemporal scales of classical interatomic potentials at quantum-level *** can be trained based on high-fidelity simulations or experiments,the former being the common ***,both approaches are impaired by scarce and erroneous data resulting in models that either do not agree with well-known experimental observations or are under-constrained and only reproduce some *** we leverage both Density Functional Theory(DFT)calculations and experimentally measured mechanical properties and lattice parameters to train an ML potential of *** demonstrate that the fused data learning strategy can concurrently satisfy all target objectives,thus resulting in a molecularmodel of higher accuracycompared to the models trained with a single data *** inaccuracies of DFT functionals at target experimental properties were corrected,while the investigated off-target properties were affected only mildly and mostly *** approach is applicable to any material and can serve as a general strategy to obtain highly accurate ML potentials.

关键词： properties satisfy attracting

来源：评论

学校读者我要写书评

暂无评论

Active learning graph neural networks for partial charge prediction of metal-organic frameworks via dropout Monte Carlo

引用

npj computational Materials 2024年第1期10卷 2360-2369页

作者： Stephan Thaler Felix Mayr Siby Thomas Alessio Gagliardi Julija Zavadlav Professorship of Multiscale Modeling of Fluid Materials Department of Engineering Physics and ComputationTUM School of Engineering and DesignTechnical University of MunichMunichGermany Valence Labs MontrealQCCanada Professorship of Simulation of Nanosystems for Energy Conversion Department of Electrical EngineeringTUM School of ComputationInformation and TechnologyTechnical University of MunichMunichGermany Munich Data Science Institute Technical University of MunichMunichGermany

Metal-organic frameworks(MOF)are an attractive class of porous materials due to their immense design space,allowing for application-tailored *** of interest,such as gas sorption,can be predicted in silico with molecular mechanics ***,the accuracy is limited by the available empirical force field and partial charge estimation *** this work,we train a graph neural network for partial charge prediction via active learning based on Dropout Monte *** show that active learning significantly reduces the required amount of labeled MOFs to reach a target *** obtained model generalizes well to different distributions of MOFs and *** addition,the uncertainty predictions of Dropout Monte Carlo enable reliable estimation of the mean absolute error for unseen *** work paves the way towards accurate molecular modeling of MOFs via next-generation potentials with machine learning predicted partial charges,supporting insilico material design.

关键词： properties charge estimation

来源：评论

学校读者我要写书评

暂无评论

Multi-objective evolutionary optimization for hardware-aware neural network pruning

引用

Fundamental Research 2024年第4期4卷 941-950页

作者： Wenjing Hong Guiying Li Shengcai Liu Peng Yang Ke Tang Guangdong Provincial Key Laboratory of Brain-Inspired Inteligent Computation Department of Computer Science and EngineeringSouthern University of Science and TechnologyShenzhen 518055China Research Institute of Trustworthy Autonomous Systems Southern University of Science and TechnologyShenzhen 518055China Department of Statistics and Data Science Southern University of Science and TechnologyShenzhen 518055China

Neural network pruning is a popular approach to reducing the computational complexity of deep neural *** recent years,as growing evidence shows that conventional network pruning methods employ inappropriate proxy metrics,and as new types of hardware become increasingly available,hardware-aware network pruning that incorporates hardware characteristics in the loop of network pruning has gained growing attention,Both network accuracy and hardware efficiency(latency,memory consumption,etc.)are critical objectives to the success of network pruning,but the conflict between the multiple objectives makes it impossible to find a single optimal *** studies mostly convert the hardware-aware network pruning to optimization problems with a single *** this paper,we propose to solve the hardware-aware network pruning problem with Multi-Objective Evolutionary Algorithms(MOEAs).Specifically,we formulate the problem as a multi-objective optimization problem,and propose a novel memetic MOEA,namely HAMP,that combines an efficient portfoliobased selection and a surrogate-assisted local search,to solve *** studies demonstrate the potential of MOEAs in providing simultaneously a set of alternative solutions and the superiority of HAMP compared to the state-of-the-art hardware-aware network pruning method.

关键词： Multi-objective optimization Evolutionary algorithm Neural network pruning Hardware-awaremachine learning Hardware efficiency

来源：评论

学校读者我要写书评

暂无评论

Broadening the coverage of computational representations of metaphor through Dynamic Metaphor Theory 1

Broadening the coverage of computational representations of ...

引用

1st Workshop on Reference, Framing, and Perspective, RFP 2024

作者： Tan, Xiaojuan Bloem, Jelke Department of Language Literature and Communication Vrije Universiteit Amsterdam Netherlands Institute for Logic Language and Computation University of Amsterdam Netherlands Data Science Centre University of Amsterdam Netherlands

ISBN: (纸本)9782493814272

Current approaches to computational metaphor processing typically incorporate static representations of metaphor. We aim to show that this limits the coverage of such systems. We take insights from dynamic metaphor theory and discuss how existing computational models of metaphor might benefit from representing the dynamics of metaphor when applied to the analysis of conflicting discourse. We propose that a frame-based approach to metaphor representation based on the model of YinYang Dynamics of Metaphoricity (YYDM) would pave the way to more comprehensive modeling of metaphor. In particular, the metaphoricity cues of the YYDM model could be used to address the task of dynamic metaphor identification. Frame-based modeling of dynamic metaphor would facilitate the computational analysis of perspectives in conflicting discourse, with potential applications in analyzing political discourse. © 2024 ELRA Language Resource Association.

关键词： computational methods

来源：评论

学校读者我要写书评

暂无评论

Evolutionary Dynamic Optimization-Based Calibration Framework for Agent-Based Financial Market Simulators 13

Evolutionary Dynamic Optimization-Based Calibration Framewor...

引用

13th IEEE Congress on Evolutionary computation, CEC 2024

作者： Yang, Zhenhua Zhong, Muyao Yang, Peng Southern University of Science and Technology Guangdong Provincial Key Laboratory of Brain-Inspired Intelligent Computation Department of Computer Science and Engineering Shenzhen518055 China Research Institute of Trustworthy Autonomous Systems Southern University of Science and Technology Department of Statistics and Data Science Shenzhen518055 China

ISBN: (纸本)9798350308365

The agent-based financial market simulators serve as an important validation tool for trading strategies. For high-fidelity simulation, it is pivotal to calibrate the parameters of a simulator so that the generated simulation data resembles the observed real market data of interest. In traditional calibration methods, it is typical that the parameters of the simulator are set to be time-invariant. However, the dynamic nature of the real financial market introduces various variability into the behaviors of the market participants over different time intervals, posing in-herent limitations to the traditional methods. A more reasonable approach might involve employing a simulator with time-variant parameters. This suggests that the model parameters can be dynamically adjusted at different stages of the simulation to adapt to the evolving market. Consequently, the calibration problem of the financial market simulators can be treated as a dynamic optimization problem. To dynamically calibrate the simulators, we introduce an Evolutionary Dynamic Optimization (EDO) framework. By monitoring the changes of the best fitness, the whole simulation time interval is adaptively divided into multiple stages. Then the Negatively Correlated Search (NCS) algorithm is employed to effectively adjust the parameters at different simulation stages to better simulate the real financial market. Empirical results on both synthetic and real data verify that our dynamic calibration framework significantly outperforms traditional calibration methods that fixing a parameter for the whole simulation interval. The proposed strategy of detecting dynamic changes is also shown to be more reliable than the naive method of manually segmenting stages. In terms of calibration time, our proposed method significantly improves by nearly 93% compared to the fixed parameter setting, and approximately 61% compared to manual segmentation calibration. © 2024 IEEE.

关键词： Financial markets

来源：评论

学校读者我要写书评

暂无评论

Self-supervised optimization of random material microstructures in the small-data regime

引用

npj computational Materials 2022年第1期8卷 435-445页

作者： Maximilian Rixner Phaedon-Stelios Koutsourelakis Professorship of Data-driven Materials Modeling Department of Engineering Physics and ComputationTechnical University of MunichBoltzmannstr.15D-85748Garching bei MünchenGermany Munich Data Science Institute(MDSI-Core Member) Garching bei MünchenGermany

While the forward and backward modeling of the process-structure-property chain has received a lot of attention from the materials’ community,fewer efforts have taken into consideration *** arise from a multitude of sources and their quantification and integration in the inversion process are essential in meeting the materials design *** first contribution of this paper is a flexible,fully probabilistic formulation of materials’ optimization problems that accounts for the uncertainty in the process-structure and structure-property linkages and enables the identification of optimal,high-dimensional,process *** employ a probabilistic,data-driven surrogate for the structure-property link which expedites computations and enables handling of non-differential *** couple this with a problem-tailored active learning strategy,i.e.,a self-supervised selection of training data,which significantly improves accuracy while reducing the number of expensive model *** demonstrate its efficacy in optimizing the mechanical and thermal properties of two-phase,random media but envision that its applicability encompasses a wide variety of microstructure-sensitive design problems.

关键词： microstructure property optimization

来源：评论

学校读者我要写书评

暂无评论

Synthesizing Accurate Relational data under Differential Privacy

Synthesizing Accurate Relational Data under Differential Pri...

引用

2024 IEEE International Conference on Big data, Bigdata 2024

作者： Kapenekakis, Antheas Dell'aglio, Daniele Vesteghem, Charles Poulsen, Laurids Bøgsted, Martin Garofalakis, Minos Hose, Katja Aalborg University Center for Clinical Data Science Aalborg Denmark Athena Research Center Athens Greece Aalborg University Department of Computer Science Aalborg Denmark Tu Wien Institute of Logic and Computation Vienna Austria

ISBN: (纸本)9798350362480

Medical data is sensitive personal data which, according to GDPR and HIPAA, necessitates regulations concerning their use. Anonymizing this data prior to research would allow for broader access, due to a lower sensitivity. Privacy-aware data synthesis has been proposed as a solution. However, current algorithms face difficulties in synthesizing medical data while maintaining privacy and utility. This is due to the structure of medical data which consists of multiple interlinked tables with high dimensional columns containing sequential aspects of the patient trajectory. The resulting number of correlations is intractable to model naively and, if relational correlations are not accounted for, the resulting data has poor utility (e.g., leads to invalid patient trajectories). In this paper, we present MARE, a relational synthesis algorithm which focuses on a set of core correlations found in relational data while pruning others. The resulting lower computational complexity allows MARE to produce accurate relational data. We showcase that MARE can synthesize multiple medical datasets, which contain sequential aspects, while maintaining utility in form of inter-table and inter-row correlations and privacy guarantees. © 2024 IEEE.

关键词： Differential privacy

来源：评论

学校读者我要写书评

暂无评论

Efficient computation of Image Persistence 39

Efficient Computation of Image Persistence

引用

39th International Symposium on computational Geometry, SoCG 2023

作者： Bauer, Ulrich Schmahl, Maximilian Department of Mathematics TUM School of Computation Information and Technology Munich Data Science Institute Technical University of Munich Germany Universität Heidelberg Germany

ISBN: (纸本)9783959772730

We present an algorithm for computing the barcode of the image of a morphism in persistent homology induced by an inclusion of filtered finite-dimensional chain complexes. The algorithm makes use of the clearing optimization and can be applied to inclusion-induced maps in persistent absolute homology and persistent relative cohomology for filtrations of pairs of simplicial complexes. The clearing optimization works particularly well in the context of relative cohomology, and using previous duality results we can translate the barcodes of images in relative cohomology to those in absolute homology. This forms the basis for an implementation of image persistence computations for inclusions of filtrations of Vietoris-Rips complexes in the framework of the software Ripser. © Ulrich Bauer and Maximilian Schmahl;licensed under Creative Commons License CC-BY 4.0.

关键词： Topology

来源：评论

学校读者我要写书评

暂无评论

Resilience of dynamical systems (Jun, 10.1017/S0956792523000141, 2023)

引用

EUROPEAN JOURNAL OF APPLIED MATHEMATICS 2024年第1期35卷 201-201页

作者： Krakovska, Hana Kuehn, Christian Longo, Iacopo P. Institute of Measurement Science Slovak Academy of Sciences Bratislava Slovakia Section for Science of Complex Systems Medical University of Vienna Vienna Austria Complexity Science Hub Vienna Vienna Austria Department of Mathematics School of Computation Information and Technology Technical University Munich München Germany Munich Data Science Institute Technical University Munich München Germany Department of Mathematics Imperial College London London United Kingdom Departamento de Matemática Aplicada Universidad de Valladolid Valladolid Spain

Stability is among the most important concepts in dynamical systems. Local stability is well-studied, whereas determining the ‘global stability’ of a nonlinear system is very challenging. Over the last few decades, many different ideas have been developed to address this issue, primarily driven by concrete applications. In particular, several disciplines suggested a web of concepts under the headline ‘resilience’. Unfortunately, there are many different variants and explanations of resilience, and often, the definitions are left relatively vague, sometimes even deliberately. Yet, to allow for a structural development of a mathematical theory of resilience that can be used across different areas, one has to ensure precise starting definitions and provide a mathematical comparison of different resilience measures. In this work, we provide a systematic review of the most relevant indicators of resilience in the context of continuous dynamical systems, grouped according to their mathematical features. The indicators are also generalised to be applicable to any attractor. These steps are important to ensure a more reliable, quantitatively comparable and reproducible study of resilience in dynamical systems. Furthermore, we also develop a new concept of resilience against certain nonautonomous perturbations to demonstrate how one can naturally extend our framework. All the indicators are finally compared via the analysis of a classic scalar model from population dynamics to show that direct quantitative application-based comparisons are an immediate consequence of a detailed mathematical analysis.

关键词： Resilience dynamical systems attractors stability 37C20 34D10 34D05 37G35 37N99

来源：评论

学校读者我要写书评

暂无评论

Towards quantifying politicization in foreign aid project reports 2

Towards quantifying politicization in foreign aid project re...

引用

2nd Workshop on Natural Language Processing for Political sciences, PoliticalNLP 2024

作者： Wang, Sidi Eggers, Gustav de Roode Torres Georgiadis, Alexia Đo, Tuan Anh Gontard, Léa Carlitz, Ruth Bloem, Jelke Data Science Centre University of Amsterdam Netherlands Computational Linguistics and Text Mining Lab Vrije Universiteit Amsterdam Netherlands Institute for Logic Language and Computation University of Amsterdam Netherlands Department of Political Science University of Amsterdam Netherlands

ISBN: (纸本)9782493814265

We aim to develop a metric of politicization by investigating whether this concept can be operationalized computationally using document embeddings. We are interested in measuring the extent to which foreign aid is politicized. Textual reports of foreign aid projects are often made available by donor governments, but these are large and unstructured. By embedding them in vector space, we can compute similarities between sets of known politicized keywords and the foreign aid reports. We present a pilot study where we apply this metric to USAID reports. © 2024 ELRA Language Resource Association.

关键词： Embeddings

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：