• 学术搜索
  • 科研智能体
    • Research Labs
    • AI 阅读
    • AI 文库
    • 深度研究
    • 学者亮点
  • 学术资源
    • AI2000
    • 期刊/会议
    • 学者库
    • 学术API
      MCP&Skill
    • 溯源树
    • 数据集
  • 知识沉淀
    • 学术空间
订阅小程序
旧版功能
aminer vip
开通会员低至0.73元/天
一次搞定AI科研
立即登录
  • English
  • 联系方式
    B

    Berliner Energieagentur (Germany)

    企业EST. 1992
    11论文总数
    70引用总数

    论文量&引用量时间轴

    机构学者

    论文(11)

    年份
    起
    –
    止
    排序
    1Gradient Guided Furthest Point Sampling for Robust Training Set Selection
    Morris Trestman, Stefan Gugler, Felix A. Faber, O. A. von Lilienfeld

    Training set sampling methods are used to improve model performance and lower data costs in machine learning problems relevant to chemistry. We introduce gradient guided furthest point sampling (GGFPS), a simple extension of furthest point sampling (FPS) that leverages molecular force norms to guide efficient sampling of configurational spaces of molecules. Numerical evidence is presented for a toy system (the Styblinski-Tang (ST) function) as well as for molecular dynamics trajectories from the MD17 dataset. Our numerical results indicate superior data efficiency and model robustness when using GGFPS compared to FPS and uniform random sampling (URS), as well as established supervised FPS-style selectors, PCov-FPS and PCov-CUR. Distribution analysis of the MD17 data suggests that FPS systematically under-samples equilibrium geometries, resulting in large test errors for relaxed structures. GGFPS cures this artifact and (i) enables up to twofold reductions in training cost without sacrificing predictive accuracy compared to FPS in the 2-dimensional ST system, (ii) systematically lowers prediction errors for equilibrium as well as strained structures in MD17, and (iii) systematically decreases prediction error variances across all of the MD17 configuration spaces. These results suggest that gradient-aware sampling methods hold great promise as effective training set selection tools, and that naive use of FPS may result in imbalanced training and inconsistent prediction outcomes.

    2026MACHINE LEARNING-SCIENCE AND TECHNOLOGY(2026)引用:1
    引用
    AI阅读
    加入学术空间
    2In-depth Interviews with Women with Eating Disorders
    Jelena Balabanić Mavrović
    2023Eating Disorders in a Capitalist World(2023)
    引用
    AI阅读
    加入学术空间
    3Am Kreuzungspunkt Von Kreis Und Linie: Von Der Ökologischen Form Ludischer Praxis Und Der Motivation Ökologischen Handelns Durch Spiel
    Michael A. Conrad
    2023Science MashUp Green Games(2023)
    引用
    AI阅读
    加入学术空间
    4Weiterentwicklung von Mieterstrommodellen mit Hilfe von Smart Building Technik – Ergebnisse des Projektes ProSHAPE
    Severin Beucker, Manfred Riedel,Friedrich Sick, Jürgen Tacken, Thomas Dittmann,Oliver Zernahle
    2017Praxishandbuch Mieterstrom(2017)引用:1
    引用
    AI阅读
    加入学术空间
    5The Integration of Renewable Energy in the French Electricity System: What Challenges for Optimization?
    Mathilde Mathieu,Andreas Ruedinger, Dimitri Pescia
    2016
    引用
    AI阅读
    加入学术空间
    立即登录,查看全部 11 篇论文

    合作机构(14)

    弗朗西斯克里克研究所合作论文 1
    Institute for Sustainable Development and International Relations合作论文 1
    博尔扎诺自由大学合作论文 1
    拉夫堡大学合作论文 1
    Hamburg Institute of International Economics合作论文 1
    曼彻斯特大学合作论文 1
    Deutsche Rentenversicherung (Germany)合作论文 1
    多伦多大学合作论文 1
    Institut für Automatisierung und Informatik合作论文 1
    哥廷根大学合作论文 1

    机构统计