• 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
    N

    New Chemical Syntheses Institute

    企业EST. 1935
    1,461论文总数
    9,118引用总数

    论文量&引用量时间轴

    机构学者

    论文(1461)

    年份
    起
    –
    止
    排序
    1Double Projection for Reconstructing Dynamical Systems: Between Stochastic and Deterministic Regimes
    Viktor Sip, Martin Breyton, Spase Petkoski,Viktor Jirsa

    Learning stochastic models of dynamical systems from observed data is of interest in many scientific fields. For reliable use in scientific applications, trained models must be able to reproduce the observed dynamics, remain amenable to analysis by mathematical and computational tools, and their dependence on key training hyperparameters must be well understood. Here, we propose a new method for this task within the family of dynamical variational autoencoders. The proposed double projection method estimates both the system state trajectories and the noise time series from data. This approach naturally allows us to perform multi-step system evolution and to learn models with a comparatively low-dimensional state space. We evaluate the performance of the method on six benchmark problems, including both simulated and experimental data. We then analyze how the teacher forcing interval, a key parameter of the multi-step system evolution, shapes the internal dynamics of the trained model, and we compare the resulting behavior to that of deterministic models of equivalent architecture. The results show that shorter teacher forcing intervals favor predominantly deterministic dynamics, whereas longer intervals shift the model behavior toward stronger reliance on stochastic forcing. We further show that the inferred noise can play distinct roles: in one case it recovers a genuine source of stochasticity underlying the data, while in another it compensates for dynamics that the model cannot capture. Our results may provide insight into the behavior of related methods based on teacher forcing techniques and into the interpretation of learned stochastic models more broadly.

    2026MACHINE LEARNING-SCIENCE AND TECHNOLOGY(2026)引用:1
    引用
    AI阅读
    加入学术空间
    2Du Rail Aux ETF : 130 Ans De Dow Jones Racontent Les Métamorphoses Du Capitalisme Financier
    Angelo Riva
    2026
    引用
    AI阅读
    加入学术空间
    3Peut-on Mesurer L’invisible ? Comment Naissent Les Indicateurs Qui Guident Nos Décisions ?
    Florence Jeannot,Guy Parmentier,Romain Rampa
    2026
    引用
    AI阅读
    加入学术空间
    4Face Au Cancer, Quand Le Corps Devient Étranger, Comment Sauver L’intimité ?
    Judith Partouche-Sebban, Saeedeh Vessal, Aymen Ammari, Youssef Souak, Alain Toledano
    2026
    引用
    AI阅读
    加入学术空间
    5Barbie, Mario, Musclor… Hollywood a Décidé De Jouer, Et Ça Rapporte
    Frédéric Aubrun
    2026
    引用
    AI阅读
    加入学术空间
    立即登录,查看全部 1461 篇论文

    合作机构(100)

    Maria Curie-Skłodowska University合作论文 15
    波尔多大学合作论文 10
    Kazimierz Pułaski University of Technology and Humanities in Radom合作论文 9
    波兰科学院合作论文 8
    华沙工业大学合作论文 7
    Kedge Business School合作论文 7
    International University of Monaco合作论文 6
    内盖夫本 - 古里安大学合作论文 5
    格勒诺布尔 - 阿尔卑斯大学合作论文 5
    世界卫生组织合作论文 5

    机构统计