يعرض 1 - 10 نتائج من 15 نتيجة بحث عن '"Heiss, Jakob"', وقت الاستعلام: 0.78s تنقيح النتائج
  1. 1
    تقرير
    Machine Learning-Powered Combinatorial Clock Auction

    المؤلفون: Soumalias, Ermis, Weissteiner, Jakob, Heiss, Jakob, Seuken, Sven

    المصدر: Proceedings of the AAAI Conference on Artificial Intelligence, 38(9) (2024) 9891-9900

    مصطلحات موضوعية: Computer Science - Computer Science and Game Theory, Computer Science - Artificial Intelligence, Computer Science - Machine Learning, 91A06, I.2

    URL الوصول: http://arxiv.org/abs/2308.10226

    أضف إلى المفضلة
  2. 2
    تقرير
    Extending Path-Dependent NJ-ODEs to Noisy Observations and a Dependent Observation Framework

    المؤلفون: Andersson, William, Heiss, Jakob, Krach, Florian, Teichmann, Josef

    المصدر: Transactions on Machine Learning Research (TMLR) 2024

    مصطلحات موضوعية: Statistics - Machine Learning, Computer Science - Machine Learning, Mathematics - Numerical Analysis, Mathematics - Probability

    URL الوصول: http://arxiv.org/abs/2307.13147

    أضف إلى المفضلة
  3. 3
    تقرير
    How (Implicit) Regularization of ReLU Neural Networks Characterizes the Learned Function -- Part II: the Multi-D Case of Two Layers with Random First Layer

    المؤلفون: Heiss, Jakob, Teichmann, Josef, Wutte, Hanna

    مصطلحات موضوعية: Computer Science - Machine Learning, Statistics - Machine Learning

    URL الوصول: http://arxiv.org/abs/2303.11454

    أضف إلى المفضلة
  4. 4
    تقرير
    Bayesian Optimization-based Combinatorial Assignment

    المؤلفون: Weissteiner, Jakob, Heiss, Jakob, Siems, Julien, Seuken, Sven

    المصدر: Proceedings of the AAAI Conference on Artificial Intelligence Vol 37 (2023)

    مصطلحات موضوعية: Computer Science - Machine Learning, Computer Science - Computer Science and Game Theory, Computer Science - Multiagent Systems

    URL الوصول: http://arxiv.org/abs/2208.14698

    أضف إلى المفضلة
  5. 5
    تقرير
    How Infinitely Wide Neural Networks Can Benefit from Multi-task Learning -- an Exact Macroscopic Characterization

    المؤلفون: Heiss, Jakob, Teichmann, Josef, Wutte, Hanna

    مصطلحات موضوعية: Computer Science - Machine Learning, Statistics - Machine Learning, 68T07, 68Q32, I.2

    URL الوصول: http://arxiv.org/abs/2112.15577

    أضف إلى المفضلة
  6. 6
    تقرير
    Monotone-Value Neural Networks: Exploiting Preference Monotonicity in Combinatorial Assignment

    المؤلفون: Weissteiner, Jakob, Heiss, Jakob, Siems, Julien, Seuken, Sven

    المصدر: Proceedings of the Thirty-First International Joint Conference on Artificial Intelligence Main Track (2022). Pages 541-548

    مصطلحات موضوعية: Computer Science - Computer Science and Game Theory

    URL الوصول: http://arxiv.org/abs/2109.15117

    أضف إلى المفضلة
  7. 7
    تقرير
    NOMU: Neural Optimization-based Model Uncertainty

    المؤلفون: Heiss, Jakob, Weissteiner, Jakob, Wutte, Hanna, Seuken, Sven, Teichmann, Josef

    المصدر: Proceedings of the 39th International Conference on Machine Learning, PMLR 162:8708-8758, 2022

    مصطلحات موضوعية: Computer Science - Machine Learning, Computer Science - Artificial Intelligence, Statistics - Machine Learning

    URL الوصول: http://arxiv.org/abs/2102.13640

    أضف إلى المفضلة
  8. 8
    تقرير
    How Implicit Regularization of ReLU Neural Networks Characterizes the Learned Function -- Part I: the 1-D Case of Two Layers with Random First Layer

    المؤلفون: Heiss, Jakob, Teichmann, Josef, Wutte, Hanna

    مصطلحات موضوعية: Computer Science - Machine Learning, Mathematics - Numerical Analysis, Statistics - Machine Learning, 41Axx, 93Exx, 68T05, 68Q32, I.2.6, G.3

    URL الوصول: http://arxiv.org/abs/1911.02903

    أضف إلى المفضلة
  9. 9
    How Infinitely Wide Neural Networks Can Benefit from Multi-task Learning - an Exact Macroscopic Characterization

    المؤلفون: Heiss, Jakob, Teichmann, Josef, Wutte, Hanna

    مصطلحات موضوعية: Bayesian neural network, Large width limit, Neural Networks, Computer Science::Neural and Evolutionary Computation, Generalization, Machine Learning (stat.ML), Multi-task learning, Machine Learning, Machine learning (artificial intelligence), Deep Learning, Deep ReLU neural networks, Deep neural networks, Bayesian Neural Networks, artificial intelligence, machine learning, Artificial neural networks, Regularization, Tikhonov regularization, Overparametrized Neural Networks, Infinite width limit, Data processing, computer science, FOS: Mathematics, ddc:510, ddc:004, Mathematics

    وصف الملف: application/application/pdf

    URL الوصول: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::d4f3c7f829449b7fec028ba8721377fa
    https://hdl.handle.net/20.500.11850/550890

    أضف إلى المفضلة
  10. 10
    Infinite width (finite depth) neural networks benefit from multi-task learning unlike shallow Gaussian Processes - an exact quantitative macroscopic characterization

    المؤلفون: Heiss, Jakob, Teichmann, Josef, Wutte, Hanna

    مصطلحات موضوعية: Machine Learning, Deep Learning, deep neural networks, neural networks, Artificial Intelligence, Artificial neural networks, Regularization, Bayesian Neural Networks, Data processing, computer science, FOS: Mathematics, ddc:510, ddc:004, Mathematics

    وصف الملف: application/application/pdf

    URL الوصول: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::d05e6fa7de7d15d8197b33e3f1b4cab6
    https://hdl.handle.net/20.500.11850/522526

    أضف إلى المفضلة
أدوات البحث: أحصل على تغذية RSS – أرسل هذا البحث بالبريد الإلكتروني – حفظ البحث – جدول التنبيهات: لا شيء