PDE MODELS FOR DEEP NEURAL NETWORKS: LEARNING THEORY, CALCULUS OF VARIATIONS AND OPTIMAL CONTROL

被引：0
|
作者：
Markowich, Peter [1 ,2 ]
Portaro, Simone [1 ]
机构：
[1] Mathematical and Computer Sciences and Engineering Division, King Abdullah University of Science and Technology, Thuwal,23955-6900, Saudi Arabia
[2] Faculty of Mathematics, University of Vienna, Oskar-Morgenstern-Platz 1, Vienna,1090, Austria
来源：
arXiv |
关键词：
Adaptive control systems - Choquet integral - Deep neural networks - Differentiation (calculus) - Feedback control - Gradient methods - Integral equations - Maximum principle - Multilayer neural networks - Optimal control systems - Ordinary differential equations - Partial differential equations - Variational techniques;
D O I：
暂无
中图分类号：
学科分类号：
摘要：
引用
收藏
相关论文
共 50 条
  • [21] LOW: Training deep neural networks by learning optimal sample weights
    Santiago, Carlos
    Barata, Catarina
    Sasdelli, Michele
    Carneiro, Gustavo
    Nascimento, Jacinto C.
    Pattern Recognition, 2021, 110
  • [22] Towards the theory of strong minimum in calculus of variations and optimal control: a view from variational analysis
    A. D. Ioffe
    Calculus of Variations and Partial Differential Equations, 2020, 59
  • [23] LOW: Training deep neural networks by learning optimal sample weights
    Santiago, Carlos
    Barata, Catarina
    Sasdelli, Michele
    Carneiro, Gustavo
    Nascimento, Jacinto C.
    PATTERN RECOGNITION, 2021, 110
  • [24] DEEP LEARNING AS OPTIMAL CONTROL PROBLEMS: MODELS AND NUMERICAL METHODS
    Benning, Martin
    Celledoni, Elena
    Ehrhardt, Matthias J.
    Owren, Brynjulf
    Schonlieb, Carola-Bibiane
    JOURNAL OF COMPUTATIONAL DYNAMICS, 2019, 6 (02): : 171 - 198
  • [25] Reluplex: a calculus for reasoning about deep neural networks
    Katz, Guy
    Barrett, Clark
    Dill, David L.
    Julian, Kyle
    Kochenderfer, Mykel J.
    FORMAL METHODS IN SYSTEM DESIGN, 2022, 60 (01) : 87 - 116
  • [26] Reluplex: a calculus for reasoning about deep neural networks
    Guy Katz
    Clark Barrett
    David L. Dill
    Kyle Julian
    Mykel J. Kochenderfer
    Formal Methods in System Design, 2022, 60 : 87 - 116
  • [27] Theory-based residual neural networks: A synergy of discrete choice models and deep neural networks
    Wang, Shenhao
    Mo, Baichuan
    Zhao, Jinhua
    TRANSPORTATION RESEARCH PART B-METHODOLOGICAL, 2021, 146 : 333 - 358
  • [28] Towards Optimal Power Control via Ensembling Deep Neural Networks
    Liang, Fei
    Shen, Cong
    Yu, Wei
    Wu, Feng
    IEEE TRANSACTIONS ON COMMUNICATIONS, 2020, 68 (03) : 1760 - 1776
  • [29] Neural networks for optimal control
    Sorensen, O
    SYSTEM STRUCTURE AND CONTROL 1995, 1996, : 361 - 366
  • [30] Neural networks for optimal control
    Narendra, KS
    Brown, SJ
    PROCEEDINGS OF THE 36TH IEEE CONFERENCE ON DECISION AND CONTROL, VOLS 1-5, 1997, : 478 - 479
12345