The search functionality is under construction.
The search functionality is under construction.

Author Search Result

[Author] Takahito YOSHIDA(1hit)

1-1hit
  • Loss Function for Deep Learning to Model Dynamical Systems Open Access

    Takahito YOSHIDA  Takaharu YAGUCHI  Takashi MATSUBARA  

     
    LETTER-Artificial Intelligence, Data Mining

      Pubricized:
    2024/07/22
      Vol:
    E107-D No:11
      Page(s):
    1458-1462

    Accurately simulating physical systems is essential in various fields. In recent years, deep learning has been used to automatically build models of such systems by learning from data. One such method is the neural ordinary differential equation (neural ODE), which treats the output of a neural network as the time derivative of the system states. However, while this and related methods have shown promise, their training strategies still require further development. Inspired by error analysis techniques in numerical analysis while replacing numerical errors with modeling errors, we propose the error-analytic strategy to address this issue. Therefore, our strategy can capture long-term errors and thus improve the accuracy of long-term predictions.