Physics-informed neural network model using natural gradient descent with Dirichlet distribution
In this article we propose the physics-informed neural network model which contains the natural gradient descent with Dirichlet distribution. Such an optimizer can more accurately converge in the global minimum of the loss function in a short number of iterations. Due to natural gradient, one consid...
Сохранить в:
| Главные авторы: | Abdulkadirov, R. I., Абдулкадиров, Р. И., Lyakhov, P. A., Ляхов, П. А., Baboshina, V. A., Бабошина, В. А. |
|---|---|
| Формат: | Статья |
| Язык: | English |
| Опубликовано: |
Elsevier Ltd
2025
|
| Темы: | |
| Online-ссылка: | https://dspace.ncfu.ru/handle/123456789/30520 |
| Метки: |
Добавить метку
Нет меток, Требуется 1-ая метка записи!
|
Схожие документы
-
A new approach to training neural networks using natural gradient descent with momentum based on Dirichlet distributions
Автор: Abdulkadirov, R. I., и др.
Опубликовано: (2023) -
Improving the Accuracy of Neural Network Pattern Recognition by Fractional Gradient Descent
Автор: Abdulkadirov, R. I., и др.
Опубликовано: (2024) -
A Second-Order Numerical Method for a Class of Optimal Control Problems
Автор: Khandzel, A. V., и др.
Опубликовано: (2024) -
Analysis of an Existing Method for Detecting Adversarial Attacks on Deep Neural Networks
Автор: Lapina, M. A., и др.
Опубликовано: (2024) -
Development of an Approach to Confidential Learning with Errors in the Design of Neural Networks
Автор: Bezuglova, E. S., и др.
Опубликовано: (2024)