A new approach to training neural networks using natural gradient descent with momentum based on Dirichlet distributions
In this paper, we propose a natural gradient descent algorithm with momentum based on Dirichlet distributions to speed up the training of neural networks. This approach takes into account not only the direction of the gradients, but also the convexity of the minimized function, which significantly a...
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Samara National Research University
2023-02-01
|
| Series: | Компьютерная оптика |
| Subjects: | |
| Online Access: | https://computeroptics.ru/eng/KO/Annot/KO47-1/470118e.html |