Back to Search
Start Over
An Adaptive Deep Learning Optimization Method Based on Radius of Curvature.
- Source :
-
Computational Intelligence & Neuroscience . 11/10/2021, p1-10. 10p. - Publication Year :
- 2021
-
Abstract
- An adaptive clamping method (SGD-MS) based on the radius of curvature is designed to alleviate the local optimal oscillation problem in deep neural network, which combines the radius of curvature of the objective function and the gradient descent of the optimizer. The radius of curvature is considered as the threshold to separate the momentum term or the future gradient moving average term adaptively. In addition, on this basis, we propose an accelerated version (SGD-MA), which further improves the convergence speed by using the method of aggregated momentum. Experimental results on several datasets show that the proposed methods effectively alleviate the local optimal oscillation problem and greatly improve the convergence speed and accuracy. A novel parameter updating algorithm is also provided in this paper for deep neural network. [ABSTRACT FROM AUTHOR]
- Subjects :
- *DEEP learning
*CURVATURE
*MOVING average process
*ALGORITHMS
Subjects
Details
- Language :
- English
- ISSN :
- 16875265
- Database :
- Academic Search Index
- Journal :
- Computational Intelligence & Neuroscience
- Publication Type :
- Academic Journal
- Accession number :
- 153496949
- Full Text :
- https://doi.org/10.1155/2021/9882068