Abstract
Finding an optimal network size is one of the major concerns when building a neural network. In using the local extended Kalman filter (EKF) algorithm, we propose an efficient approach that combines EKF training and pruning as a whole. In particular, the covariance matrix obtained along with the local EKF training can be utilized to indicate the importance of the network weights. As a result, the network size can be determined adaptively to keep pace with the changes in input characteristics. The effectiveness of this algorithm is demonstrated on generalized XOR logic function and handwritten digit recognition. © 2001 Chinese Physical Society.
| Translated title of the contribution | Adaptive training and pruning for neural networks: Algorithms and application |
|---|---|
| Original language | Chinese (Simplified) |
| Pages (from-to) | 674-681 |
| Journal | 物理学报 |
| Volume | 50 |
| Issue number | 4 |
| DOIs | |
| Publication status | Published - Apr 2001 |
Research Keywords
- 神经网络
- 模式识别
- 广义卡尔曼滤波
- 删剪
- Neural networks
- Pattern recognition
- Extended kalman filtering
- Pruning
Fingerprint
Dive into the research topics of 'Adaptive training and pruning for neural networks: Algorithms and application'. Together they form a unique fingerprint.Cite this
- APA
- Author
- BIBTEX
- Harvard
- Standard
- RIS
- Vancouver