.png){kind=icon}
返回
Data-driven performance metrics for neural network learning
.png){kind=icon}
OA
AI
DOI：10.1002/acs.3701.png)
.png){kind=icon}
原文求助.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
Effectiveness of data-driven neural learning in terms of both local mimima trapping and convergence rate is addressed. Such issues are investigated in a case study involving the training of one-hidden-layer feedforward neural networks with the extended Kalman filter, which reduces the search for the optimal network parameters to a state estimation problem, as compared to descent-based methods. In this respect, the performances of the training are assessed by using the Cramer-Rao bound, along with a novel metric based on an empirical criterion to evaluate robustness with respect to local minima trapping. Numerical results are provided to illustrate the performances of the training based on the extended Kalman filter in comparison with gradient-based learning.
Keyword:
Cramer-Rao bound
extended Kalman filter
feedforward neural networks
local minima
neural learning
performance metrics
期刊
IF:
3.8
论文数:
2.6K
被引数:
3.6K
机构
引用论文
Impact of Industrial Pollution on Radial Growth of Conifers in a Former Mining Area in the Eastern Carpathians (Northern Romania).png)
ForestsOAAI
ForestsIF0
OAAI分享收藏
查看更多内容