.png){kind=icon}
返回
OCReP: An Optimally Conditioned Regularization for pseudoinversion based neural training
.png){kind=icon}
OA
AI
DOI：10.1016/j.neunet.2015.07.015.png)
.png){kind=icon}
.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
In this paper we consider the training of single hidden layer neural networks by pseudoinversion, which, in spite of its popularity, is sometimes affected by numerical instability issues. Regularization is known to be effective in such cases, so that we introduce, in the framework of Tikhonov regularization, a matricial reformulation of the problem which allows us to use the condition number as a diagnostic tool for identification of instability. By imposing well-conditioning requirements on the relevant matrices, our theoretical analysis allows the identification of an optimal value for the regularization parameter from the standpoint of stability. We compare with the value derived by cross-validation for overfitting control and optimization of the generalization performance. We test our method for both regression and classification tasks. The proposed method is quite effective in terms of predictivity, often with some improvement on performance with respect to the reference cases considered. This approach, due to analytical determination of the regularization parameter, dramatically reduces the computational load required by many other techniques. (C) 2015 Elsevier Ltd. All rights reserved.
Keyword:
Regularization parameter
Condition number
Pseudoinversion
Numerical instability
AI总结
对已上传原文的论文进行重点信息的提取，主要内容包括：简要概述、研究摘要、背景介绍、关键亮点、图文解析、展望与总结。
期刊
IF:
6.3
论文数:
7.8K
被引数:
3.0W
机构
引用论文
Performance-based incentives for agricultural pollution control: identifying and assessing performance measures in the United States.png)
Water Policy
Water PolicyIF0
PREAI
分享收藏Productivity enhancement of solar still by PCM and Nanoparticles miscellaneous basin absorbing materialsDesalinationOAAI
DesalinationIF0
OAAI分享收藏Special Issue on Extreme Learning Machines (ELM 2011) Hangzhou, China, December 6-8 2011SOFT COMPUTING
OAAI
SOFT COMPUTINGIF2.5
OAAI分享收藏分享收藏
查看更多内容