.png){kind=icon}
返回
Mini-max initialization for function approximation
.png){kind=icon}
PRE
AI
DOI：10.1016/j.neucom.2003.10.014.png)
.png){kind=icon}
原文求助.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
Neural networks have been successfully applied to various pattern recognition and function approximation problems. However, the training process remains a time-consuming procedure that often gets stuck in a local minimum. The optimum network size and topology are usually unknown. In this paper, we formulate the concept of extrema equivalence for estimating the complexity of a function. Based on this formulation, the optimal network size and topology can be selected according to the number of extrema. Mini-max initialization method is then proposed to select the initial values of the weights for the network that is proven to greatly speed up training. The superior performance of our method in terms of convergence and generalization has been substantiated by experimental results. (C) 2003 Elsevier B.V. All rights reserved.
Keyword:
extrema equivalence
random initialization
mini-max initialization
promising area
chessboard initialization
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:
6.5
论文数:
2.5W
被引数:
6.5W
机构
暂无机构信息
引用论文
分享收藏分享收藏Clinical significance and diagnostic value of serum CEA, CA19-9 and CA72-4 in patients with gastric cancer.png)
Oncotarget
OAAI
OncotargetIF0
OAAI分享收藏Community pharmacy's contribution to improving the public's health: the case of weight management
OAAI
OAAI分享收藏
查看更多内容