.png){kind=icon}
返回
Function approximation on non-Euclidean spaces
.png){kind=icon}
PRE
AI
DOI：10.1016/j.neunet.2004.09.003.png)
.png){kind=icon}
原文求助.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
This paper presents a family of layered feed-forward networks that is able to uniformly approximate functions on any metric space, and also on a wide variety of non-metric spaces. Non-Euclidean input spaces are frequently encountered in practice, while usual approximation schemes are guaranteed to work only on Euclidean metric spaces. Theoretical foundations are provided, as well as practical algorithms and illustrative examples. This tool potentially constitutes a significant extension of the common notion of 'universal approximation capability'. (C) 2004 Elsevier Ltd. All rights reserved.
Keyword:
function approximation
non-metric spaces
feed-forward neural networks
regularization
invariants
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:
8.2K
被引数:
3.0W
机构
暂无机构信息
引用论文
分享收藏分享收藏Real-time and offline techniques for identifying obstructive sleep apnea patients用于识别阻塞性睡眠呼吸暂停患者的实时和离线技术
PREAI
分享收藏Two-dimensional bricklayer arrangements of tolans using halogen bonding interactions使用卤素键相互作用的tolans的二维瓦工层布置
PREAI
分享收藏Effect of ultrasonic treatment on microstructural and mechanical properties of Al 7075/Grp composite
PREAI
分享收藏Nuclear import of cutaneous beta genus HPV8 E7 oncoprotein is mediated by hydrophobic interactions between its zinc-binding domain and FG nucleoporins.png)
Virology
OAAI
VirologyIF0
OAAI分享收藏
查看更多内容