.png){kind=icon}
返回
Refinement and Universal Approximation via Sparsely Connected ReLU Convolution Nets
.png){kind=icon}
PRE
AI
DOI：10.1109/LSP.2020.3005051.png)
.png){kind=icon}
原文求助.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
We construct a highly regular and simple structured class of sparsely connected convolutional neural networks with rectifier activations that provide universal function approximation in a coarse-to-fine manner with increasing number of layers. The networks are localized in the sense that local changes in the function to be approximated only require local changes in the final layer of weights. At the core of the construction lies the fact that the characteristic function can be derived from a convolution of characteristic functions at the next coarser resolution via a rectifier passing. The latter refinement result holds for all higher order univariate B-splines.
Keyword:
Function approximation
neural networks
splines
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:
9.6
论文数:
1.1W
被引数:
1.7W
机构
引用论文
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Improved Particle Size Control for the Dispersion Polymerization of Methyl methacrylate in Supercritical Carbon Dioxide超临界二氧化碳中甲基丙烯酸甲酯分散聚合的改进粒度控制
OAAI
OAAI分享收藏Preparation of graphite-loaded epoxy-based voltammetric electrodes using a multi-layer coating and hardening technique.png)
The Analyst
The AnalystIF0
PREAI
分享收藏Optimal approximation of piecewise smooth functions using deep ReLU neural networksNEURAL NETWORKSOAAI
NEURAL NETWORKSIF6.3
OAAI分享收藏
查看更多内容