.png){kind=icon}
返回
Upper bound on pattern storage in feedforward networks
.png){kind=icon}
PRE
AI
DOI：10.1016/j.neucom.2008.04.014.png)
.png){kind=icon}
原文求助.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
An upper bound on pattern storage is stated for nonlinear feedforward networks with analytic activation functions, like the multilayer perceptron and radial basis function network. The bound is given in terms of the number of network weights, and applies to networks having any number of output nodes and arbitrary connectivity. Starting from the strict interpolation equations and exact finite degree polynomial models for the hidden units, a straightforward proof by contradiction is developed for the upper bound. Several networks, trained by conjugate gradient, are used to demonstrate the tightness of the bound for random patterns. (C) 2008 Elsevier B.V. All rights reserved.
Keyword:
Pattern storage
Memorization
Upper bound
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
引用论文
Adsorption of basic dye from aqueous solutions by modified sepiolite: Equilibrium, kinetics and thermodynamics study.png)
Desalination
DesalinationIF0
PREAI
分享收藏Performance and efficiency: Recent advances in supervised learningPROCEEDINGS OF THE IEEE
PROCEEDINGS OF THE IEEEIF25.9
PREAI
分享收藏New strategy of personalized tissue regeneration: when autologous platelet concentrates encounter biomaterials个性化组织再生的新策略：当自体血小板浓缩物遇到生物材料
OAAI
OAAI分享收藏
查看更多内容