.png){kind=icon}
返回
Statistical guarantees for regularized neural networks
.png){kind=icon}
OA
AI
DOI：10.1016/j.neunet.2021.04.034.png)
.png){kind=icon}
.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
Neural networks have become standard tools in the analysis of data, but they lack comprehensive mathematical theories. For example, there are very few statistical guarantees for learning neural networks from data, especially for classes of estimators that are used in practice or at least similar to such. In this paper, we develop a general statistical guarantee for estimators that consist of a least-squares term and a regularizer. We then exemplify this guarantee with l(1)-regularization, showing that the corresponding prediction error increases at most logarithmically in the total number of parameters and can even decrease in the number of layers. Our results establish a mathematical basis for regularized estimation of neural networks, and they deepen our mathematical understanding of neural networks and deep learning more generally. (C) 2021 Elsevier Ltd. All rights reserved.
Keyword:
Neural networks
Deep learning
Prediction guarantees
Regularization
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
引用论文
Electrochemically assisted micro localized grafting of aptamers in a microchannel engraved in fluorinated thermoplastic polymer Dyneon THV.png)
RSC Advances
RSC AdvancesIF0
PREAI
分享收藏Threshold voltage for purely flexoelectric deformations of conducting homeotropic nematic layers
PREAI
分享收藏
查看更多内容