.png){kind=icon}
返回
l1 Regularization in Two-Layer Neural Networks
.png){kind=icon}
PRE
AI
DOI：10.1109/LSP.2021.3129698.png)
.png){kind=icon}
原文求助.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
A crucial problem of neural networks is to select an architecture that strikes appropriate tradeoffs between underfitting and overfitting. This work shows that l(1) regularizations for two-layer neural networks can control the generalization error and sparsify the input dimension. In particular, with an appropriate l(1) regularization on the output layer, the network can produce a tight statistical risk. Moreover, an appropriate l(1) regularization on the input layer leads to a risk hound that does not involve the input data dimension. The results also indicate that training a wide neural network with a suitable regularization provides an alternative bias-variance tradeoff to selecting from a candidate set of neural networks. Our analysis is based on a new integration of dimension-based and norm-based complexity analysis to bound the generalization error.
Keyword:
Generalization error
model complexity
neural network
regularization
期刊
IF:
9.6
论文数:
1.1W
被引数:
1.7W
机构
引用论文
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
NONPARAMETRIC REGRESSION USING DEEP NEURAL NETWORKS WITH RELU ACTIVATION FUNCTION.png)
ANNALS OF STATISTICS
OAAI
ANNALS OF STATISTICSIF3.7
OAAI分享收藏AQP2 is a substrate for endogenous PP2B activity within an inner medullary AKAP-signaling complex
PREAI
分享收藏
查看更多内容