Computing and Analyzing the Sensitivity of MLP Due to the Errors of the i.i.d. Inputs and Weights Based on CLT

NCU Institutional Repository > 資訊電機學院 > 電機工程學系 > 期刊論文 > Item 987654321/51925

jsp.display-item.identifier=請使用永久網址來引用或連結此文件: http://ir.lib.ncu.edu.tw/handle/987654321/51925

题名:	Computing and Analyzing the Sensitivity of MLP Due to the Errors of the i.i.d. Inputs and Weights Based on CLT
作者:	Yang,SS;Ho,CL;Siu,S
贡献者:	電機工程學系
关键词:	MULTILAYER PERCEPTRON;PERTURBATION;NETWORKS
日期:	2010
上传时间:	2012-03-28 10:10:36 (UTC+8)
出版者:	國立中央大學
摘要:	In this paper, we propose an algorithm based on the central limit theorem to compute the sensitivity of the multilayer perceptron (MLP) due to the errors of the inputs and weights. For simplicity and practicality, all inputs and weights studied here are independently identically distributed (i.i.d.). The theoretical results derived from the proposed algorithm show that the sensitivity of the MLP is affected by the number of layers and the number of neurons adopted in each layer. To prove the reliability of the proposed algorithm, some experimental results of the sensitivity are also presented, and they match the theoretical ones. The good agreement between the theoretical results and the experimental results verifies the reliability and feasibility of the proposed algorithm. Furthermore, the proposed algorithm can also be applied to compute precisely the sensitivity of the MLP with any available activation functions and any types of i.i.d. inputs and weights.
關聯:	IEEE TRANSACTIONS ON NEURAL NETWORKS
显示于类别:	[電機工程學系] 期刊論文

文件中的档案:

档案	描述	大小	格式	浏览次数
index.html		0Kb	HTML	343	检视/开启

在NCUIR中所有的数据项都受到原著作权保护.

社群 sharing