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

NCUIR > College of Electrical Engineering & Computer Science > Department of Electrical Engineering > journal & Dissertation > Item 987654321/51925

Please use this identifier to cite or link to this item: http://ir.lib.ncu.edu.tw/handle/987654321/51925

Title:	Computing and Analyzing the Sensitivity of MLP Due to the Errors of the i.i.d. Inputs and Weights Based on CLT
Authors:	Yang,SS;Ho,CL;Siu,S
Contributors:	電機工程學系
Keywords:	MULTILAYER PERCEPTRON;PERTURBATION;NETWORKS
Date:	2010
Issue Date:	2012-03-28 10:10:36 (UTC+8)
Publisher:	國立中央大學
Abstract:	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.
Relation:	IEEE TRANSACTIONS ON NEURAL NETWORKS
Appears in Collections:	[Department of Electrical Engineering] journal & Dissertation

Files in This Item:

File	Description	Size	Format
index.html		0Kb	HTML	390	View/Open

社群 sharing