A quantified sensitivity measure for multilayer perceptron to input perturbation

The sensitivity of a neural network's output to its input perturbation is an important issue with both theoretical and practical values. In this article, we propose an approach to quantify the sensitivity of the most popular and general feedforward network: multilayer perceptron (MLP). The sens...

Full description

Bibliographic Details
Published in:Neural computation, Vol. 15, No. 1 (2003), p. 183-212
Main Author: Zeng, Xiaoqin
Other Involved Persons: Yeung, Daniel S
Format: Article
Item Description:Date Completed 12.03.2003
Date Revised 15.11.2007
published: Print
Citation Status MEDLINE
Copyright: From MEDLINE®/PubMed®, a database of the U.S. National Library of Medicine
QR Code: Show QR Code