Strathprints Home | Open Access | Browse | Search | User area | Copyright | Help | Library Home | SUPrimo

Information-gap robustness of a neural network regression model

Pierce, S.G. and Worden, K. and Manson, G. (2004) Information-gap robustness of a neural network regression model. [Proceedings Paper]

Full text not available in this repository. (Request a copy from the Strathclyde author)

Abstract

As a result of their black-box nature, neural networks resist traditional methods of certification and therefore cannot be used in safety critical applications. This situation is undesirable as neural networks can provide an effective solution to many engineering problems. The object of the current paper is to explore the possibility of quantifying and qualifying the reliability of neural networks by a means outside the traditional framework. The approach used here will follow Ben-Haim’s information-gap theory of uncertainty. This is a non-probabilistic approach which may lend itself well to certification of black-box systems. The approach is demonstrated here on a neural network regression model of the process of pre-sliding friction between solids.

Item type: Proceedings Paper
ID code: 41868
Keywords: information-gap, robustness, neural network, regression model, Electrical engineering. Electronics Nuclear engineering
Subjects: Technology > Electrical engineering. Electronics Nuclear engineering
Department: Faculty of Engineering > Electronic and Electrical Engineering
Related URLs:
Depositing user: Pure Administrator
Date Deposited: 01 Nov 2012 11:59
Last modified: 17 Jul 2013 14:15
URI: http://strathprints.strath.ac.uk/id/eprint/41868

Actions (login required)

View Item