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.
Original language | English |
---|---|
Title of host publication | 22nd IMAC Conference and Exposition 2004 (IMAC XXII): A Conference and Exposition on Structural Dynamics |
Pages | 1068-1076 |
Number of pages | 9 |
Publication status | Published - 2004 |
Event | 22nd IMAC Conference and Exposition 2004 (IMAC XXII) - Dearborn, Michigan, United States Duration: 26 Jan 2004 → 29 Jan 2004 |
Conference
Conference | 22nd IMAC Conference and Exposition 2004 (IMAC XXII) |
---|---|
Country | United States |
City | Dearborn, Michigan |
Period | 26/01/04 → 29/01/04 |
Keywords
- information-gap
- robustness
- neural network
- regression model