4. Summary
Guidance on risk assessment specific to the special characteristics of neural network software is required, and this is not presently available. General frameworks and taxonomies for software probabilistic risk assessment have been proposed, but they are not specific, nor applicable in some instances, to neural networks. This chapter, while limited in its applicability to every safety- and mission-critical neural network system, points out several possible risk assessment techniques as well as useful places to begin considering identification of risks and hazards.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
References
Bolt, George Ravuama. 1992. Fault Tolerance in Artificial Neural Networks — Are Neural Networks Inherently Fault Tolerant? D. Phil. Thesis, University of York. Nov.
Chillarege, R.; W. L. Kao; and R. G. Condit. 1992. Orthogonal Defect Classification — A Concept for In-Process Measurements. IEEE Transactions on Software Engineering SE-18:943–956.
IEEE Std 1012-1998. 1998. IEEE Standard for Software Verification and Validation. New York, NY.
Mackall, Dale; Stacy Nelson; and Johann Schumman. 2002. Verification and Validation of Neural Networks for Aerospace Systems. NASA Dryden Flight Research Center and NASA Ames Research Center. June 12.
Mackall, Dale; Brian Taylor; et al. 2003. Verification and Validation of Adaptive Neural Networks for Aerospace Systems, Version 1.2 (Draft without Appendices). NASA Dryden Flight Research Center and NASA Ames Research Center. March 31.
Miikkulainen, R.; and M. Dyer. 1988. Encoding Input/Output Representations in Connectionist Cognitive Systems. 1988 Connectionist Models Summer School, Carnegie-Mellon University. Morgan Kaufmann.
Rumelhart, D.E.; G.E. Hinton; and R.J. Williams. 1986. Learning Internal Representations by Error Propagation. In Parallel Distributed Processing, eds. Rumelhart, D.E.; and J.L. McClelland. pp. 318–362. MIT Press.
Smidts, Carol; Bin Li; and Ming Li. 2001 Integrating Software into Probabilistic Risk Assessment. NASA report.
Author information
Authors and Affiliations
Rights and permissions
Copyright information
© 2006 Springer Science+Business Media, Inc.
About this chapter
Cite this chapter
Pullum, L., Taylor, B.J. (2006). Risk and Hazard Analysis for Neural Network Systems. In: Methods and Procedures for the Verification and Validation of Artificial Neural Networks. Springer, Boston, MA. https://doi.org/10.1007/0-387-29485-6_3
Download citation
DOI: https://doi.org/10.1007/0-387-29485-6_3
Publisher Name: Springer, Boston, MA
Print ISBN: 978-0-387-28288-6
Online ISBN: 978-0-387-29485-8
eBook Packages: Computer ScienceComputer Science (R0)