Abstract
Artificial neural networks are employed in many areas of industry such as medicine and defence. There are many techniques that aim to improve the performance of neural networks for safety-critical systems. However, there is a complete absence of analytical certification methods for neural network paradigms. Consequently, their role in safety-critical applications, if any, is typically restricted to advisory systems. It is therefore desirable to enable neural networks for highly-dependable roles. This paper defines the safety criteria which if enforced, would contribute to justifying the safety of neural networks. The criteria are a set of safety requirements for the behaviour of neural networks. The paper also highlights the challenge of maintaining performance in terms of adaptability and generalisation whilst providing acceptable safety arguments.
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
Lisboa, P.: Industrial use of safety-related artificial neural networks. Health & Safety Executive 327 (2001)
Sharkey, A.J.C., Sharkey, N.E.: Combining Diverse Neural Nets, in Computer Science. University of Sheffield, Sheffield (1997)
Nabney, I., et al.: Practical Assessment of Neural Network Applications. Aston University & Lloyd’s Register, UK (2000)
Rodvold, D.M.: A Software Development Process Model for Artificial Neural Networks in Critical Applications. In: Proceedings of the 1999 International Conference on Neural Networks (IJCNN 1999), Washington D.C. (1999)
Wen, W., Callahan, J., Napolitano, M.: Towards Developing Verifiable Neural Network Controller. Department of Aerospace Engineering, NASA/WVU Software Research Laboratory, West Virginia University, Morgantown (1996)
Leveson, N.: Safeware: system safety and computers. Addison-Wesley, Reading (1995)
Villemeur, A.: Reliability, Availability, Maintainability and Safety Assessment, vol. 1. John Wiley & Sons, Chichester (1992)
MoD, Defence Standard 00-55: Requirements for Safety Related Software in Defence Equipment. UK Ministry of Defence (1996)
SAE, ARP 4761 - Guidelines and Methods for Conducting the Safety Assessment Process on Civil Airborne Systems and Equipment. The Society for Automotive Engineers (1996)
MoD, Interim Defence Standard 00-58 Issue 1: HAZOP Studies on Systems Containing Programmable Electronics, UK Ministry of Defence (1996)
Kelly, T.P.: Arguing Safety – A Systematic Approach to Managing Safety Cases. Department of Computer Science, University of York, York (1998)
Kearns, M.: A Bound on the Error of Cross Validation Using the Approximation and Estimation Rates, with Consequences for the Training-Test Split. AT&T Bell Laboratories
Andrews, R., Diederich, J., Tickle, A.: A survey and critique of techniques for extracting rules from trained artificial neural networks. Neurocomputing Research Centre, Queensland University of Technology (1995)
Kilimasaukas, C.C.: Neural nets tell why. Dr Dobbs’s pp. 16–24 (April 1991)
Venema, R.S.: Aspects of an Integrated Neural Prediction System, Rijksuniversiteit, Groningen, Netherlands (1999)
Weaver, R.A., McDermid, J.A., Kelly, T.P.: Software Safety Arguments: Towards a Systematic Categorisation of Evidence. In: International System Safety Conference, Denver, CO (2002)
Dorffner, G., Wiklicky, H., Prem, E.: Formal neural network specification and its implications on standardisation. Computer Standards and Interfaces 16, 205–219 (1994)
Osherson, D.N., Weinstein, S., Stoli, M.: Modular Learning. Computational Neuroscience, Cambridge, MA, pp. 369–377 (1990)
Zwaag, B.J., Slump, K.: Process Identification Through Modular Neural Networks and Rule Extraction. In: 5th International FLINS Conference. World Scientific, Gent (2002)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2003 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Kurd, Z., Kelly, T. (2003). Establishing Safety Criteria for Artificial Neural Networks. In: Palade, V., Howlett, R.J., Jain, L. (eds) Knowledge-Based Intelligent Information and Engineering Systems. KES 2003. Lecture Notes in Computer Science(), vol 2773. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-540-45224-9_24
Download citation
DOI: https://doi.org/10.1007/978-3-540-45224-9_24
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-40803-1
Online ISBN: 978-3-540-45224-9
eBook Packages: Springer Book Archive