This paper reports the initial results of a joint research project carried out by Aston University and Lloyd's Register to develop a practical method of assessing neural network applications. A set of assessment guidelines for neural network applications were developed and tested on two applications. These case studies showed that it is practical to assess neural networks in a statistical pattern recognition framework. However there is need for more standardisation in neural network technology and a wider takeup of good development practice amongst the neural network community.
|Title of host publication||SafeComp 97: Proceedings of the 16th International Conference on Computing Safety, Reliability and Security|
|Place of Publication||London|
|Number of pages||12|
|Publication status||Published - 1997|
|Event||SafeComp 97, Proceedings of the 16th International Conference on Computer Safety, Reliability and Security, ed. P. Daniel, pp. 357-368. - |
Duration: 1 Jan 1997 → 1 Jan 1997
|Conference||SafeComp 97, Proceedings of the 16th International Conference on Computer Safety, Reliability and Security, ed. P. Daniel, pp. 357-368.|
|Period||1/01/97 → 1/01/97|
Bibliographical noteCopyright of Springer 16th International Conference on Computer Safety, Reliability, and Security, York, UK, September 7-10, 1997
Nabney, I. T., Paven, M. J. S., Eldridge, R. C., & Lee, C. (1997). Practical assessment of neural network applications. In P. Daniel (Ed.), SafeComp 97: Proceedings of the 16th International Conference on Computing Safety, Reliability and Security (pp. 357-368). Springer.