Knowledge extraction from neural networks
Browne, Antony, Hudson, Brian, Whitley, David, Ford, Martyn, Picton, Phil and Kazemian, Hassan (2003) Knowledge extraction from neural networks Proceedings of the 29th Annual Conference of the IEEE Industrial Electronics Society. pp. 1909-1913.
In the past, neural networks have been viewed as classification and regression systems whose internal representations were incomprehensible. It is now becoming apparent that algorithms can be designed which extract comprehensible representations from trained neural networks, enabling them to be used for data mining, i.e. the discovery and explanation of previously unknown relationships present in data. This paper reviews existing algorithms for extracting comprehensible representations from neural networks and describes research to generalize and extend the capabilities of one of these algorithms. The algorithm has been generalized for application to bioinformatics datasets, including the prediction of splice site junctions in human DNA sequences. Results generated on this dataset are compared with those generated by a conventional data mining technique (C5), and conclusions are drawn regarding the application of the neural network based technique to other fields of interest.
|Additional Information:||Browne, A., Hudson, B., Whitley, D., Ford, M., Picton, P., & Kazemian, H. (2003). Knowledge extraction from neural networks. Proceedings of the 29th Annual Conference of the IEEE Industrial Electronics Society, Roanoke, Virginia, USA, 1909-1913. © 2003 IEEE. Personal use of this material is permitted. However, permission to reprint/republish this material for advertising or promotional purposes or for creating new collective works for resale or redistribution to servers or lists, or to reuse any copyrighted component of this work in other works must be obtained from the IEEE.|
|Uncontrolled Keywords:||Neural networks, knowledge extraction, data mining, bioinformatics.|
|Divisions:||Faculty of Engineering and Physical Sciences > Computing Science|
|Depositing User:||Mr Adam Field|
|Date Deposited:||27 May 2010 14:09|
|Last Modified:||23 Sep 2013 18:28|
Actions (login required)
Downloads per month over past year