A new method to evaluate a trained artificial neural network

De Montfort University Open Research Archive

Show simple item record

dc.contributor.author Yang, Yingjie en
dc.contributor.author Gillingwater, David en
dc.contributor.author Hinde, Chris J. en
dc.date.accessioned 2008-11-24T13:24:15Z
dc.date.available 2008-11-24T13:24:15Z
dc.date.issued 2001-01-01 en
dc.identifier.citation Yang, Y., Hinde, C.J., and Gillingwater, D. (2001) A new method to evaluate a trained artificial neural network. In: Proceedings. IJCNN '01. International Joint Conference Neural Networks, Washington, DC, 15-19 July, Vol.4, pp. 2620-2625
dc.identifier.isbn 0-7803-7046-5 en
dc.identifier.uri http://hdl.handle.net/2086/187
dc.description It is possible for a trained neural network to give a false mapping. We propose a new approach to evaluate a trained neural network. A new parameter is defined to identify the different potential roles of the individual input factors based on the trained connections of the nodes in the network. Compared with field-specific knowledge, the dominance of individual input factors can be checked and then false mappings satisfying only the specific data set may be avoided. In this way, the available data could be fully applied to the training stage and the validation is simple and efficient. en
dc.language.iso en en
dc.subject RAE 2008
dc.subject UoA 23 Computer Science and Informatics
dc.subject neural nets
dc.title A new method to evaluate a trained artificial neural network en
dc.type Other en
dc.identifier.doi http://dx.doi.org/10.1109/IJCNN.2001.938783
dc.researchgroup Centre for Computational Intelligence
dc.researchgroup DIGITS en

Files in this item

This item appears in the following Collection(s)

Show simple item record