Show simple item record

dc.contributor.authorYang, Yingjieen
dc.contributor.authorGillingwater, Daviden
dc.contributor.authorHinde, Chris J.en
dc.date.accessioned2008-11-24T13:24:15Z
dc.date.available2008-11-24T13:24:15Z
dc.date.issued2001-01-01en
dc.identifier.citationYang, 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.isbn0-7803-7046-5
dc.identifier.urihttp://hdl.handle.net/2086/187
dc.descriptionIt 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.isoenen
dc.subjectRAE 2008
dc.subjectUoA 23 Computer Science and Informatics
dc.subjectneural nets
dc.titleA new method to evaluate a trained artificial neural networken
dc.typeOtheren
dc.identifier.doihttp://dx.doi.org/10.1109/IJCNN.2001.938783
dc.researchgroupCentre for Computational Intelligence
dc.researchgroupDIGITSen
dc.researchinstituteInstitute of Artificial Intelligence (IAI)en


Files in this item

FilesSizeFormatView

There are no files associated with this item.

This item appears in the following Collection(s)

Show simple item record