Comparison of two methods for increasing training Milne, Linda en_US Willcock, Charles en_US 2021-11-25T12:46:41Z 2021-11-25T12:46:41Z 1995 en_US
dc.description.abstract The use of artifcial neural networks with geographical data is often constrained by the very small number of training data points which can be obtained. Using multi-spectral and parametric data from the Nullica state forest in NSW, Australia, we look at addition of noise and resampling as methods of increasing the number and quality of the training set to get the most out of the data. Resampling the data appears to offer potential as a method of generalising the neural network without the accuracy trade off of added noise. en_US
dc.language English
dc.language.iso EN en_US
dc.rights CC BY-NC-ND 3.0 en_US
dc.rights.uri en_US
dc.source Legacy MARC en_US
dc.subject.other remotely sensed data en_US
dc.subject.other neural network en_US
dc.subject.other resampling data en_US
dc.subject.other noise en_US
dc.subject.other small datasets en_US
dc.subject.other Neural Networks, Genetic Algorithms and Fuzzy Logic (280212) en_US
dc.title Comparison of two methods for increasing training en_US
dc.type Conference Paper en
dcterms.accessRights open access
dspace.entity.type Publication en_US
unsw.relation.faculty Engineering
unsw.relation.ispartofconferenceLocation Canberra, Australia en_US
unsw.relation.ispartofconferenceName AI in the Environment Workshop en_US
unsw.relation.ispartofconferenceProceedingsTitle Proceedings of the Eighth Australian Joint Conference on Artificial Intelligence, AI’95, Artificial Intelligence in the Environment Workshop en_US
unsw.relation.ispartofconferenceYear 1995 en_US
unsw.relation.ispartofpagefrompageto 89-94 en_US
unsw.relation.originalPublicationAffiliation Milne, Linda, Computer Science & Engineering, Faculty of Engineering, UNSW en_US
unsw.relation.originalPublicationAffiliation Willcock, Charles, Computer Science & Engineering, Faculty of Engineering, UNSW en_US School of Computer Science and Engineering *
Original bundle
Now showing 1 - 1 of 1
Thumbnail Image
141.59 KB
Resource type