Explaining the output of ensembles on a case by case basis
Citation:
Robert Wall, 'Explaining the output of ensembles on a case by case basis', [thesis], Trinity College (Dublin, Ireland). School of Computer Science & Statistics, 2003, pp 138Download Item:
Wall TCD THESIS 7322 Explaining the.pdf (PDF) 58.23Mb
Abstract:
This thesis introduces a novel method for explaining the predictions of ensembles of artificial neural networks on a case by case basis. Current research is primarily directed towards building global model, that is, models that fully describe all possible input conditions and their associated outputs. The alternative case by case by case approach is referred to as local explanation. This thesis demonstrates a process for performing local explanation.
Author: Wall, Robert
Advisor:
Cunningham, PádraigQualification name:
Doctor of Philosophy (Ph.D.)Publisher:
Trinity College (Dublin, Ireland). School of Computer Science & StatisticsNote:
TARA (Trinity's Access to Research Archive) has a robust takedown policy. Please contact us if you have any concerns: rssadmin@tcd.ieType of material:
thesisAvailability:
Full text availableLicences: