Generalization error estimates and training data valuation
This thesis addresses several problems related to generalization in machine learning systems. We introduce a theoretical framework for studying learning and generalization. Within this framework, a closed form is derived for the expected generalization error that estimates the out-of-sample performa...
Internet
https://thesis.library.caltech.edu/3347/1/Nicholson_a_2002.pdfNicholson, Alexander Marshall (2002) Generalization error estimates and training data valuation. Dissertation (Ph.D.), California Institute of Technology. doi:10.7907/1H16-VX81. https://resolver.caltech.edu/CaltechETD:etd-09062005-083717 <https://resolver.caltech.edu/CaltechETD:etd-09062005-083717>