Return to search

PAC-learning with label noise

One of the main criticisms of previously studied label noise models in the PAC-learning framework is the inability of such models to represent the noise in real world data. In this thesis, we study this problem by introducing a framework for modeling label noise and suggesting four new
label noise models. We prove positive learnability results for these noise models in learning simple concept classes and discuss the difficulty of the problem of learning other interesting concept classes under these new models. In addition, we study the previous general learning algorithm,
called the minimum pn-disagreement strategy, that is used to prove learnability results in the PAC-learning framework both in the absence and presence of noise. Because of limitations of the minimum pn-disagreement strategy, we propose a new general learning algorithm called the minimum
nn-disagreement strategy. Finally, for both minimum pn-disagreement strategy and minimum nn-disagreement strategy, we investigate some properties of label noise models that provide sufficient conditions for the learnability of specific concept classes.

Identiferoai:union.ndltd.org:LACETR/oai:collectionscanada.gc.ca:AEU.10048/1645
Date06 1900
CreatorsJabbari Arfaee, Shahin
ContributorsHolte, Robert C. (Computing Science), Zilles, Sandra (Adjunct Computing Science), Lewis, Mark (Mathematical and Statistical Sciences), Greiner, Russell (Computing Science)
Source SetsLibrary and Archives Canada ETDs Repository / Centre d'archives des thèses électroniques de Bibliothèque et Archives Canada
Languageen_US
Detected LanguageEnglish
TypeThesis
Format839295 bytes, application/pdf

Page generated in 0.0021 seconds