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.
Identifer | oai:union.ndltd.org:LACETR/oai:collectionscanada.gc.ca:AEU.10048/1645 |
Date | 06 1900 |
Creators | Jabbari Arfaee, Shahin |
Contributors | Holte, Robert C. (Computing Science), Zilles, Sandra (Adjunct Computing Science), Lewis, Mark (Mathematical and Statistical Sciences), Greiner, Russell (Computing Science) |
Source Sets | Library and Archives Canada ETDs Repository / Centre d'archives des thèses électroniques de Bibliothèque et Archives Canada |
Language | en_US |
Detected Language | English |
Type | Thesis |
Format | 839295 bytes, application/pdf |
Page generated in 0.002 seconds