ERA

Download the full-sized PDF of PAC-learning with label noiseDownload the full-sized PDF

Analytics

Share

Permanent link (DOI): https://doi.org/10.7939/R36Q67

Download

Export to: EndNote  |  Zotero  |  Mendeley

Communities

This file is in the following communities:

Graduate Studies and Research, Faculty of

Collections

This file is in the following collections:

Theses and Dissertations

PAC-learning with label noise Open Access

Descriptions

Other title
Subject/Keyword
PAC learning, label noise, minimum disagreement strategy, binary classification
noise, class noise, PAC, probably approximately correct
Type of item
Thesis
Degree grantor
University of Alberta
Author or creator
Jabbari Arfaee, Shahin
Supervisor and department
Zilles, Sandra (Adjunct Computing Science)
Holte, Robert C. (Computing Science)
Examining committee member and department
Lewis, Mark (Mathematical and Statistical Sciences)
Greiner, Russell (Computing Science)
Department
Department of Computing Science
Specialization

Date accepted
2010-12-08T18:31:18Z
Graduation date
2011-06
Degree
Master of Science
Degree level
Master's
Abstract
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.
Language
English
DOI
doi:10.7939/R36Q67
Rights
License granted by Shahin Jabbari Arfaee (sjabbari@ualberta.ca) on 2010-12-02T21:58:48Z (GMT): Permission is hereby granted to the University of Alberta Libraries to reproduce single copies of this thesis and to lend or sell such copies for private, scholarly or scientific research purposes only. Where the thesis is converted to, or otherwise made available in digital form, the University of Alberta will advise potential users of the thesis of the above terms. The author reserves all other publication and other rights in association with the copyright in the thesis, and except as herein provided, neither the thesis nor any substantial portion thereof may be printed or otherwise reproduced in any material form whatsoever without the author's prior written permission.
Citation for previous publication

File Details

Date Uploaded
Date Modified
2014-04-25T00:06:15.441+00:00
Audit Status
Audits have not yet been run on this file.
Characterization
File format: pdf (Portable Document Format)
Mime type: application/pdf
File size: 839295
Last modified: 2015:10:12 15:24:05-06:00
Filename: Jabbari Arfaee_Shahin_Spring 2011.pdf
Original checksum: 9a94d848b1836a455913def540c51bc3
Well formed: false
Valid: false
Status message: Lexical error offset=832239
Page count: 71
Activity of users you follow
User Activity Date