Note: This website is not updated anymore and may contain outdated information. The new website is at

Seminar: Shahin Jabbari, "PAC-learning with label noise," Jan. 26, 12:30, CL 408 (Expired)

SPEAKER:     Shahin Jabbari
                        University of Alberta
DATE:             January 26, 2011
TIME:             12:30 p.m.
PLACE:          CL 408

TITLE:            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.

Breaking News

Recent News

Do You Have News for the Department of Computer Science?

  • Please send a plain text version of your posting, which can include URL links, to
To Top of Page