Learning and Smooth Simultaneous Estimation of Errors Based on Empirical Data

This thesis examines issues related to Valiant's Probably Approximately Correct (PAC) model for learning from examples. In this model, a student observes examples that consist of sample points drawn according to a fixed, unknown probability distribution and labeled by a fixed, unknown binary-valued function. Based on this empirical data, the student must select, from a set of candidate functions, a particular function, or "hypothesis," that will accurately predict the labels of future sample points. The expected mismatch between its prediction and the label of a new sample point is called a hypothesis' "generalization error."

Name thesis:degree_name

Ph.D.

Level thesis:degree_level

Dissertation

Discipline thesis:degree_discipline

Electrical Engineering

Grantor

University of Illinois at Urbana-Champaign

Year dc:date

2014

Author dc:creator

• Buescher, Kevin Lee

Contributors dc:contributor

• Kumar, P.R.

• Statistics
• Engineering, System Science
• Artificial Intelligence
• Computer Science

Identifier

(UMI)AAI9314848

OAI identifier oai:identifier

oai:www.ideals.illinois.edu:2142/71990