Files in this item

FilesDescriptionFormat

application/pdf

application/pdf3269889.pdf (4MB)Restricted to U of Illinois
(no description provided)PDF

Description

Title:Combining Prior Knowledge and Data: Beyond the Bayesian Framework
Author(s):Epshteyn, Arkady
Doctoral Committee Chair(s):Gerald DeJong
Department / Program:Computer Science
Discipline:Computer Science
Degree Granting Institution:University of Illinois at Urbana-Champaign
Degree:Ph.D.
Genre:Dissertation
Subject(s):Artificial Intelligence
Abstract:We explore this task in three contexts: classification (determining the subject of a newsgroup posting), control (learning to perform tasks such as driving a car up a mountain in simulation), and optimization (optimizing performance of linear algebra operations on different hardware platforms). For the text categorization problem, we introduce a novel algorithm which efficiently integrates prior knowledge into large margin classification. For reinforcement learning, we introduce a novel framework for defining and solving planning problems in terms of qualitative statements about the world. In compiler optimization, Bayesian prior based on an analytic model of hardware is combined with empirical measurements of performance of optimized code to determine the maximum-a-posteriori estimates of the optimization parameters.
Issue Date:2007
Type:Text
Language:English
Description:114 p.
Thesis (Ph.D.)--University of Illinois at Urbana-Champaign, 2007.
URI:http://hdl.handle.net/2142/81761
Other Identifier(s):(MiAaPQ)AAI3269889
Date Available in IDEALS:2015-09-25
Date Deposited:2007


This item appears in the following Collection(s)

Item Statistics