Dissertation/Thesis Abstract

Tactic-Based Learning for collective learning systems
by Armstrong, Alice, D.Sc., The George Washington University, 2008, 320; 3304083
Abstract (Summary)

Tactic-Based Learning is a new selection policy for statistical learning systems that has been tested with a Collective Learning Automaton which solves a simple, but representative problem. Current selection policies respond to immature stimuli that do not yet have high-confidence responses associated with them by selecting responses randomly. Albeit unbiased, this policy ignores any confident information already acquired for other well-trained stimuli. To exploit this confident information, Tactic-Based Learning hypothesizes that in the absence of a sufficiently confident response to a given stimulus, selecting a confident response to a different, but nonetheless well-trained stimulus is a better strategy than selecting a random response. Tactic-Based Learning does not require any feature comparison in search of an appropriate response. Preliminary results show that Tactic-Based Learning significantly accelerates learning and reduces error, especially when several stimuli share the same response, i.e. , when broad domain generalization is possible. Tactic-Based Learning reduces the use of pseudo-random number generators in the response selection process. Additionally, Tactic-Based Learning assists the recovery of learning performance when the problem evolves over time.

Supplemental Files

Some files may require a special program or browser plug-in. More Information

Indexing (document details)
Advisor: Bock, Peter
Commitee: Becker, Glenn, Happel, Mark, Martin, C. Dianne, Youssef, Abdou
School: The George Washington University
Department: Computer Science
School Location: United States -- District of Columbia
Source: DAI-B 69/03, Dissertation Abstracts International
Source Type: DISSERTATION
Subjects: Statistics, Artificial intelligence
Keywords: Cognitive development, Collective learning systems, Machine learning, Reinforcement learning, Statistical learning, Tactic-based learning
Publication Number: 3304083
ISBN: 978-0-549-52118-1
Copyright © 2019 ProQuest LLC. All rights reserved. Terms and Conditions Privacy Policy Cookie Policy
ProQuest