Exploring Supervised Many Layered Learning as a Precursor to Transfer Learning

Persistent Link:
http://hdl.handle.net/10150/271607
Title:
Exploring Supervised Many Layered Learning as a Precursor to Transfer Learning
Author:
Juozapaitis, Jeffrey James
Issue Date:
2012
Publisher:
The University of Arizona.
Rights:
Copyright © is held by the author. Digital access to this material is made possible by the University Libraries, University of Arizona. Further transmission, reproduction or presentation (such as public display or performance) of protected items is prohibited except with permission of the author.
Abstract:
In this paper, we learn a simple conceptual card game as learned by David Stracuzzi's Cumulus algorithm. We then posit a (sadly unimplemented) scheme to transfer the neural net created by it to a similar game with small modifications, hopefully cutting down the learning time. We then analyze the flaws with the transfer scheme and posit other schemes that may produce better results.
Type:
text; Electronic Thesis
Degree Name:
B.S.
Degree Level:
bachelors
Degree Program:
Honors College; Computer Science
Degree Grantor:
University of Arizona

Full metadata record

DC FieldValue Language
dc.language.isoenen_US
dc.titleExploring Supervised Many Layered Learning as a Precursor to Transfer Learningen_US
dc.creatorJuozapaitis, Jeffrey Jamesen_US
dc.contributor.authorJuozapaitis, Jeffrey Jamesen_US
dc.date.issued2012-
dc.publisherThe University of Arizona.en_US
dc.rightsCopyright © is held by the author. Digital access to this material is made possible by the University Libraries, University of Arizona. Further transmission, reproduction or presentation (such as public display or performance) of protected items is prohibited except with permission of the author.en_US
dc.description.abstractIn this paper, we learn a simple conceptual card game as learned by David Stracuzzi's Cumulus algorithm. We then posit a (sadly unimplemented) scheme to transfer the neural net created by it to a similar game with small modifications, hopefully cutting down the learning time. We then analyze the flaws with the transfer scheme and posit other schemes that may produce better results.en_US
dc.typetexten_US
dc.typeElectronic Thesisen_US
thesis.degree.nameB.S.en_US
thesis.degree.levelbachelorsen_US
thesis.degree.disciplineHonors Collegeen_US
thesis.degree.disciplineComputer Scienceen_US
thesis.degree.grantorUniversity of Arizonaen_US
All Items in UA Campus Repository are protected by copyright, with all rights reserved, unless otherwise indicated.