add to favorites : reference url back to results : previous : next
 

OPTIMIZATION OF NETWORK PARAMETERS AND SEMI-SUPERVISION IN GAUSSIAN ART ARCHITECTURES
Access this item.
TitleOPTIMIZATION OF NETWORK PARAMETERS AND SEMI-SUPERVISION IN GAUSSIAN ART ARCHITECTURES
AuthorChalasani, Roopa
KeywordsImproving the performance of the ART Networks and Comparing the performance of different ARTNetworks
AbstractIn this thesis we extensively experiment with two ART (adaptive resonance theory) architectures called Gaussian ARTMAP (GAM) and Distributed Gaussian ARTMAP (dGAM). Both of these classifiers have been successfully used in the past on a variety of applications. One of our contributions in this thesis is extensively experiments with the GAM and dGAM network parameters and appropriately identifying ranges for these parameters for which these architectures attain good performance (good classification performance and small network size). Furthermore, we have implemented novel modifications of these architectures, called semi-supervised GAM and dGAM architectures. Semi-supervision is a concept that has been used effectively before with the FAM and EAM architectures and in this thesis we are answering the question of whether semi-supervision has the same beneficial effect on the GAM architectures too. Finally, we compared the performance of GAM, dGAM, EAM, FAM and their semi-supervised versions on a number of datasets (simulated and real datasets). These experiments allowed us to draw appropriate conclusions regarding the comparative performance of these architectures.
AdviserGeorgiopoulos, Michael
PublisherUniversity of Central Florida
DegreeM.S.E.E.
Degree DisciplineDepartment of Electrical and Computer Engineering
Degree GrantorEngineering and Computer Science
Degree ProgramElectrical Engineering
Graduation Date2005-05-01
TypeMaster's thesis
Access LevelPublic - Allow Worldwide Access
Release Date2005-05-01
RepositoryUniversity Archives
Repository CollectionElectronic Theses and Dissertations
IdentifierCFE0000474
Access Linkhttp://purl.fcla.edu/fcla/etd/CFE0000474

add to favorites : reference url back to results : previous : next
powered by CONTENTdm ® | contact us  ^ to top ^