Title
Genetically Engineered Art Architectures
Abstract
This chapter focuses on the evolution of ARTMAP architectures, using genetic algorithms, with the objective of improving generalization performance and alleviating the ART category proliferation problem. We refer to the resulting architectures as GFAM, GEAM, and GGAM. We demonstrate through extensive experimentation that evolved ARTMAP architectures exhibit good generalization and are of small size, while consuming reasonable computational effort to produce an optimal or a sub-optimal network. Furthermore, we compare the performance of GFAM, GEAM and GGAM with other competitive ARTMAP structures that have appeared in the literature and addressed the category proliferation problem in ART. © 2007 Springer-Verlag Berlin Heidelberg.
Publication Date
7-9-2007
Publication Title
Studies in Computational Intelligence
Volume
67
Number of Pages
233-262
Document Type
Article
Personal Identifier
scopus
DOI Link
https://doi.org/10.1007/978-3-540-72687-6_12
Copyright Status
Unknown
Socpus ID
34347377134 (Scopus)
Source API URL
https://api.elsevier.com/content/abstract/scopus_id/34347377134
STARS Citation
Al-Daraiseh, Ahmad; Kaylani, Assem; Georgiopoulos, Michael; Mollaghasemi, Mansooreh; and Wu, Annie S., "Genetically Engineered Art Architectures" (2007). Scopus Export 2000s. 6478.
https://stars.library.ucf.edu/scopus2000/6478