Title
Genetic Optimization Of Art Neural Network Architectures
Keywords
ARTMAP; Category proliferation; Classification; Genetic algorithms; Genetic operators; Machine learning
Abstract
Adaptive Resonance Theory (ART) neural network architectures, such as Fuzzy ARTMAP (FAM), Ellipsoidal ARTMAP (EAM), and Gaussian ARTMAP (GAM), have solved successfully a variety of classification problems. However, they suffer from an inherent ART problem, that of creating larger architectures than it is necessary to solve the problem at hand (referred to as the ART category proliferation problem). This problem is especially amplified for classification problems which have noisy data, and/or data, belonging to different labels, that significantly overlap. A variety of modified ART architectures, referred to as semi-supervised (ss) ART architectures (e.g., ssFAM, ssEAM, ssGAM), summarily referred to as ssART, have addressed the category proliferation problem. In this paper, we are proposing another approach of solving the ART category proliferation problem, by designing genetically engineered ART architectures, such as GFAM, GEAM, GGAM, summarily referred to as GART. In particular, in this paper, we explain how to design GART architectures and compare their performance (in terms of accuracy, size, and computational complexity) with the performance of the ssART architectures. Our results demonstrate that GART is superior to ssART, and quite often it produces the optimal classifier.
Publication Date
12-1-2007
Publication Title
Proceedings of the 11th IASTED International Conference on Artificial Intelligence and Soft Computing, ASC 2007
Number of Pages
225-230
Document Type
Article; Proceedings Paper
Personal Identifier
scopus
Copyright Status
Unknown
Socpus ID
54949124195 (Scopus)
Source API URL
https://api.elsevier.com/content/abstract/scopus_id/54949124195
STARS Citation
Kaylani, Assem; Georgiopoulos, Michael; Anagnostopoulos, Georgios; and Mollaghasemi, Mansooreh, "Genetic Optimization Of Art Neural Network Architectures" (2007). Scopus Export 2000s. 6053.
https://stars.library.ucf.edu/scopus2000/6053