Sciweavers

Share
TNN
2010

An adaptive multiobjective approach to evolving ART architectures

8 years 8 months ago
An adaptive multiobjective approach to evolving ART architectures
In this paper, we present the evolution of adaptive resonance theory (ART) neural network architectures (classifiers) using a multiobjective optimization approach. In particular, we propose the use of a multiobjective evolutionary approach to simultaneously evolve the weights and the topology of three well-known ART architectures; fuzzy ARTMAP (FAM), ellipsoidal ARTMAP (EAM), and Gaussian ARTMAP (GAM). We refer to the resulting architectures as MO-GFAM, MO-GEAM, and MO-GGAM, and collectively as MO-GART. The major advantage of MO-GART is that it produces a number of solutions for the classification problem at hand that have different levels of merit [accuracy on unseen data (generalization) and size (number of categories created)]. MO-GART is shown to be more elegant (does not require user intervention to define the network parameters), more effective (of better accuracy and smaller size), and more efficient (faster to produce the solution networks) than other ART neural network archite...
Assem Kaylani, Michael Georgiopoulos, Mansooreh Mo
Added 22 May 2011
Updated 22 May 2011
Type Journal
Year 2010
Where TNN
Authors Assem Kaylani, Michael Georgiopoulos, Mansooreh Mollaghasemi, Georgios C. Anagnostopoulos, Christopher Sentelle, Mingyu Zhong
Comments (0)
books