Generalization performance of ARTMAP-based networks in structural risk minimization framework

Stephen J. Verzi, Gregory L. Heileman

Research output: Contribution to conferencePaperpeer-review

2 Scopus citations


Many techniques have been proposed for improving the generalization performance of Fuzzy ARTMAP. We present a study of these architectures in the framework of structural risk minimization and computational learning theory. Fuzzy ARTMAP training uses on-line learning, has proven convergence results, and has relatively few parameters to deal with. Empirical risk minimization is employed by Fuzzy ARTMAP during its training phase. One weakness of Fuzzy ARTMAP concerns over-training on noisy training data sets or naturally overlapping training classes of data. Most of these proposed techniques attempt to address this issue, in different ways, either directly or indirectly. In this paper we will present a summary of how some of these architectures achieve success as learning algorithms.

Original languageEnglish (US)
Number of pages6
StatePublished - 2002
Externally publishedYes
Event2002 International Joint Conference on Neural Networks (IJCNN'02) - Honolulu, HI, United States
Duration: May 12 2002May 17 2002


Conference2002 International Joint Conference on Neural Networks (IJCNN'02)
Country/TerritoryUnited States
CityHonolulu, HI


  • Adaptive resonance theory
  • Classification
  • Empirical and structural risk minimization
  • Generalization performance
  • Machine learning
  • Neural networks

ASJC Scopus subject areas

  • Software
  • Artificial Intelligence


Dive into the research topics of 'Generalization performance of ARTMAP-based networks in structural risk minimization framework'. Together they form a unique fingerprint.

Cite this