Abstract
In our research we are interested in bounding the performance of Fuzzy ARTMAP and other ART-based neural network architectures, such as Boosted ARTMAP, according to the theory of Structural Risk Minimization. Structural risk minimization research indicates a trade-off between training error and hypothesis complexity. This trade-off directly motivated Boosted ARTMAP. In this paper, we present empirical evidence for Boosted ARTMAP as a viable learning technique, in general, in comparison to Fuzzy ARTMAP and other ART-based neural network architectures. We also show direct empirical evidence for decreased hypothesis complexity in conjunction with improved empirical performance for Boosted ARTMAP as compared with Fuzzy ARTMAP. Application of the Rademacher penalty to Boosted ARTMAP on a specific learning problem further indicates its utility as compared with Fuzzy ARTMAP.
Original language | English (US) |
---|---|
Pages | 1191-1196 |
Number of pages | 6 |
State | Published - 2001 |
Externally published | Yes |
Event | International Joint Conference on Neural Networks (IJCNN'01) - Washington, DC, United States Duration: Jul 15 2001 → Jul 19 2001 |
Conference
Conference | International Joint Conference on Neural Networks (IJCNN'01) |
---|---|
Country/Territory | United States |
City | Washington, DC |
Period | 7/15/01 → 7/19/01 |
ASJC Scopus subject areas
- Software
- Artificial Intelligence