Rademacher penalization applied to Fuzzy ARTMAP and Boosted ARTMAP

S. J. Verzi; G. L. Heileman; M. Georgiopoulos; M. J. Healy

Rademacher penalization applied to Fuzzy ARTMAP and Boosted ARTMAP

S. J. Verzi, G. L. Heileman, M. Georgiopoulos, M. J. Healy

Research output: Contribution to conference › Paper › peer-review

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

Cite this

@conference{c0def5b0c25b4315b7df2686fb3351d5,

title = "Rademacher penalization applied to Fuzzy ARTMAP and Boosted ARTMAP",

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.",

author = "Verzi, {S. J.} and Heileman, {G. L.} and M. Georgiopoulos and Healy, {M. J.}",

year = "2001",

language = "English (US)",

pages = "1191--1196",

note = "International Joint Conference on Neural Networks (IJCNN'01) ; Conference date: 15-07-2001 Through 19-07-2001",

}

TY - CONF

T1 - Rademacher penalization applied to Fuzzy ARTMAP and Boosted ARTMAP

AU - Verzi, S. J.

AU - Heileman, G. L.

AU - Georgiopoulos, M.

AU - Healy, M. J.

PY - 2001

Y1 - 2001

N2 - 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.

AB - 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.

UR - http://www.scopus.com/inward/record.url?scp=0034869346&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0034869346&partnerID=8YFLogxK

M3 - Paper

AN - SCOPUS:0034869346

SP - 1191

EP - 1196

T2 - International Joint Conference on Neural Networks (IJCNN'01)

Y2 - 15 July 2001 through 19 July 2001

ER -

Rademacher penalization applied to Fuzzy ARTMAP and Boosted ARTMAP

Abstract

Conference

ASJC Scopus subject areas

Other files and links

Fingerprint

Cite this