Title

Similarity-based learning for pattern classification

Authors

Laurene V. Fausett

Document Type

Conference Proceeding

Publication Title

Proceedings of SPIE - the International Society for Optical Engineering

Abstract

Several standard neural networks, including counterpropagation networks, predictive ART networks, and radial basis function networks, are based on a combination of clustering (unsupervised learning) and mapping (supervised learning). A comparison of the characteristics of these networks for pattern classification problems is presented.

First Page

26

Last Page

35

DOI

10.1117/12.235944

Publication Date

3-22-1996

Recommended Citation

Fausett, L. V. (1996). Similarity-based learning for pattern classification. Paper presented at the Proceedings of SPIE - the International Society for Optical Engineering, , 2760 26-35.