Exploring margin setting for good generalization in multiple class discrimination

Authors:
H. John Caulfield;Kaveh Heidary
Affiliations:
Alabama A&M University Research Institute, PO Box 313, Normal, AL 35762, USA;Department of Electrical Engineering, Alabama A&M University, PO Box 702, Normal, AL 35762, USA
Venue:
Pattern Recognition
Year:
2005

Citing 4
Cited 4

A theory of the learnable

Communications of the ACM
The Strength of Weak Learnability

Machine Learning
Locally Adaptive Metric Nearest-Neighbor Classification

IEEE Transactions on Pattern Analysis and Machine Intelligence
Improving optical Fourier pattern recognition by accommodating the missing information

Information Sciences: an International Journal - Special issue: Optics and information sciences

Use of Artificial Color filtering to improve iris recognition and searching

Pattern Recognition Letters
Designing spectral sensitivity curves for use with Artificial Color

Pattern Recognition
Making a smarter color camera

Image and Vision Computing
Presmoothing effects in Artificial Color image segmentation

Computer Vision and Image Understanding

Quantified Score

Hi-index	0.01

Visualization

Abstract

In earlier publications, we showed that it is possible to achieve both low VC dimension and high accuracy, if we divide the given training set into a sequence of subsets each of which does admit such a solution. Here we explore in substantially more detail how the various steps in what was called ''Margin Setting'' impact false classification and indecision rates. A complex relationship exists between margin size, the number of steps in the process, and those two classification failures. After mapping those relationships, we offer a qualitative explanation of them.