Exploring margin setting for good generalization in multiple class discrimination. (English) Zbl 1079.68602
Summary: 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.
MSC:
| 68T10 | Pattern recognition, speech recognition |
References:
| [1] | Burges, C. J.C., A Tutorial on Support Vector Machines for Pattern Recognition (1998), Kluwer Academic Publishers: Kluwer Academic Publishers Dordrecht |
| [2] | Valiant, L. G., A theory of learnability, Commun. ACM, 27, 1134-1142 (1984) · Zbl 0587.68077 |
| [3] | Schapire, R. E., The strength of weak learnability, Mach. Learn., 5, 2, 197-227 (1990) |
| [4] | Caulfield, H. J., Independent task Fourier filters, Opt. Eng., 40, 2414-2418 (2001) |
| [5] | Caulfield, H. J.; Karavolos, A.; Ludman, J. E., Improving optical Fourier pattern recognition by accommodating the missing information, Inf. Sci., 162, 1, 35-52 (2004) · Zbl 1074.68598 |
| [6] | H.J. Caulfield, Generalization in heteroassociative neural networks, Neural Comput. (2003), submitted for publication.; H.J. Caulfield, Generalization in heteroassociative neural networks, Neural Comput. (2003), submitted for publication. |
| [7] | R.A. Fisher, The use of multiple measurements in taxonomic problems, Ann. Eugen. (1936) 179-188.; R.A. Fisher, The use of multiple measurements in taxonomic problems, Ann. Eugen. (1936) 179-188. |
| [8] | Domeniconi, C.; Peng, J.; Gunopulos, D., Locally adaptive metric nearest-neighbor classification, IEEE Trans. Pattern Recogn. Mach. Intell., 24, 9, 1281-1285 (2002) |
This reference list is based on information provided by the publisher or from digital mathematics libraries. Its items are heuristically matched to zbMATH identifiers and may contain data conversion errors. In some cases that data have been complemented/enhanced by data from zbMATH Open. This attempts to reflect the references listed in the original paper as accurately as possible without claiming completeness or a perfect matching.
