Learning Prototype Models for Tangent Distance
暂无分享,去创建一个
Simard, LeCun & Denker (1993) showed that the performance of nearest-neighbor classification schemes for handwritten character recognition can be improved by incorporating invariance to specific transformations in the underlying distance metric - the so called tangent distance. The resulting classifier, however, can be prohibitively slow and memory intensive due to the large amount of prototypes that need to be stored and used in the distance comparisons. In this paper we develop rich models for representing large subsets of the prototypes. These models are either used singly per class, or as basic building blocks in conjunction with the K-means clustering algorithm.
[1] Teuvo Kohonen,et al. Self-Organization and Associative Memory , 1988 .
[2] Teuvo Kohonen,et al. Self-organization and associative memory: 3rd edition , 1989 .
[3] Erkki Oja,et al. Neural Networks, Principal Components, and Subspaces , 1989, Int. J. Neural Syst..
[4] Yann LeCun,et al. Efficient Pattern Recognition Using a New Transformation Distance , 1992, NIPS.
[5] Eric Mjolsness,et al. Clustering with a Domain-Specific Distance Measure , 1993, NIPS.