Learning to Compare using Operator-Valued Large-Margin Classifiers
Feb 25, 2007 3513 views 
en
0.25
0.5
0.75
1.25
1.5
1.75
2
The proposed method uses homonymous and heteronymous examplepairs to train a linear preprocessor on a kernel-induced Hilbert space. The algorithm seeks to optimize the expected performance of elementary classifiers to be generated from single future training examples. The method is justified by PAC-style generalization guarantees and the resulting algorithm has been tested on problems of geometrically invariant pattern recognition and face verification.