A re-weighting strategy for improving margins

Artificial Intelligence

Volumn 137, Issue 1-2, 2002, Pages 197-216

  Aiolli, Fabio ^a   Sperduti, Alessandro ^a  

^a UNIVERSITY OF PISA   (Italy)

Author keywords

Invariant pattern recognition; Learning Vector Quantization; Machine learning; Margins; Multi class classification; Nearest Neighbor; Re weighting; Tangent distance

Indexed keywords

ALGORITHMS; MATHEMATICAL MODELS; VECTOR QUANTIZATION; VECTORS;

RE-WEIGHTING STRATEGY;

PATTERN RECOGNITION;

EID: 0036567291     PISSN: 00043702     EISSN: None     Source Type: Journal    
DOI: 10.1016/S0004-3702(02)00122-4     Document Type: Article

References (16)

1. The sample complexity of pattern classification with neural networks: The size of the weights is more important than the size of the network
2. Learning prototype models for tangent distance
3. Modeling the manifold of images of handwritten digits
4. Theoretical views of boosting
5. Boosting the margin: A new explanation for the effectiveness of voting methods
6. Learning discriminant tangent models for handwritten character recognition
7. Transformation invariant autoassociation with application to handwritten character recognition
8. Efficient pattern recognition using a new transformation distance
9. Efficient computation of complex distance metrics using hierarchical filtering
10. A constructive learning algorithm for discriminant tangent models
11. Discriminant pattern recognition using transformation invariant neurons
12. A rapid graph-based method for arbitrary transformation-invariant pattern classification