Abstract

The method of Structural Risk Minimization refers to tuning the capacity of the classifier to the available amount of training data. This capacity is influenced by several factors, including: (1) properties of the input space, (2) nature and structure of the classifier, and (3) learning algorithm. Actions based on these three factors are combined here to control the capacity of linear classifiers and improve generalization on the problem of handwritten digit recognition.

Keywords

Classifier (UML)MinificationComputer scienceStructural risk minimizationCharacter recognitionArtificial intelligencePattern recognition (psychology)Machine learningGeneralizationDigit recognitionTraining setMathematicsArtificial neural network

Affiliated Institutions

Related Publications

Perfect metrics

Tuyen Ho Thi Thanh , Henry S. Baird

The authors describe an experiment in the construction of perfect metrics for minimum-distance classification of character images. A perfect metric is one that, with high probab...

2002 17 citations

Publication Info

Year
1991
Type
article
Volume
4
Pages
471-479
Citations
102
Access
Closed

External Links

Citation Metrics

102
OpenAlex

Cite This

Isabelle Guyon, Vladimir Vapnik, Bernhard E. Boser et al. (1991). Structural Risk Minimization for Character Recognition. Neural Information Processing Systems , 4 , 471-479.