Structural Risk Minimization for Character Recognition
Isabelle Guyon, Vladimir N. Vapnik, Bernhard E. Boser et al. · neural information processing systems · 1991
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.
Cited by 101 works.
Authors
References
- Pattern classification and scene analysis
- Backpropagation Applied to Handwritten Zip Code Recognition
- Estimation of Dependences Based on Empirical Data
- Optimal Brain Damage
- On optimal nonlinear associative recall
- Design of a neural network character recognizer for a touch terminal
- Comparing different neural network architectures for classifying handwritten digits
- Decision, estimation, and classification: an introduction to pattern recognition and related topics
- Principles of Risk Minimization for Learning Theory