论文信息 - Structural Risk Minimization for Character Recognition

Structural Risk Minimization for Character Recognition

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.

[1] Richard O. Duda,et al. Pattern classification and scene analysis , 1974, A Wiley-Interscience publication.

[2] Y. Le Cun,et al. Comparing different neural network architectures for classifying handwritten digits , 1989, International 1989 Joint Conference on Neural Networks.

[3] C. W. Therrien,et al. Decision, Estimation and Classification: An Introduction to Pattern Recognition and Related Topics , 1989 .

[4] Lawrence D. Jackel,et al. Backpropagation Applied to Handwritten Zip Code Recognition , 1989, Neural Computation.

[5] Yann LeCun,et al. Optimal Brain Damage , 1989, NIPS.

[6] Vladimir Vapnik,et al. Principles of Risk Minimization for Learning Theory , 1991, NIPS.

[7] Isabelle Guyon,et al. Design of a neural network character recognizer for a touch terminal , 1991, Pattern Recognit..

[8] D. Mackay,et al. A Practical Bayesian Framework for Backprop Networks , 1991 .