论文信息 - Measuring the VC-Dimension of a Learning Machine

Measuring the VC-Dimension of a Learning Machine

A method for measuring the capacity of learning machines is described. The method is based on fitting a theoretically derived function to empirical measurements of the maximal difference between the error rates on two separate data sets of varying sizes. Experimental measurements of the capacity of various types of linear classifiers are presented.

[1] Vladimir Vapnik,et al. Chervonenkis: On the uniform convergence of relative frequencies of events to their probabilities , 1971 .

[2] L. Devroye. Bounds for the Uniform Deviation of Empirical Measures , 1982 .

[3] David Haussler,et al. What Size Net Gives Valid Generalization? , 1989, Neural Computation.

[4] V. Rich. Personal communication , 1989, Nature.

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

[6] David E. Rumelhart,et al. Generalization by Weight-Elimination with Application to Forecasting , 1990, NIPS.

[7] Isabelle Guyon,et al. Structural Risk Minimization for Character Recognition , 1991, NIPS.

[8] Yaser S. Abu-Mostafa,et al. Hints and the VC Dimension , 1993, Neural Computation.