论文信息 - Complexity measures for classes of neural networks with variable weight bounds

Complexity measures for classes of neural networks with variable weight bounds

The author derives complexity measures for classes of single-hidden-layer feedforward networks based on the capacity and metric entropy of a class of functions. Based on these measures, some deficiencies in commonly used complexity-penalty terms implemented to prevent overfitting are indicated.<<ETX>>

W. Finnoff

[1] D. Pollard. Convergence of stochastic processes , 1984 .

[2] R. Dudley. A course on empirical processes , 1984 .

[3] Michael C. Mozer,et al. Skeletonization: A Technique for Trimming the Fat from a Network via Relevance Assessment , 1988, NIPS.

[4] M. C. Jones,et al. Spline Smoothing and Nonparametric Regression. , 1989 .

[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.