论文信息 - Characterising complexity by the degrees of freedom in a radial basis function network

Characterising complexity by the degrees of freedom in a radial basis function network

Abstract In this paper we discuss an approach for characterising the complexity of a radial basis function network by estimating its effective degrees of freedom. We introduce a simple method for determining the degrees of freedom by exploiting a relationship to the theory of linear smoothers. Specifically, the complexity of the model is demonstrated theoretically and empirically to be determined by a spectral analysis of the space spanned by the outputs of the hidden layer.

David Lowe | D. Lowe

[1] G. P. King,et al. Extracting qualitative dynamics from experimental data , 1986 .

[2] Neep Hazarika,et al. Iterative time series prediction and analysis by embedding and multiple time-scale decomposition networks , 1997, Defense, Security, and Sensing.

[3] G. Wahba. Spline models for observational data , 1990 .

[4] Peter Grant,et al. Orthogonal least squares algorithms for training multi-output radial basis function networks , 1991 .

[5] Tomaso A. Poggio,et al. Regularization Theory and Neural Networks Architectures , 1995, Neural Computation.

[6] David Lowe,et al. The optimised internal representation of multilayer classifier networks performs nonlinear discriminant analysis , 1990, Neural Networks.

[7] R. Tibshirani,et al. Generalized additive models for medical research , 1986, Statistical methods in medical research.