论文信息 - Elliptical Basis Function Networks for Classification Tasks

Elliptical Basis Function Networks for Classification Tasks

In this paper we compare variants of elliptical basis function networks for classification tasks. The networks are introduced as density estimators and then modified towards RBF networks. Node reduction is accomplished by a genetic algorithm(GA). Two different kinds of node connections are compared. As a second degree of freedom different types of basis functions are investigated. On an artificial test set of the time series domain the impact of dimensionality is considered.

Steffen Gutjahr | Joachim Feist | S. Gutjahr | J. Feist

[1] Mark A. Kramer,et al. Probability density estimation using elliptical basis functions , 1994 .

[2] Mohamad T. Musavi,et al. On the training of radial basis function classifiers , 1992, Neural Networks.

[3] J. Simonoff. Multivariate Density Estimation , 1996 .

[4] David J. Spiegelhalter,et al. Machine Learning, Neural and Statistical Classification , 2009 .

[5] Mohamad T. Musavi,et al. A minimum error neural network (MNN) , 1993, Neural Networks.

[6] Donald F. Specht,et al. Probabilistic neural networks , 1990, Neural Networks.

[7] Richard Lippmann,et al. Neural Network Classifiers Estimate Bayesian a posteriori Probabilities , 1991, Neural Computation.

[8] E. Parzen. On Estimation of a Probability Density Function and Mode , 1962 .

[9] D. Lowe. On the use of nonlocal and nonpositive definite basis functions in radial basis function networks , 1995 .

[10] Timothy Masters,et al. Practical neural network recipes in C , 1993 .