International Conference on Neural Networks andâ€¦

2003

This paper utilizes a discrete wavelet transform to present a parallel architecture for independent component analysis (ICA), which is a hybrid system consisting of two sub-ICA processes. One process takes the high-frequency wavelet part of observations as its input, meanwhile the other process takes the low-frequency part. Their results are then merged toâ€¦ (More)

This paper presents a new divide-and-conquer based learning approach to radial basis function (RBF) networks, in which a conventional RBF network is divided into several RBF sub-networks. Each of them individually takes an input sub-space as its input. The original networkâ€™s output then becomes a linear combination of the sub-networksâ€™ outputs with theâ€¦ (More)

This paper experimentally investigates Independent Component Analysis (ICA) and Principle Component Analysis (PCA) on reducing the input dimension of a Radial Basis Function (RBF) network such that the netâ€™s complexity is reduced. The results have shown that a RBF network with ICA as an input pre-process has the similar generalization ability to the oneâ€¦ (More)

Our recent paper (Huang et al. 2002) has presented a divideand-conquer based radial basis function network (DCRBF) that is a hybrid system consisting of several sub-RBF networks, each of which individually takes a sub-input space as its input. Since this system reduces the structural complexity of a RBF network by mapping a highdimensional modelling problemâ€¦ (More)