Title :
Kernel-based topographic map formation achieved with normalized Gaussian competition
Author :
Van Hulle, Marc M.
Author_Institution :
Laboratorium voor Neuro- en Psychofysiologie, Katholieke Univ., Leuven, Belgium
Abstract :
A new learning algorithm for kernel-based topographic map formation is introduced. The kernels are Gaussians, and their centers and ranges individually adapted so as to yield an equiprobabilistic topographic map. The converged map also generates a heteroscedastic Gaussian mixture model of the input density. This is verified for both synthetic and real-world examples, and compared with other algorithms for kernel-based topographic map formation.
Keywords :
Gaussian distribution; neural nets; unsupervised learning; converged map; equiprobabilistic topographic map; heteroscedastic Gaussian mixture model; input density; kernel-based topographic map formation; learning algorithm; neural network; normalized Gaussian competition; unsupervised competitive learning; Clustering algorithms; Entropy; Kernel; Laboratories; Lattices; Marine vehicles; Maximum likelihood estimation; Neural networks; Neurons; Psychology;
Conference_Titel :
Neural Networks for Signal Processing, 2002. Proceedings of the 2002 12th IEEE Workshop on
Print_ISBN :
0-7803-7616-1
DOI :
10.1109/NNSP.2002.1030028
