Title :
Minimal distance neural methods
Author :
W. Dich;K. Grudzinski;G.H.F. Diercksen
Author_Institution :
Dept. of Comput. Methods, Nicholas Copernicus Univ., Torun, Poland
Abstract :
A general framework for minimal distance methods is presented. Radial basis functions (RBFs) and multilayer perceptrons (MLPs) neural networks are included in this framework as special cases. New versions of minimal distance methods are formulated. A few of them have been tested on real-world datasets obtaining very encouraging results.
Keywords :
"Nearest neighbor searches","Testing","Learning","Astrophysics","Multilayer perceptrons","Neural networks","Multi-layer neural network","Large-scale systems","Classification algorithms","Pattern recognition"
Conference_Titel :
Neural Networks Proceedings, 1998. IEEE World Congress on Computational Intelligence. The 1998 IEEE International Joint Conference on
Print_ISBN :
0-7803-4859-1
DOI :
10.1109/IJCNN.1998.685962
