Title :
On new RBF-like classifier
Author :
Wojnarski, Marcin
Author_Institution :
Inst. of Comput. Sci., Jagiellonian Univ., Krakow, Poland
fDate :
6/24/1905 12:00:00 AM
Abstract :
This paper presents a new neural network for solving classification problems - a local transfer function classifier (LTF-C). It has a similar architecture as the radial basis function neural network (RBF), but utilizes different training algorithms, including not only changing positions and sizes of reception fields, but also inserting and removing neurons during the training
Keywords :
handwritten character recognition; learning (artificial intelligence); pattern classification; radial basis function networks; transfer functions; handwritten character recognition; learning algorithm; local transfer function classifier; network architecture; pattern classification; radial basis function neural network; reception fields; training set; Character recognition; Computer architecture; Computer science; Filling; Handwriting recognition; Neural networks; Neurons; Radial basis function networks; Shape; Transfer functions;
Conference_Titel :
Neural Networks, 2002. IJCNN '02. Proceedings of the 2002 International Joint Conference on
Conference_Location :
Honolulu, HI
Print_ISBN :
0-7803-7278-6
DOI :
10.1109/IJCNN.2002.1005591
