Title :
Feedforward neural networks with sigmoidal and radial basis functions hidden neurons
Author :
Valova, Iren ; Gueorguieva, N. ; Kempka, Matthias
Author_Institution :
Comput. & Inf. Sci., Massachusetts Univ., North Dartmouth, MA, USA
Abstract :
This discussion paper concentrates on a possible combination of different activation functions in the multilayered perceptron (MLP) for classification tasks. The activation functions, which are combined are the sigmoidal and the radial basis function. We propose this approach to modification of MLP as solutions to some of the shortfalls of this network.
Keywords :
benchmark testing; multilayer perceptrons; radial basis function networks; transfer functions; activation functions; benchmark tests; feedforward neural networks; intertwined spiral problem; multilayered perceptron; radial basis function neural networks; sigmoidal hidden neurons; Computer networks; Computer science; Convergence; Educational institutions; Feedforward neural networks; Feedforward systems; Multilayer perceptrons; Neural networks; Neurons; Testing;
Conference_Titel :
Systems, Man and Cybernetics, 2003. IEEE International Conference on
Print_ISBN :
0-7803-7952-7
DOI :
10.1109/ICSMC.2003.1244646