MATLAB: Sir what is the difference between Artificial neural network and RBF based network????Why RBF network is more suitable for classification than Regular artificial neural network????

Deep Learning Toolbox

Sir what is the difference between Artificial neural network and RBF based network????Why RBF network is more suitable for classification than Regular artificial neural network?????

Best Answer

BOTH are feedforward artificial neural networks.
MLP or MLPNN: Multilayer Perceptron NN uses S-shaped sigmoid functions in the hidden layers
EBF or EBFNN: Elliptical Basis Function NN uses elliptical Gaussian functions in the hidden layers
RBF is a special case of the EBF that uses spherical Gaussian functions in the hidden layers
ALL configurations can be UNIVERSAL APPROXIMATORS with only one hidden layer.
The best one to use for classification depends on the shape of the class boundaries.
Hope this helps.
Thank you for formally accepting my answer
Greg