In this paper we show that there are some intriguing links between the
Backpropagation and LVQ algorithms. We show that Backpropagation used
for training the weights of radial basis function networks exhibits a
n increasing competitive nature as the dispersion parameters decrease.
In particular, we prove that LVQ can be regarded as a competitive lea
rning scheme taking place in radial basis function networks. (C) 1997
Elsevier Science B.V.