The performance of a classical linear vector predictor is limited by i
ts ability to exploit only the linear correlation between the blocks.
However, a nonlinear predictor exploits the higher order correlations
among the neighboring blocks, and can predict edge blocks,vith increas
ed accuracy. In this paper, we have investigated several neural networ
k architectures that can be used to implement a nonlinear vector predi
ctor, including the multilayer perceptron (MLP), the functional link (
FL) network, and the radial basis function (RBF) network. Our experime
ntal results show that a neural network predictor can predict the bloc
ks containing edges with a higher accuracy than a Linear predictor.