In this paper, a wavelet-based neural network is described. The struct
ure of this network is similar to that of the radial basis function (R
BP) network, except that here the radial basis functions are replaced
by orthonormal scaling functions that are not necessarily radial symme
tric. The efficacy of this type of network in function learning and es
timation is demonstrated through theoretical analysis and experimental
results. In particular, it has been shown that the wavelet network ha
s universal and L(2) approximation properties and is a consistent func
tion estimator. Convergence rates associated with these properties are
obtained for certain function classes where the rates avoid the ''cur
se of dimensionality.'' In the experiments, the wavelet network perfor
med well and compared favorably to the MLP and RBF networks.