Feedforward networks have powerful approximation capabilities without the "explosion of parameters" problem faced by Fourier and polynomial expansions. This paper first introduces feedforward networks and describes their approximation capabilities, then we address several practical issues faced...

This paper presents a feedforward network estimation algorithm that addresses two issues, (i) avoiding local inferior minima to the performance criteria, and (ii) imposing a priori constraints to improve generalization and test economic hypotheses. The algorithm combines methods either...