An insight into the standard back-propagation neural network model for regression analysis

This memorandum offers an extension of the work of Chiang et al., (Omega, The International Journal of Management Science, 1996, 24, 205-215) by investigating the issue of the standard backpropagation neural network model for regression analysis. It provides an analytical insight which shows how a regression result based on a simple back-propagation neural network may be adversely affected. It also proposes a general neural-network-based regression model, and demonstrates a practical example, (C) 1998 Elsevier Science Ltd, All rights reserved.