Adaptive learning of rational expectations using neural networks

This paper investigates how adaptive learning of rational expectations may be modeled with the help of neural networks. Necessary conditions for the c onvergence of the learning process towards (approximate) rational expectati ons are derived using a simple nonlinear cobweb model. The results obtained are similar to results obtained within the framework of linear models usin g recursive least squares learning procedures. In general, however, converg ence of a learning process based on a neural network may imply that the res ulting expectations are not even local minimizers of the mean-squared predi ction error. (C) 2000 Elsevier Science B.V. All rights reserved. JEL classi fication. C 45; D 83.