Adaptive learning of rational expectations using neural networks

Abstract This paper investigates how adaptive learning of rational expectations may be modeled with the help of neural networks. Necessary conditions for the convergence of the learning process towards (approximate) rational expectations are derived using a simple nonlinear cobweb model. The results obtained are similar to results obtained within the framework of linear models using recursive least squares learning procedures. In general, however, convergence of a learning process based on a neural network may imply that the resulting expectations are not even local minimizers of the mean-squared prediction error.

[1]  Maik Heinemann,et al.  Modellierung von Preiserwartungen durch neuronale Netze , 1997 .

[2]  R. Radner,et al.  Convergence to rational expectations equilibrium , 1984 .

[3]  Mark Salmon,et al.  Bounded Rationality and Learning: Procedural Learning , 1994 .

[4]  Berndt Müller,et al.  Neural networks: an introduction , 1990 .

[5]  Roman Frydman,et al.  Individual Forecasting and Aggregate Outcomes , 1985 .

[6]  George Cybenko,et al.  Approximation by superpositions of a sigmoidal function , 1989, Math. Control. Signals Syst..

[7]  Christian Gourieroux,et al.  Learning procedure and convergence to rationality , 1986 .

[8]  William A. Barnett,et al.  Equilibrium Theory and Applications , 1991 .

[9]  Mark Salmon,et al.  Learning and Rationality in Economics , 1995 .

[10]  Ken-ichi Funahashi,et al.  On the approximate realization of continuous mappings by neural networks , 1989, Neural Networks.

[11]  T. Sargent.  Bounded rationality in macroeconomics , 1993 .

[12]  Kurt Hornik,et al.  Multilayer feedforward networks are universal approximators , 1989, Neural Networks.

[13]  G. Laroque,et al.  Economic dynamics with learning : some instability examples , 1990 .

[14]  T. Sargent,et al.  Convergence of Least Squares Learning Mechanisms in Self- Referential Linear Stochastic Models* , 1989 .

[15]  H. White.  Some Asymptotic Results for Learning in Single Hidden-Layer Feedforward Network Models , 1989 .

[16]  H. White,et al.  ADAPTIVE LEARNING WITH NONLINEAR DYNAMICS DRIVEN BY DEPENDENT PROCESSES , 1994 .

[17]  Halbert White,et al.  Connectionist nonparametric regression: Multilayer feedforward networks can learn arbitrary mappings , 1990, Neural Networks.

[18]  Tamer Basar,et al.  Analysis of Recursive Stochastic Algorithms , 2001 .

[19]  Halbert White,et al.  Artificial neural networks: an econometric perspective ∗ , 1994 .

[20]  M. Bray,et al.  Rational Expectations Equilibria, Learning, and Model Specification , 1986 .

[21]  Xiaohong Chen,et al.  Nonparametric Adaptive Learning with Feedback , 1998 .

[22]  M. Hirsch,et al.  Differential Equations, Dynamical Systems, and Linear Algebra , 1974 .