Artificial Neural Networks
Artificial neural networks (ANNs) constitute a class of flexible nonlinear models designed to mimic biological neural systems. In this article we introduce ANN using familiar econometric terminology and provide an overview of the ANN modelling approach and its implementation methods.
KeywordsARMA models Artificial neural networks Back propagation algorithm BAYESIAN information criterion Distributed lags Feedforward neural networks Learning Model misspecification Newton algorithm Nonlinear least squares (NLS) method Nonlinear models Nonparametric functional analysis Nonparametric methods Predictive stochastic complexity Recurrent neural networks Stochastic approximation method
I would like to express my sincere gratitude to Steven Durlauf for his patience and constructive comments on early drafts of this article. I also thank Shih-Hsun Hsu and Yu-Lieh Huang for very helpful suggestions. The remaining errors are all mine.
- Barron, A. 1991. Complexity regularization with application to artificial neural networks. In Nonparametric functional estimation and related topics, ed. G. Roussas. Dordrecht: Kluwer Academic Publishers.Google Scholar
- Gallant, A., and H. White. 1988. A unified theory of estimation and inference for nonlinear dynamic models. Oxford: Basil Blackwell.Google Scholar
- Jordan, M. 1986. Serial order: A parallel distributed processing approach, Report No. 8604. La Jolla: Institute for Cognitive Science, University of California San Diego.Google Scholar
- McClelland, J.,D. Rumelhart, and the PDP Research Group. 1986. Parallel distributed processing: Explorations in the microstructure of cognition, vol. 2. Cambridge, MA: MIT Press.Google Scholar
- Rissanen, J. 1987. Stochastic complexity (with discussions). Journal of the Royal Statistical Society, B 49(223–39): 252–265.Google Scholar
- Rumelhart, D., G. Hinton, and R. Williams. 1986a. Learning internal representation by error propagation. In Parallel distributed processing: Explorations in the microstructure of cognition, vol. 1, ed. D. Rumelhart, J. McClelland and the PDP Research Group. Cambridge, MA: MIT Press.Google Scholar
- Rumelhart, D., J. McClelland, and the PDP Research Group, eds. 1986b. Parallel distributed processing: Explorations in the microstructure of cognition, vol. 1. Cambridge, MA: MIT Press.Google Scholar
- White, H. 1988. Economic prediction using neural networks: The case of IBM stock prices.In: Proceedings of the second annual IEEE conference on neural networks II. New York: IEEE Press.Google Scholar