Conventional time series analysis depends heavily on the twin assumptions of linearity and stationarity. However; there are certain cases where sampled data tend to violate the assumptions. In this paper, we use neural networks technology to explore the situation when the assumptions of linearity and stationarity are failed. At the end of the paper, we discuss an illustrative example about the annual expenditures of government and science-education-culture of R.O.C.

[BART 90] Chance or Chaos? J. R. Statist. Soc. A (1990) 153, Part 3, pp. 321-347
[BOX 76] Box, G. E. P., and Jenkins, G. M., 1976 Time Series Analysis Forecasting and Control. 2nd. ed. San Francisco: Holden-Day.
[CYBE 89] Cybenko, G., 1989 Approximation by superposition of a sigmiodal function, A1athematics of control, signals and systems, 2nd, pp. 303-314.
[FUNA 89] Funahashi, K. I., 1989 On the approximate of continuous mappings by neural networks, Neural Networks, 2nd, pp183-192.
[Geor 90] Nonlinear forecasting as a way of distinguishing chaos from measurement error in time series. Nature Vol. 344 pp. 734-741
[GROS 82] Grosberg, S. 1982 Studies of Mind and Brain: Neural principles of learning, Perception, Development, Cognition and Motor Control. Boston, MA: Reidel.
[GRAN 91] Granger, C.W.J., 1991. Developments in the Nonlinear Analysis of Economic Series, Scand. J. of Economics, 93(2}, pp. 263-276.
[HARV 90] Harvey, A. 1990 The econometrics analysis of time series, 2nd. ed. London: BPCC Wheaton Ltd,.
[HORN 91] Hornik., 1991 Approximation Capabilities of Multi-layer Feedforward Networks, Neural Networks, 4, pp. 251-257.
[KHAN 90] Khanna, TaTun. (1990) Fundations of neural networks, AddisionWesley Inc.
[KOSK 91] Kosko, B. 1991 Neural Networks and Fuzzy system, Prentice Hall ,Englewood Cliffs, NJ.
[KOSK 92] Kosko, B. 1992 Neural Networks for Signal Processing, Prentice Hall , Englewood Cliffs, NJ.
[LAPE 88] Lapedes, A., and Farber, R., 1988 How neural nets work. Theoretical Division Los Alamos National Laboratory Los Alamos, N M87545.
[MEDI91] Medio, A., (1991) Continuous-time Models of Chaos in Economics . J. of Econ. Behavior and Organ. 16} pp. 115-151.
[Prie 88] M. B. Priestley (1988), Non-linear and Non-stationary Time Series Analysis, Academic Press.
[RAME 89] Ramey,J. Neural computing. vol.1. Neural Ware, Inc. Pittsburgh.
[WEI 90] Wei, W. W. S. 1990 Time Serirs Analysis: Unitvariate and Multivariate Methods, Addision-Wesley Inc.
[WU 92] Wu, B. and Chan, D. 1992 Budge-Planning, Forecasting Control of the Taiwan Government expenditure . The National Chengchi University Journal, 64 pp .81-104.