The authors study the performance of feedforward artificial neural networks in forecasting future values of several different time series. They explore both short- and long-term prediction of several periodic time series. They find that a significant source of error in long-term prediction of time series is introduced by a phase shift between the network output and the time series. They explore the origin of this phase shift and suggest strategies for minimizing its effect. They find that the phase diagrams of the time series and the neural network forecast contain useful diagnostic information.

The United States is emerging from the Cold War era into an exciting, but challenging future. Improving the economic competitiveness of our Nation is essential both for improving the quality of life in the United States and maintaining a strong national security. The research and technical skills used to maintain a leading edge in defense and energy now should be used to help meet the challenge of maintaining, regaining, and establishing US leadership in industrial technologies. Companies recognize that success in the world marketplace depends on products that are at the leading edge of technology, with competitive cost, quality, and performance. Los Alamos National Laboratory and its Industrial Partnership Center (IPC) has the strategic goal to make a strong contribution to the nation`s economic competitiveness by leveraging the government`s investment at the Laboratory: personnel, infrastructure, and technological expertise.