Study On Linear Time-Series Forecasting Based On Neural Networks Theory

Feedforward neural networks theory has been proved to be an important and useful theory algorithm. The natural tightly connection between neural networks and time series forms into a new subjective model and prediction. Time series analysis based on neural networks theory cross through traditional frame of subjective model draw out prediction on the inner rules of linear time series data. In this article, We examine the capability of neural networks for linear time-series forecasting. Using both simulated and real data, the effects of neural network factors such as the number of input nodes and the number of hidden nodes as well as the training sample size are investigated. Results show that neural networks are quite competent in modeling and forecasting linear time series in a variety of situations and neural networks are better than the traditional forecasting models for linear data with noise when the linear system with noise. according to the principle of simple, simple neural networks are often effective in modeling and forecasting linear time series.The purpose of this paper is to investigate the effectiveness of neural networks for linear time-series analysis and forecasting. First, a variety of methods of describing and predicting time series are reviewed. Second, Feed forward neural networks which have received so much attention in recent literature are discussed in some detail, in terms of how they represent and learn to represent functional relationship and give a example; Finally, We designed a pseudo experiment to talk about the linear time series analysis based on neural networks theory.If neural networks can compete with traditional forecasting models for linear data with noise, they can be used in even broader situations for forecasting researchers and practitioners.