Time Series Analysis and Forcast Based on Active Learning Artificial Neural Network
Tongzhi He, Shijue Zheng · 2009
As is known to all, the neutral network has made a great progress in many fields. But due to some strict theoretical system, there are still many defaults in practical application. In this paper, we present an active learning artificial neural network (ALANN). The key issue of this kind of approach is what information can be analysis and forecast about time series(TS). However, the parameters of ALANN need to be adjusted for optimal performance. This point is just what this paper explain about. It overcomes the conventional method defaults, such as slow convergence, local minimum. The good result of the algorithm makes it can be used in the changing of temperature, the trends of population, etc.