| 对复杂混沌时间序列快速预测的前馈神经网络 |
| |
| 引用本文： | 顾炜,瞿东辉.对复杂混沌时间序列快速预测的前馈神经网络[J].复旦学报(自然科学版),1995,34(3):262-268. |
| |
| 作者姓名： | 顾炜 瞿东辉 |
| |
| 作者单位： | 复旦大学电子工程系 |
| |
| 基金项目： | 国家攀登计划认知科学（神经网络）重大关键项目,上海市科委重点基金 |
| |
| 摘 要： | 提出了一种基于前馈神经网络结构的适合于非线性预测的在线学习方法，这种方法吸收了最小二乘法和传统在线ＢＰ算法的优点，具有收敛速度快，跟踪性能好、适用于非线性预测等特点。
|
| 关 键 词： | 时间序列 预测 ARMA模型 浑沌 神经网络 |
A neural network for fast prediction of chaotic the series |
| |
| Gu Wei, Qu Donghui, Zhang Liming.A neural network for fast prediction of chaotic the series[J].Journal of Fudan University(Natural Science),1995,34(3):262-268. |
| |
| Authors: | Gu Wei Qu Donghui Zhang Liming |
| |
| Institution: | Department of Electronic Engineering |
| |
| Abstract: | In this paper a real-time non-linear predictive algorithm based on feed-forward neural network was proposed. This method combines the advantages of both least square and Bp algorithm, so it has fast convergent speed and perfect trace performance.Specially, it is suitable for complex non-linear prediction. Some chaotic time series, such as Logistic mapping, Henon equation and EEG signal, were predicted by the proposed algorithm. The simulation results showed the good properties of the method. |
| |
| Keywords: | on-line algorithm ARMA(autoregressive moving average)model chaos |
| 本文献已被 CNKI 维普 等数据库收录！ |
