Wavelet Packet Multi-layer Perceptron for Chaotic Time Series Prediction: Effects of Weight Initialization
Wavelet Packet Multi-layer Perceptron for Chaotic Time Series Prediction: Effects of Weight Initialization
复制标题
DOI：
10.1007/3-540-45718-6_35
复制
发表时间：
2001-05
期刊：
影响因子：
--
通讯作者：
Kok Keong Teo;Lipo Wang;Zhiping Lin
中科院分区：
文献类型：
--
作者：
Kok Keong Teo;Lipo Wang;Zhiping Lin
采用反向传播方法训练小波包多层感知器神经网络（WP-MLP）进行时间序列预测。反向传播算法中的权值通常用小的随机值初始化。如果随机初始权值离较好的解很远，或者接近较差的局部最优解，则训练可能需要很长时间或陷入局部最优。适当的权值初始化将使权值接近一个好的解，同时减少训练时间，增加获得一个好的解的可能性。本文利用两种聚类算法研究了权值初始化对WP-MLP的影响。我们用太阳黑子和Mackey-Glass基准时间序列对WP-MLP的初始化方法进行了测试。结果表明，通过适当的权值初始化，可以获得更好的预测性能。
We train the wavelet packet multi-layer perceptron neural network (WP-MLP) by backpropagation for time series prediction. Weights in the backpropagation algorithm are usually initialized with small random values. If the random initial weights happen to be far from a good solution or they are near a poor local optimum, training may take a long time or get trap in the local optimum. Proper weights initialization will place the weights close to a good solution with reduced training time and increased the possibility of reaching a good solution. In this paper, we investigate the effect of weight initialization on WP-MLP using two clustering algorithms. We test the initialization methods on WP-MLP with the sunspots and Mackey-Glass benchmark time series. We show that with proper weight initialization, better prediction performance can be attained.