基于去趋势多重互相关的深度回声状态网络剪枝算法  

Deep Echo State Network Pruning Algorithm Based on Detrended Multiple Cross-correlation

作　　者：孙晓川 王宇 李莹琦 黄天宇 SUN Xiaochuan;WANG Yu;LI Yingqi;HUANG Tianyu(College of Artificial Intelligence,North China University of Science and Technology,Tangshan 063210,China;Hebei Provincial Key Laboratory of Industrial Intelligent Perception,Tangshan 063210,China)

机构地区：[1]华北理工大学人工智能学院,河北唐山063210 [2]河北省工业智能感知重点实验室,河北唐山063210

出　　处：《郑州大学学报（工学版）》2024年第4期38-45,共8页Journal of Zhengzhou University（Engineering Science）

基　　金：河北省海洋生态修复与智慧海洋工程研究中心开放基金项目(HBMESO2315)。

摘　　要：针对储备池中存在的冗余结构导致深度回声状态网络预测精度不佳的问题,提出了一种基于去趋势多重互相关的深度回声状态网络剪枝算法。首先,根据去趋势协方差函数和去趋势方差函数,依次计算所选储备池中每2个神经元之间的去趋势互相关系数,构建去趋势互相关矩阵,基于该矩阵评估该储备池中所选神经元与所有剩余神经元之间的去趋势多重互相关性。其次,依次删除每个储备池中高相关性神经元到输出层的连接,从而去除网络中的冗余结构。最后,通过最小二乘回归重新训练剪枝后的网络,以获得最优的深度回声状态网络拓扑结构。仿真结果表明:经过所提算法优化后的深度回声状态网络在Mackey-Glass时间序列上的预测精度和记忆能力分别提高了89.80%和30.93%,在Call时间序列上的预测精度和记忆能力分别提高了14.34%和0.10%。To address the problem of undesirable prediction accuracy of a deep echo state network caused by redun-dant structures in the reservoirs,a pruning algorithm for the deep echo state network based on detrended multiple cross-correlation was proposed.Firstly,according to the detrended covariance function and the detrended variance function,the detrended cross-correlation coefficient between each two neurons in the selected reservoirs in turn was calculated,and the detrended cross-correlation matrix was constructed.Based on this matrix,the detrended multi-ple cross-correlation between a selected neuron and all remaining neurons in this reservoir could be evaluated.Sub-sequently,the connections from the highly correlated neurons in each reservoir to the output layer were pruned se-quentially,thus removing redundant components in the network.Finally,the network after pruning was retrained by least squares regression to obtain the optimal deep echo state network topology.Simulation results showed that the prediction accuracy and memory capacity of the deep echo state network optimized by the proposed algorithm on Mackey-Glass time series were improved by 89.80%and 30.93%,respectively,and on Call time series by 14.34%and 0.10%,respectively.

关 键 词：深度回声状态网络 结构优化 剪枝 去趋势多重互相关 时间序列预测 

分 类 号：TP183[自动化与计算机技术—控制理论与控制工程]