控制理论与应用2024，Vol.41Issue(3)：385-395,11.DOI:10.7641/CTA.2023.20539
具有双储层结构的动态误差补偿回声状态网络
A new echo state network with a double reservoir compensates for dynamic error
摘要
Abstract
The traditional echo state network is challenging to deal with the high-order nonlinear complex model effec-tively.We proposed an error trace reservoir computing and designed the optimal network algorithm.This new reservoir computing structure consists of a computing layer and a compensation layer.The computing layer mainly undertakes the fitting task,and the compensation layer acts as an error trace function.Because the computing layer always has an insuffi-cient variance estimation,it will lead to unstable neural network prediction.Thus,we proposed the compensation layer to trace neural network error in real-time.The numerical experiments on modeling the multiple superimposed oscillators and nonlinear data sets demonstrate that error trace reservoir structure has higher stability and generalization performance than the conventional network,especially in the high order nonlinear complex models.关键词
回声状态网络/高阶非线性复杂模型/补偿回声状态网络/多阶振荡器Key words
echo state network/high order nonlinear complex model/compensating echo state network/multiple superimposed oscillator引用本文复制引用
张昭昭,朱应钦,余文..具有双储层结构的动态误差补偿回声状态网络[J].控制理论与应用,2024,41(3):385-395,11.基金项目
陕西省自然科学基础研究计划陕煤联合基金资助项目(2019JLZ-08),陕西省自然科学基础研究计划资助项目(2020JM-522,2021JM-396)资助.Supported by the Basic Research Plan of Natural Science Foundation of Shaanxi Coal Joint Fund(2019JLZ-08)and the Basic Research Plan of Nature Science in Shaanxi Province of China(2020JM-522,2021JM-396). （2019JLZ-08）
