摘要
混沌系统在电路、保密通讯、加密解密等方面具有重要的研究意义.由于其对初值非常敏感,传统的统计学时间序列预测方法在处理混沌时间序列预测问题是具有挑战的.回声状态网络是一种特殊的循环神经网络,在复杂动态系统动力学与控制方面具有优势.经典的回声状态网络将每个样本置于同一地位,然而实际问题中不同的样本的重要性往往是有差异的.本文提出注意力机制回声状态神经网络模型,将回声状态网络与注意力机制相结合体现样本之间的差异性以及样本之间的相互作用对预测的影响.对混沌系统的预测结果表明注意力机制回声状态神经网络具有更好的预测性能.
Chaotic systems have important research significance in circuit,secure communication,encryption and decryption.The traditional statistical time series prediction methods are challenging in dealing with the chaotic systems because the chaotic systems are very sensitive to the initial values.Echo state network is a special cyclic neural network,and has advantages in the dynamics and control of complex dynamic systems.The classical echo state network places all samples in the same importance,however in practical problems,the importance of the samples are often different.This paper proposes the attention mechanism echo state network by combining the echo state network and the attention machine to reflect the differences and interactions between samples.The prediction results on chaotic systems show that the prediction performance of the echo state network with attention mechanism is better than that of the classical methods.
作者
刘建明
徐一宸
Liu Jianming;Xu Yichen(College of Mathematics,Jilin University,Changchun 130012,China;School of Information,Renmin University of China,Beijing 100872,China)
出处
《动力学与控制学报》
2023年第8期31-37,共7页
Journal of Dynamics and Control
基金
国家自然科学基金资助项目(12072128)
吉林大学研究生教改项目(2021JGZ26,2021JGZ15)。
关键词
混沌系统
回声状态网络
储备池计算
注意力机制
机器学习
chaotic systems
echo state network
reservoir computing
attention mechanism
machine learning
