延迟回声状态神经网络用于复杂系统分析和应用

Delayed Echo State Neural Network for Analysis and Application of Complex Systems

提出一种改进的回声状态神经网络模型,用于复杂系统的长期行为分析和预测.模型通过引入隐层状态的延迟反馈体现系统过去时刻的信息对当前状态的影响,避免了传统回声状态网络方法记忆能力弱的缺点以及获得最优参数的困难.

We proposed an improved echo state neural network model for the analysis and prediction of long-term behavior of complex systems.The model introduced the delayed feedback of hidden layer state to reflect the influence of the past time information on the current state of the system,avoiding the shortcomings of weak memory ability and difficulty of obtaining optimal parameters in traditional echo state network methods.