A new type of Echo State Network based on nonlinearreadout nodes

摘要：

　　The classical Echo state network (ESN)cannot fully exploit its advantages in some workwhich characterizestrong nonlinearity and high-order statistics.In order to overcome the shortcomings, this paper using the nonlinear readout nodesinstead of the traditional linear readout nodes in classical ESN, Radical Basis Function (RBF) neural network was introduced to read out the reservoir state.Benchmark experiments on Lorenz chaotic time series and NARMA modelidentification shown that the proposed new type of ESN canimprove the nonlinear characteristics andit”s performance exceeded the classical ESNin dealing with some higher degree of nonlinear system and model.

关键词： Echo state network linear regression nonlinear readout RBF

作者: WU Ri-na YANGLin WANGFang

作者单位: School of Information Science and Engineering,Lanzhou University,Lanzhou,730000,China;Inner Mongolia School of Information Science and Engineering,Lanzhou University,Lanzhou,730000,China

会议类型: 国内会议

会议名称: 2013年第四届全国通信新理论与新技术学术大会CTC2013

会议地点: 北京

会议语种:英文

页码: 111-116

在线出版日期: 2014-01-01（万方平台首次上网日期，不代表论文的发表时间）