a novel model of leaky integrator echo state network for time-series prediction论文.pdf

Neurocomputing 159 (2015) 58–66 Contents lists available at ScienceDirect Neurocomputing journal homepage: /locate/neucom A novel model of leaky integrator echo state network for time-series prediction Shu-Xian Lun a, Xian-Shuang Yao b, Hong-Yun Qi b, Hai-Feng Hu b a College of New Energy, Bohai University, Jinzhou 121013, China b College of Engineering, Bohai University, Jinzhou 121013, China a r t i c l e i n f o a b s t r a c t Article history: In this paper, an improved leaky integrator echo state network is proposed. The improved model, named Received 30 December 2014 double activation functions echo state network (DAF-ESN), introduces double activation functions to Received in revised form replace the original single activation function in the reservoir state update equation. For the purely 25 January 2015 input-driven applications, the model can flexibly modify the reservoir state according to different input Accepted 9 February 2015 signals. A sufficient condition for DAF-ESN is given to guarantee that DAF-ESN has the echo state Communicated by H. Zhang Available online 23 February 2015 property. Since double activation functions are represented as the weighted sum, two new parameters are introduced. The batch gradient descent method is utilized to optimize the parameters. Finally, the Keywords: proposed method is