论文信息 - Effect of shapes of activation functions on predictability in the echo state network

Effect of shapes of activation functions on predictability in the echo state network

We investigate prediction accuracy for time series of Echo state networks with respect to several kinds of activation functions. As a result, we found that some kinds of activation functions with an appropriate nonlinearity show high performance compared to the conventional sigmoid function.

Hiroyasu Ando | Shinji Nakaoka | Hanten Chang

[1] Cheng-jian Wei,et al. Harnessing Non-linearity by Sigmoid-wavelet Hybrid Echo State Networks (SWHESN) , 2006, 2006 6th World Congress on Intelligent Control and Automation.

[2] Herbert Jaeger,et al. Reservoir computing approaches to recurrent neural network training , 2009, Comput. Sci. Rev..

[3] Takashi Ikegami,et al. A Reservoir Computing approach to Image Classification using Coupled Echo State and BackPropagation Neural Networks , 2011 .

[4] M. Muskulus,et al. Wasserstein distances in the analysis of time series and dynamical systems , 2011 .

[5] Harald Haas,et al. Harnessing Nonlinearity: Predicting Chaotic Systems and Saving Energy in Wireless Communication , 2004, Science.