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

Add code
May 22, 2019
Hanten Chang, Shinji Nakaoka, Hiroyasu Ando
Figure 1 for Effect of shapes of activation functions on predictability in the echo state network
Figure 2 for Effect of shapes of activation functions on predictability in the echo state network
Figure 3 for Effect of shapes of activation functions on predictability in the echo state network

Share this with someone who'll enjoy it:

Twitter IconFacebook IconLinkedin IconWhatsapp IconMessenger Icon

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.

View paper onarxiv icon

Share this with someone who'll enjoy it:

Twitter IconFacebook IconLinkedin IconWhatsapp IconMessenger Icon