Effect of shapes of activation functions on predictability in the echo state network
Neural and Evolutionary Computing
2019-05-24 v1 Machine Learning
Abstract
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.
Keywords
Cite
@article{arxiv.1905.09419,
title = {Effect of shapes of activation functions on predictability in the echo state network},
author = {Hanten Chang and Shinji Nakaoka and Hiroyasu Ando},
journal= {arXiv preprint arXiv:1905.09419},
year = {2019}
}