Zobrazeno 1 - 3
of 3
pro vyhledávání: '"Xian-shuang Yao"'
Publikováno v:
Applied Soft Computing. 77:750-760
Leaky integrator echo state network (Leaky-ESN), an improved echo state network, is suitable for learning very slow dynamic systems and replaying the learnt system at different speeds. To ensure the echo state property of Leaky-ESN, spectral radius o
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::6dc19cc5c32bb3ad2e271acca49bd315
https://doi.org/10.1016/j.asoc.2019.02.005
https://doi.org/10.1016/j.asoc.2019.02.005
Publikováno v:
Information Sciences. :103-119
This paper proposes a new echo state network (ESN) with variable memory length. For input-driven applications, existing ESNs do not fully consider the characteristics of input signals and usually ignore output feedback connections. Therefore, the ech
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::f9d781acbc01669994427751fc471843
https://doi.org/10.1016/j.ins.2016.07.065
https://doi.org/10.1016/j.ins.2016.07.065
Publikováno v:
Neurocomputing. 159:58-66
In this paper, an improved leaky integrator echo state network is proposed. The improved model, named double activation functions echo state network (DAF-ESN), introduces double activation functions to replace the original single activation function
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::b49c2c31d0211a28405bfc6b6582a89d
https://doi.org/10.1016/j.neucom.2015.02.029
https://doi.org/10.1016/j.neucom.2015.02.029