.png){kind=icon}
.png){kind=icon}
Return
Balanced echo state networks
.png){kind=icon}
PRE
AI
DOI：10.1016/j.neunet.2012.08.008.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
This paper investigates the interaction between the driving output feedback and the internal reservoir dynamics in echo state networks (ESNs). The interplay is studied experimentally on the multiple superimposed oscillators (MSOs) benchmark. The experimental data reveals a dual effect of the output feedback strength on the network dynamics: it drives the dynamic reservoir but it can also block suitable reservoir dynamics. Moreover, the data shows that the reservoir size crucially co-determines the likelihood of generating an effective ESN. We show that dependent on the complexity of the MSO dynamics somewhat smaller networks can yield better performance. Optimizing the output feedback weight range and the network size is thus crucial for generating an effective ESN. With proper parameter choices, we show that it is possible to generate ESNs that approximate MSOs with several orders of magnitude smaller errors than those previously reported. We conclude that there appears to be still much more potential in ESNs than previously thought and sketch-out some promising future research directions. (C) 2012 Elsevier Ltd. All rights reserved.
Keywords:
Echo state network
Output feedback
Multiple superimposed oscillator
Recurrent neural networks
Dynamic reservoir
Journal
IF:
6.3
Papers:
7.8K
Citations:
3.0W