Decouple Adversarial Capacities with Dual-Reservoir Network

Qianli Ma, Lifeng Shen, Wanqing Zhuang, Jieyu Chen

Abstract

Reservoir computing such as Echo State Network (ESN) and Liquid State Machine (LSM) has been successfully applied in dynamical system modeling. However, there is an antagonistic trade-off between the non-linear mapping capacity and the short-term memory capacity in single-reservoir networks, especially when the input signals contain high non-linearity and short-term dependencies. To address this problem, we propose a novel reservoir computing model called Dual-Reservoir Network (DRN), which connects two reservoirs with an unsupervised encoder such as PCA. Specifically, we allow these two adversarial capacities to be decoupled and enhanced in the dual reservoirs respectively. In our experiments, we first verify DRN’s feasibility on an extended polynomial system, which allows us to control the nonlinearity and short-term dependencies of data. In addition, we demonstrate the effectiveness of DRN on the synthesis and real-world time series predictions.
BibTeX
@inproceedings{ma2017decouple,
  author = {Qianli Ma and Lifeng Shen and Wanqing Zhuang and Jieyu Chen},
  title = {{Decouple Adversarial Capacities with Dual-Reservoir Network}},
  booktitle = {ICONIP},
  year = {2017},
  doi = {10.1007/978-3-319-70139-4\_48},
}

Loading related content...

Figure