期刊
NEUROCOMPUTING
卷 298, 期 -, 页码 4-8出版社
ELSEVIER SCIENCE BV
DOI: 10.1016/j.neucom.2017.11.076
关键词
Fisher memory of dynamical systems; Recurrent neural network; Echo State Network; Reservoir Computing
资金
- EPSRC grant Personalised Medicine Through Learning in the Model Space [EP/L000296/1]
- Biotechnology and Biological Sciences Research Council [BB/H012508/1] Funding Source: researchfish
- Engineering and Physical Sciences Research Council [EP/L000296/1] Funding Source: researchfish
- BBSRC [BB/H012508/1] Funding Source: UKRI
- EPSRC [EP/L000296/1] Funding Source: UKRI
We study asymptotic properties of Fisher memory of linear Echo State Networks with randomized symmetric state space coupling. In particular, two reservoir constructions are considered: (1) More direct dynamic coupling construction using a class of Wigner matrices and (2) positive semi-definite dynamic coupling obtained as a product of unconstrained stochastic matrices. We show that the maximal Fisher memory is achieved when the input-to-state coupling is collinear with the dominant eigenvector of the reservoir coupling matrix. In the case of Wigner reservoirs we show that as the system size grows, the contribution to the Fisher memory of self-coupling of reservoir units is negligible. We also prove that when the input-to-state coupling is collinear with the sum of eigenvectors of the state space coupling, the expected normalized memory is four and eight time smaller than the maximal memory value for the Wigner and product constructions, respectively. (C) 2018 Elsevier B.V. All rights reserved.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据