Echo state networks are universal
Echo state networks are universal
复制标题
DOI：
10.1016/j.neunet.2018.08.025
复制
发表时间：
2018-12-01
期刊：
影响因子：
7.8
通讯作者：
Ortega, Juan-Pablo
中科院分区：
文献类型：
--
作者：
Grigoryeva, Lyudmila;Ortega, Juan-Pablo
本文表明，回声状态网络的背景下，离散时间衰减记忆滤波器的一致有界输入定义在负无限次的普遍一致逼近。这一结果保证了任何衰落记忆输入/输出系统在离散时间可以实现为一个简单的有限维神经网络型状态空间模型与静态线性读出映射。这种近似对于无限时间间隔都有效。这一声明的证明是基于基本的结果，也提出了在这项工作中，有关的拓扑性质的衰落的记忆属性和有关水库计算系统所产生的连续水库地图。(c)2018爱思唯尔有限公司版权所有。
This paper shows that echo state networks are universal uniform approximants in the context of discrete-time fading memory filters with uniformly bounded inputs defined on negative infinite times. This result guarantees that any fading memory input/output system in discrete time can be realized as a simple finite-dimensional neural network-type state-space model with a static linear readout map. This approximation is valid for infinite time intervals. The proof of this statement is based on fundamental results, also presented in this work, about the topological nature of the fading memory property and about reservoir computing systems generated by continuous reservoir maps. (c) 2018 Elsevier Ltd. All rights reserved.