Dynamical approximation by recurrent neural networks

doi:10.1016/S0925-2312(99)00114-9

1999-11-01

PRE

Max Garzón *

Fernanda Botelho

DOI：10.1016/S0925-2312(99)00114-9

原文链接

原文求助

摘要

En 中文

We examine the approximating power of recurrent networks for dynamical systems through an unbounded number of iterations. It is shown that the natural family of recurrent neural networks with saturated linear transfer functions and synaptic weight matrices of rank 1 are essentially equivalent to feedforward neural networks with recurrent layers. Therefore, they inherit the universal approximation property of real-valued functions in one variable in a stronger sense, namely through an unbounded number of iterations and approximation guaranteed to be within O(1/n), with n neurons and possibly lateral synapses allowed in the hidden-layer. However, they are not as complex in their dynamical behavior as systems defined by Turing machines. It is further proved that every continuous dynamical system can be approximated through all iterations, by both finite analog and boolean networks, when one requires approximation of given arbitrary exact orbits of the (perhaps unknown) map. This result no longer holds when the orbits of the given map are only available as contaminated orbits of the approximant net due to the presence of random noise (e.g., due to digital truncations of analog activations). Neural nets can nonetheless approximate large families of continuous maps, including chaotic maps and maps sensitive to initial conditions. A precise characterization of what maps can be approximated fault-tolerantly by analog and discrete neural networks for unboundedly many iterations remains an open problem. (C) 1999 Published by Elsevier Science B.V. All rights reserved.

Keyword:

analog neural network

recurrent net

Boolean net

approximation

noise

observability

computation universality

shadowing

total variation

期刊

Neurocomputing

IF:

6.5

论文数:

2.5W

被引数:

6.5W

机构

暂无机构信息

引用论文

Coliquefaction of Lignite and Corn Stalk in Ethanol–Water Mixed Solvent with Addition of Formic Acid and Iron Ore Catalyst

Energy & Fuels

IF0

2018-02-06

PREAI

Hengfu Shui; Hanren Jiao; Fang He; Tao Shui; Xiaoling Wang; Hua Zhou; Chunxiu Pan; Zhicai Wang; Zhiping Lei; Shibiao Ren; Shigang Kang; Charles Chunbao Xu

Carbon Paste Electrodes

Analytical Chemistry

IF0

2003-04-08

PREAI

Ralph N. Adams

Real-time and offline techniques for identifying obstructive sleep apnea patients 用于识别阻塞性睡眠呼吸暂停患者的实时和离线技术

2016 IEEE International Conference on Computational Intelligence and Computing Research (ICCIC)

IF0

2016-12-01

PREAI

J Dhara Prathap; Ekanath Rangan; Rahul Krishnan Pathinarupothi