Complete controllability of continuous-time recurrent neural networks

Eduardo Sontag; Héctor Sussmann

doi:10.1016/S0167-6911(97)00002-9

Complete controllability of continuous-time recurrent neural networks

Eduardo Sontag, Héctor Sussmann

Research output: Contribution to journal › Article › peer-review

31 Scopus citations

Abstract

This paper studies controllability for the class of control systems commonly called (continuous-time) recurrent neural networks. It is shown that, under a generic condition on the input matrix, the system is controllable, for every possible state matrix. The result holds when the activation function is the hyperbolic tangent.

Original language	English (US)
Pages (from-to)	177-183
Number of pages	7
Journal	Systems and Control Letters
Volume	30
Issue number	4
DOIs	https://doi.org/10.1016/S0167-6911(97)00002-9
State	Published - May 1997

All Science Journal Classification (ASJC) codes

Control and Systems Engineering
Computer Science(all)
Mechanical Engineering
Electrical and Electronic Engineering

Keywords

Global stabilization
Linear discrete-time systems
Saturated feedback

Access to Document

10.1016/S0167-6911(97)00002-9

Cite this

@article{7cc43d6b0a7444aaa37fba03b22edbd6,

title = "Complete controllability of continuous-time recurrent neural networks",

abstract = "This paper studies controllability for the class of control systems commonly called (continuous-time) recurrent neural networks. It is shown that, under a generic condition on the input matrix, the system is controllable, for every possible state matrix. The result holds when the activation function is the hyperbolic tangent.",

keywords = "Global stabilization, Linear discrete-time systems, Saturated feedback",

author = "Eduardo Sontag and H{\'e}ctor Sussmann",

note = "Funding Information: *Corresponding author. E-mail: sontag@control.rutgers.edu. 1Supported in part by L S Air Force Grant AFOSR-94-0293.",

year = "1997",

month = may,

doi = "10.1016/S0167-6911(97)00002-9",

language = "English (US)",

volume = "30",

pages = "177--183",

journal = "Systems and Control Letters",

issn = "0167-6911",

publisher = "Elsevier",

number = "4",

}

TY - JOUR

T1 - Complete controllability of continuous-time recurrent neural networks

AU - Sontag, Eduardo

AU - Sussmann, Héctor

N1 - Funding Information: *Corresponding author. E-mail: sontag@control.rutgers.edu. 1Supported in part by L S Air Force Grant AFOSR-94-0293.

PY - 1997/5

Y1 - 1997/5

N2 - This paper studies controllability for the class of control systems commonly called (continuous-time) recurrent neural networks. It is shown that, under a generic condition on the input matrix, the system is controllable, for every possible state matrix. The result holds when the activation function is the hyperbolic tangent.

AB - This paper studies controllability for the class of control systems commonly called (continuous-time) recurrent neural networks. It is shown that, under a generic condition on the input matrix, the system is controllable, for every possible state matrix. The result holds when the activation function is the hyperbolic tangent.

KW - Global stabilization

KW - Linear discrete-time systems

KW - Saturated feedback

UR - http://www.scopus.com/inward/record.url?scp=0031146078&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0031146078&partnerID=8YFLogxK

U2 - 10.1016/S0167-6911(97)00002-9

DO - 10.1016/S0167-6911(97)00002-9

M3 - Article

AN - SCOPUS:0031146078

SN - 0167-6911

VL - 30

SP - 177

EP - 183

JO - Systems and Control Letters

JF - Systems and Control Letters

IS - 4

ER -

Complete controllability of continuous-time recurrent neural networks

Abstract

All Science Journal Classification (ASJC) codes

Keywords

Access to Document

Other files and links

Fingerprint

Cite this