Home

About

Advanced Search

Browse by Discipline

Scientific Societies

E-print Alerts

Add E-prints

E-print Network
FAQHELPSITE MAPCONTACT US


  Advanced Search  

 
IEEE TRANSACTIONS ON INSTRUMENTATION AND MEASUREMENT, VOL. 48, NO. 6, DECEMBER 1999 1073 Neural Modeling of Dynamic Systems
 

Summary: IEEE TRANSACTIONS ON INSTRUMENTATION AND MEASUREMENT, VOL. 48, NO. 6, DECEMBER 1999 1073
Neural Modeling of Dynamic Systems
with Nonmeasurable State Variables
Cesare Alippi, Senior Member, IEEE, and Vincenzo Piuri, Senior Member, IEEE
Abstract--The paper studies the ability possessed by recurrent
neural networks to model dynamic systems when some rele-
vant state variables are not measurable. Neural architectures
based on virtual states--which naturally arise from a space
state representation--are introduced and compared with the
more traditional neural output error ones. Despite the evident
potential model ability possessed by virtual state architectures
we experimented that their performances strongly depend on the
training efficiency. A novel validation criterion for neural output
error architectures is suggested which allows to assess the neural
network not only in terms of its approximation accuracy but also
with respect to stability issues.
Index Terms-- Dynamic systems, recurrent neural networks,
stability, training.
I. INTRODUCTION
THE development of a black-box model for a dynamic

  

Source: Alippi, Cesare - Dipartimento di Elettronica e Informazione, Politecnico di Milano

 

Collections: Computer Technologies and Information Sciences