Home

About

Advanced Search

Browse by Discipline

Scientific Societies

E-print Alerts

Add E-prints

E-print Network
FAQHELPSITE MAPCONTACT US


  Advanced Search  

 
FA4 -1O:OO Neural Network Construction and Rapid Learning for System Identification
 

Summary: FA4 - 1O:OO
Neural Network Construction and Rapid Learning for System Identification
John 0. Moody and Panos J. Antsaklis
Department of Electrical Engineering
University of Notre Dame
Notre Dame, IN 46556
Abstract
A very large number of potential applications
for feedforward neural networks in the field of
control theory have been proposed in recent
years. The main method used for training such
networks is gradient descent, such as the back-
propagation algorithm, which is slow and often
impractical for real time applications. In this
paper a new learning algorithm is introduced
and used to identify nonlinear functions. Its dis-
tinctive features are that it transforms the prob-
lem to a quadratic optimization problem that
is solved by a number of linear equations and
it constructs the appropriate network that will

  

Source: Antsaklis, Panos - Department of Electrical Engineering, University of Notre Dame

 

Collections: Engineering