Scheduled System Maintenance on May 29th, 2015:
IEEE Xplore will be upgraded between 11:00 AM and 10:00 PM EDT. During this time there may be intermittent impact on performance. We apologize for any inconvenience.
By Topic

Identification of nonlinear dynamical systems by recurrent high-order neural networks

Sign In

Cookies must be enabled to login.After enabling cookies , please use refresh or reload or ctrl+f5 on the browser for the login options.

Formats Non-Member Member
$31 $13
Learn how you can qualify for the best price for this item!
Become an IEEE Member or Subscribe to
IEEE Xplore for exclusive pricing!
close button

puzzle piece

IEEE membership options for an individual and IEEE Xplore subscriptions for an organization offer the most affordable access to essential journal articles, conference papers, standards, eBooks, and eLearning courses.

Learn more about:

IEEE membership

IEEE Xplore subscriptions

3 Author(s)
Kuroe, Y. ; Dept. of Electron. & Inf. Sci., Kyoto Inst. of Technol., Japan ; Ikeda, H. ; Mori, T.

Recently high-order neural networks have been recognized to possess higher capability of nonlinear function representations. This paper presents a method for identification of general nonlinear dynamical systems by recurrent high-order neural networks. We introduce a new architecture of the networks in which dynamic neurons and static neurons are arbitrarily connected through high-order connections. A procedure to determine structures of the networks is studied from the view of their capability of approximating nonlinear dynamical systems. We formulate an identification scheme as training problem of the networks and derive an efficient algorithm for adjusting not only their connection weights but also their initial states. The performance of the proposed method is shown through simulation studies

Published in:

Systems, Man, and Cybernetics, 1997. Computational Cybernetics and Simulation., 1997 IEEE International Conference on  (Volume:1 )

Date of Conference:

12-15 Oct 1997