東華大學圖書館 |

Language: English

Help

回圖書館首頁

手機版館藏查詢

Back

Switch To: Labeled | MARC Mode | ISBD

Stability analysis of recurrent neur...

Jafari, Reza.

Linked to FindBook

Google Book

Amazon

博客來

Stability analysis of recurrent neural-based controllers.

Record Type:	Language materials, printed : Monograph/item
Title/Author:	Stability analysis of recurrent neural-based controllers./
Author:	Jafari, Reza.
Description:	237 p.
Notes:	Source: Dissertation Abstracts International, Volume: 73-10(E), Section: B.
Contained By:	Dissertation Abstracts International73-10B(E).
Subject:	Biology, Neuroscience. -
Online resource:	http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=3512935
ISBN:	9781267424105

Stability analysis of recurrent neural-based controllers.
Jafari, Reza.

Stability analysis of recurrent neural-based controllers. - 237 p.

Source: Dissertation Abstracts International, Volume: 73-10(E), Section: B.

Thesis (Ph.D.)--Oklahoma State University, 2012.

Scope and Method of Study: In the last two decades, more attention has been given to Recurrent Neural Networks (RNNs) and their applications. The ability of RNNs to solve complex problems in control, system identification, signal processing, communication, pattern recognition, etc. is well understood. Although RNNs are more powerful than feedforward networks, this comes at the expense of more difficult training and the potential for instabilities. It has become more and more important to have efficient methods for determining the stability of RNNs. The purpose of this research is to develop improved methods for determining the stability of RNNs.

ISBN: 9781267424105Subjects--Topical Terms:

1017680
Biology, Neuroscience.

Stability analysis of recurrent neural-based controllers.
LDR:02278nam 2200337 4500 001 1957265
005 20131202131324.5
008 150210s2012 ||||||||||||||||| ||eng d
020 $a 9781267424105
035 $a (UMI)AAI3512935
035 $a AAI3512935
040 $a UMI $c UMI
100 1 $a Jafari, Reza. $3 2092130
245 1 0 $a Stability analysis of recurrent neural-based controllers.
300 $a 237 p.
500 $a Source: Dissertation Abstracts International, Volume: 73-10(E), Section: B.
500 $a Adviser: Martin Hagan.
502 $a Thesis (Ph.D.)--Oklahoma State University, 2012.
520 $a Scope and Method of Study: In the last two decades, more attention has been given to Recurrent Neural Networks (RNNs) and their applications. The ability of RNNs to solve complex problems in control, system identification, signal processing, communication, pattern recognition, etc. is well understood. Although RNNs are more powerful than feedforward networks, this comes at the expense of more difficult training and the potential for instabilities. It has become more and more important to have efficient methods for determining the stability of RNNs. The purpose of this research is to develop improved methods for determining the stability of RNNs.
520 $a Findings and Conclusions: The main contribution of this research is the development of an efficient algorithm to detect global asymptotic stability of RNNs and then use the stable RNNs for the purpose of control and system identification. Three Lyapunov-based algorithms, RODD-LB2, RODD-EB and RODD-Hybrid, are developed to detect global asymptotic stability of RNNs. We found that the RODD-Hybrid method generally produced the fastest and the most consistent results. The applications of the proposed algorithms have been applied to neural network control problems.
590 $a School code: 0664.
650 4 $a Biology, Neuroscience. $3 1017680
650 4 $a Engineering, General. $3 1020744
650 4 $a Engineering, Biomedical. $3 1017684
690 $a 0317
690 $a 0537
690 $a 0541
710 2 $a Oklahoma State University. $b Electrical Engineering. $3 1030588
773 0 $t Dissertation Abstracts International $g 73-10B(E).
790 1 0 $a Hagan, Martin, $e advisor
790 1 0 $a Latino, Carl $e committee member
790 1 0 $a Scheets, George $e committee member
790 1 0 $a Kable, Anthony $e committee member
790 $a 0664
791 $a Ph.D.
792 $a 2012
856 4 0 $u http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=3512935