JAIST Repository >
School of Information Science >
Articles >
Journal Articles >

Please use this identifier to cite or link to this item: http://hdl.handle.net/10119/4899

Title: Back-Propagation Learning of Infinite-Dimensional Dynamical Systems
Authors: Tokuda, Isao
Tokunaga, Ryuji
Aihara, Kazuyuki
Keywords: back-propagation learning
time-delay
recurrent neural network
retarded functional differential equations
infinite-dimensional dynamical system
Issue Date: 2003-10
Publisher: Elsevier
Magazine name: Neural Networks
Volume: 16
Number: 8
Start page: 1179
End page: 1193
DOI: 10.1016/S0893-6080(03)00076-5
Abstract: This paper presents numerical studies of applying back-propagation learning to a delayed recurrent neural network (DRNN). The DRNN is a continuoustime recurrent neural network having time delayed feedbacks and the backpropagation learning is to teach spatio-temporal dynamics to the DRNN. Since the time-delays make the dynamics of the DRNN infinite-dimensional, the learning algorithm and the learning capability of the DRNN are different from those of the ordinary recurrent neural network (ORNN) having no time-delays. First, two types of learning algorithms are developed for a class of DRNNs. Then, using chaotic signals generated from the Mackey- Glass equation and the R¨ossler equations, learning capability of the DRNN is examined. Comparing the learning algorithms, learning capability, and robustness against noise of the DRNN with those of the ORNN and time delay neural network (TDNN), advantages as well as disadvantages of the DRNN are investigated.
Rights: NOTICE: This is the author's version of a work accepted for publication by Elsevier. Isao Tokuda, Ryuji Tokunaga and Kazuyuki Aihara, Neural Networks, 16(8), 2003, 1179-1193, http://dx.doi.org/10.1016/S0893-6080(03)00076-5
URI: http://hdl.handle.net/10119/4899
Material Type: author
Appears in Collections:b10-1. 雑誌掲載論文 (Journal Articles)

Files in This Item:

File Description SizeFormat
C6289.pdf385KbAdobe PDFView/Open

All items in DSpace are protected by copyright, with all rights reserved.

 


Contact : Library Information Section, JAIST (ir-sys[at]ml.jaist.ac.jp)